Search

Autonomous driving, as a pivotal technology in modern transportation, is progressively transforming the modalities of human mobility. In this domain, vehicle detection is a significant research direction that involves the intersection of multiple disciplines, including sensor technology and computer vision. In recent years, many excellent vehicle detection methods have been reported, but few studies have focused on summarizing and analyzing these algorithms. This work provides a comprehensive review of existing vehicle detection algorithms and discusses their practical applications in the field of autonomous driving. First, we provide a brief description of the tasks, evaluation metrics, and datasets for vehicle detection. Second, more than 200 classical and latest vehicle detection algorithms are summarized in detail, including those based on machine vision, LiDAR, millimeter-wave radar, and sensor fusion. Finally, this article discusses the strengths and limitations of different algorithms and sensors, and proposes future trends. [ABSTRACT FROM AUTHOR]

In recent years, the proliferation of vehicles on roadways, accompanied by an escalating demand for augmented safety and refined traffic management, has fueled substantial progress in the domains of computer vision and deep learning methodologies. This technological surge has precipitated ground-breaking applications, with real-time vehicle detection emerging as a linchpin. Capability to accurately detect vehicles in a real-time holds profound implications across diverse domains. In the context of autonomous driving, it underpins essential functions such as path planning, collision avoidance, and decision-making, essential for the safe operation of autonomous vehicles. In the arena of traffic monitoring, it empowers transportation authorities to acquire real-time insights into traffic dynamics, congestion patterns, and incident detection, thereby optimizing traffic flow and resource allocation strategies. Furthermore, within surveillance systems, real-time vehicle detection equips security personnel with the means to swiftly identify potential security threats, enhancing overall situational awareness and safety. This paper contributes to this dynamic landscape by introducing an innovative architecture expressly crafted for vehicle detection. Leveraging state-of-the-art computer vision techniques and deep learning methodologies, this architecture addresses the evolving challenges posed by contemporary traffic scenarios. Through the enhancement of real-time vehicle detection capabilities, our aim is to fortify the foundations of safety, efficiency, and security within vehicular contexts. The paper includes a fusion of AlexNet and Darknet accompanied by a comparative analysis. It is expected to deliver unmatched dependability and accuracy in real-time traffic monitoring, setting a new standard for performance in this application. [ABSTRACT FROM AUTHOR]

This research paper highlights the significance of vehicle detection in aerial images for surveillance systems, focusing on deep learning methods that outperform traditional approaches. However, the challenge of high computation complexity due to diverse vehicle appearances persists. The motivation behind this study is to highlight the crucial role of vehicle detection in aerial images for surveillance systems, emphasizing the superior performance of deep learning methods compared to traditional approaches. To address this, a lightweight deep neural network-based model is developed, striking a balance between accuracy and efficiency enabling real-time operation. The model is trained and evaluated on a standardized dataset, with extensive experiments demonstrating its ability to achieve accurate vehicle detection with significantly reduced computation costs, offering a practical solution for real-world aerial surveillance scenarios. [ABSTRACT FROM AUTHOR]

Surveillance cameras can provide more accurate traffic information compared to GPS and infrared radiation sensors. With the intelligent processing of image information provided by them, the analysis of traffic problems is done more precisely. Meanwhile, the speed of car positioning is of particular importance because, after positioning the car, other processes are needed to make decisions that require time management. The purpose of the present study is to propose an algorithm based on deep networks that solves this challenge. In the presented algorithm, a fast and accurate detector network is designed based on multiple receptive fields, segmentation, and differential images, which increases the accuracy of the detector by producing semantic feature maps and filtering them. Also, it increases detector speed by reducing the parameters. Each vehicle's maneuver is decided based on the time and location information of that vehicle and the vehicles nearby. Then, according to the type of maneuver, the predictive network is selected in one of the modes of lane keeping, left turn or right turn. The networks designed in the proposed algorithm are complementary to each other. The performance of the proposed algorithm is demonstrated by experiments on the Highway and UADETRAC datasets. [ABSTRACT FROM AUTHOR]

This paper presents our research on a traffic signal control system (TSCS) at V2X intersections. The overall objective of the study is to create an implementable TSCS. The specific objective of this paper is to investigate a distributed system towards implementation. The objective function of minimizing queue delay is formulated as the integral of queue lengths. The discrete queueing estimation is mixed with macro and micro traffic flow models. The novel proposed architecture alleviates the communication network bandwidth constraint by processing BSMs and computing queue lengths at the local intersection. In addition, a two-stage distributed system is designed to optimize offsets, splits, and cycle length simultaneously and in real time. The paper advances TSCS theories by contributing a novel analytic formulation of delay functions and their first degree of derivatives for a two-stage optimization model. The open-source traffic simulation engine Enhanced Transportation Flow Open-Source Microscopic Model (ETFOMM version 1.2) was selected as a simulation environment to develop, debug, and evaluate the models and the system. The control delay of the major direction, minor direction, and the total network were collected to assess the system performance. Compared with the optimized TSCS timing plan by the Virginia Department of Transportation, the system generated a 21% control delay reduction in the major direction and a 7% control delay reduction in the minor direction at just a 10% penetration rate of connected vehicles. Finally, the proposed distributed and centralized systems present similar performances in the case study. [ABSTRACT FROM AUTHOR]

The lack of discernible vehicle contour features in low-light conditions poses a formidable challenge for nighttime vehicle detection under hardware cost constraints. Addressing this issue, an enhanced histogram of oriented gradients (HOGs) approach is introduced to extract relevant vehicle features. Initially, vehicle lights are extracted using a combination of background illumination removal and a saliency model. Subsequently, these lights are integrated with a template-based approach to delineate regions containing potential vehicles. In the next step, the fusion of superpixel and HOG (S-HOG) features within these regions is performed, and the support vector machine (SVM) is employed for classification. A non-maximum suppression (NMS) method is applied to eliminate overlapping areas, incorporating the fusion of vertical histograms of symmetrical features of oriented gradients (V-HOGs). Finally, the Kalman filter is utilized for tracking candidate vehicles over time. Experimental results demonstrate a significant improvement in the accuracy of vehicle recognition in nighttime scenarios with the proposed method. [ABSTRACT FROM AUTHOR]

A vision-based autonomous driving perception system necessitates the accomplishment of a suite of tasks, including vehicle detection, drivable area segmentation, and lane line segmentation. In light of the limited computational resources available, multi-task learning has emerged as the preeminent methodology for crafting such systems. In this article, we introduce a highly efficient end-to-end multi-task learning model that showcases promising performance on all fronts. Our approach entails the development of a reliable feature extraction network by introducing a feature extraction module called C2SPD. Moreover, to account for the disparities among various tasks, we propose a dual-neck architecture. Finally, we present an optimized design for the decoders of each task. Our model evinces strong performance on the demanding BDD100K dataset, attaining remarkable accuracy (Acc) in vehicle detection and superior precision in drivable area segmentation (mIoU). In addition, this is the first work that can process these three visual perception tasks simultaneously in real time on an embedded device Atlas 200I A2 and maintain excellent accuracy. [ABSTRACT FROM AUTHOR]

A vehicle detection algorithm is an indispensable component of intelligent traffic management and control systems, influencing the efficiency and functionality of the system. In this paper, we propose a lightweight improvement method for the YOLOv5 algorithm based on integrated perceptual attention, with few parameters and high detection accuracy. First, we propose a lightweight module IPA with a Transformer encoder based on integrated perceptual attention, which leads to a reduction in the number of parameters while capturing global dependencies for richer contextual information. Second, we propose a lightweight and efficient multiscale spatial channel reconstruction (MSCCR) module that does not increase parameter and computational complexity and facilitates representative feature learning. Finally, we incorporate the IPA module and the MSCCR module into the YOLOv5s backbone network to reduce model parameters and improve accuracy. The test results show that, compared with the original model, the model parameters decrease by about 9%, the average accuracy (mAP@50) increases by 3.1%, and the FLOPS does not increase. [ABSTRACT FROM AUTHOR]

The availability of transportation is considered a significant hallmark of a developed society. Since the evolution of the human species, the imperative to relocate from one location to another has been a fundamental requirement. At present, there exists a plethora of transportation options in Indonesia. However, most individuals favor road transportation due to its ease and convenience. The rise in population has led to a corresponding increase in the number of vehicles on the roadways. Hence, it presents a challenge for security authorities and governmental bodies to oversee all automobiles' mobility across various locations effectively. The present study proposes a methodology for detecting and tracking vehicles using video-based techniques. The process's initial stages involve preprocessing, including frame conversion and background subtraction. Next, the process of detecting vehicles involves the utilization of change detection and a model of body shape. Subsequently, the next stage entails the feature extraction process, focusing on extracting energy features and directional cosine. Subsequently, a technique for optimizing data is employed on the vector comprising excessively extracted features. The methodology integrates a data mining technique based on association rules, which is subsequently complemented by a random forest classification algorithm. The approach generally integrates multiple methodologies to attain effective and precise identification of automobiles in video-derived datasets. [ABSTRACT FROM AUTHOR]

Accurate identification of vehicles and estimating density in traffic surveillance systems is a challenging task, particularly in scenarios with closely spaced lanes. Single Shot MultiBox Detector (SSD) is introduced in vehicle detection and classification due to its speed and accuracy. It utilizes a transfer learning technique that enables them to utilize features from pretrained Convolutional Neural Networks (CNNs). Although the utilization of multi-scale feature maps in SSD has achieved efficient results in vehicle detection, it struggles to identify key features of vehicles due to its one-stage detection approach. Furthermore, the use of VGG16 as the backbone network in these approaches leads to the loss of fine-grained details, posing challenges in accurately localizing and classifying small vehicles. Also, there is no interaction between high- and low-level features, which restricts the networks ability to effectively integrate and utilize both features for accurate vehicle detection. To overcome these limitations, an improved SSD approach is introduced in this paper, leveraging interactive multi-scale attention characteristics to accurately detect and classify vehicles. This approach utilizes ResNet50 as the network backbone to overcome the limitations of traditional SSDs in detecting small vehicles. Also, an attention block is incorporated into it to focus on key details and assign higher attention to relevant pixels within the feature map. Also, the network employs a parallel detection framework and shares multi-scale layers (both high and low), enabling efficient detection of vehicles with various sizes. Then, traffic density is estimated based on the weights assigned to the categorized vehicles obtained from the improved SSD and the recorded area. Finally, traffic is classified as high, low, or moderate by comparing the estimated density to a threshold value. By adding attention characteristics of different scales to the original detection branch and replacing the VGG16 with ResNet50 of the SSD technique using our method, the feature representation capability and detection accuracy are both significantly improved. [ABSTRACT FROM AUTHOR]

Two-wheeled non-motorized vehicles (TNVs) have become the primary mode of transportation for short-distance travel among residents in many underdeveloped cities in China due to their convenience and low cost. However, this trend also brings corresponding risks of traffic accidents. Therefore, it is necessary to analyze the driving behavior characteristics of TNVs through their trajectory data in order to provide guidance for traffic safety. Nevertheless, the compact size, agile steering, and high maneuverability of these TNVs pose substantial challenges in acquiring high-precision trajectories. These characteristics complicate the tracking and analysis processes essential for understanding their movement patterns. To tackle this challenge, we propose an enhanced You Only Look Once Version X (YOLOx) model, which incorporates a median pooling-Convolutional Block Attention Mechanism (M-CBAM). This model is specifically designed for the detection of TNVs, and aims to improve accuracy and efficiency in trajectory tracking. Furthermore, based on this enhanced YOLOx model, we have developed a micro-trajectory data mining framework specifically for TNVs. Initially, the paper establishes an aerial dataset dedicated to the detection of TNVs, which then serves as a foundational resource for training the detection model. Subsequently, an augmentation of the Convolutional Block Attention Mechanism (CBAM) is introduced, integrating median pooling to amplify the model's feature extraction capabilities. Subsequently, additional detection heads are integrated into the YOLOx model to elevate the detection rate of small-scale targets, particularly focusing on TNVs. Concurrently, the Deep Sort algorithm is utilized for the precise tracking of vehicle targets. The process culminates with the reconstruction of trajectories, which is achieved through a combination of video stabilization, coordinate mapping, and filtering denoising techniques. The experimental results derived from our self-constructed dataset reveal that the enhanced YOLOx model demonstrates superior detection performance in comparison to other analogous methods. The comprehensive framework accomplishes an average trajectory recall rate of 85% across three test videos. This significant achievement provides a reliable method for data acquisition, which is essential for investigating the micro-level operational mechanisms of TNVs. The results of this study can further contribute to the understanding and improvement of traffic safety on mixed-use roads. [ABSTRACT FROM AUTHOR]

Recently, there has been a significant increase in the use of deep learning and low-computing edge devices for analysis of video-based systems, particularly in the field of intelligent transportation systems (ITS). One promising application of computer vision techniques in ITS is in the development of lowcomputing and accurate vehicle counting systems that can be used to eliminate dependence on external cloud computing resources. This paper proposes a compact, reliable and real-time vehicle counting solution which can be deployed on low-computational requirement edge computing devices. The system makes use of a custom-built vehicle detection algorithm based on the you only look once version 8 nano (YOLOv8n), combined with a deep association metric (DeepSORT) object tracking algorithm and an efficient vehicle counting method for accurate counting of vehicles in highway scenes. The system is trained to detect, track and count four distinct vehicle classeses, namely: car, motorcycle, bus, and truck. The proposed system was able to achieve an average vehicle detection mean average precision (mAP) score of 97.5%, a vehicle counting accuracy score of 96.8% and an average speed of 19.4 frames per second (FPS), all while being deployed on a compact Nvidia Jetson Nano edge-computing device. The proposed system outperforms other previously proposed tools in terms of both accuracy and speed. [ABSTRACT FROM AUTHOR]

Recent advancements in computer vision technology, developments in sensors and sensor-collecting approaches, and the use of deep and transfer learning approaches have excelled in the development of autonomous vehicles. On-road vehicle detection has become a task of significant importance, especially due to exponentially increasing research on autonomous vehicles during the past few years. With high-end computing resources, a large number of deep learning models have been trained and tested for on-road vehicle detection recently. Vehicle detection may become a challenging process especially due to varying light and weather conditions like night, snow, sand, rain, foggy conditions, etc. In addition, vehicle detection should be fast enough to work in real time. This study investigates the use of the recent YOLO version, YOLOx, to detect vehicles in bad weather conditions including rain, fog, snow, and sandstorms. The model is tested on the publicly available benchmark dataset DAWN containing images containing four bad weather conditions, different illuminations, background, and number of vehicles in a frame. The efficacy of the model is evaluated in terms of precision, recall, and mAP. The results exhibit the better performance of YOLOx-s over YOLOx-m and YOLOx-l variants. YOLOx-s has 0.8983 and 0.8656 mAP for snow and sandstorms, respectively, while its mAP for rain and fog is 0.9509 and 0.9524, respectively. The performance of models is better for snow and foggy weather than rainy weather sandstorms. Further experiments indicate that enhancing image quality using multiscale retinex improves YOLOx performance. [ABSTRACT FROM AUTHOR]

The utilization of remote sensing products for vehicle detection through deep learning has gained immense popularity, especially due to the advancement of unmanned aerial vehicles (UAVs). UAVs offer millimeter-level spatial resolution at low flight altitudes, which surpasses traditional airborne platforms. Detecting vehicles from very high-resolution UAV data is crucial in numerous applications, including parking lot and highway management, traffic monitoring, search and rescue missions, and military operations. Obtaining UAV data at desired periods allows the detection and tracking of target objects even several times during a day. Despite challenges such as diverse vehicle characteristics, traffic congestion, and hardware limitations, the detection task must be executed swiftly and accurately. This study successfully achieved automated detection and instance segmentation of parked and moving vehicles across a large university campus by employing the robust learning capabilities of the You Only Look Once version 7 (YOLOv7) deep learning algorithm. The generation of an ultrahigh-resolution orthomosaic of the university campus was accomplished through photogrammetric processing, employing 20-megapixel aerial images obtained from RGB UAV flights with polygonal nadir-view and bundle-grid oblique-view imaging geometries. The vehicle dataset was created by cropping image patches containing vehicle objects from the orthomosaic and manually labeling the boundaries of the vehicle targets using the LabelMe annotation tool. After expanding the dataset by applying data augmentation, the YOLOv7 algorithm was trained and tested using the transfer learning approach. The accuracy metric of precision, recall, and mAP@0.50 scores for the bounding boxes and masks of vehicles were estimated as 99.79, 97.54, and 99.46%, respectively. In addition, the robustness of the trained algorithm was also tested on a short video and (> 80%) prediction scores were achieved. [ABSTRACT FROM AUTHOR]

Vehicle detection is crucial for traffic surveillance and assisted driving. To overcome the loss of efficiency, accuracy, and stability in low-light conditions, we propose a lightweight "You Only Look Once" (YOLO) detection model. A polarized self-attention-enhanced aggregation feature pyramid network is used to improve feature extraction and fusion in low-light scenarios, and enhanced "Swift" spatial pyramid pooling is used to reduce model parameters and enhance real-time nighttime detection. To address imbalanced low-light samples, we integrate an anchor mechanism with a focal loss to improve network stability and accuracy. Ablation experiments show the superior accuracy and real-time performance of our Light-YOLO model. Compared with EfficientNetv2-YOLOv5, Light-YOLO boosts mAP@0.5 and mAP@0.5:0.95 by 4.03 and 2.36%, respectively, cuts parameters by 44.37%, and increases recognition speed by 20.42%. Light-YOLO competes effectively with advanced lightweight networks and offers a solution for efficient nighttime vehicle-detection. [ABSTRACT FROM AUTHOR]

Rear‐lamp tracking at night is a research topic in night vision that is essential for Advanced Driver Assistance Systems (ADAS). Most current computer vision‐based methods address this problem using color features because rear lamps are lit during night driving. However, such methods are sufficiently robust in complex environments owing to the lack of feature diversity. On the other hand, as there is no off‐the‐shelf dataset, the application of deep learning to nighttime rear‐lamp tracking has been sparsely explored. To tackle the above issues, in this paper, we propose hierarchical rear‐lamp tracking at nighttime (H‐RTN) and create a novel dataset for rear‐lamp tracking. Specifically, the H‐RTN consists of a rough detection hierarchy (R‐hierarchy), an accurate detection hierarchy (A‐hierarchy), and an optimization hierarchy (O‐hierarchy). The R‐hierarchy determines the region of interest (ROI) containing the target rear lamps, the A‐hierarchy samples the rear‐lamp candidates in the ROI, and the O‐hierarchy selects the best pair of candidates as the final location of the target rear lamps. The experimental results show that H‐RTN outperforms the alternative existing methods. © 2023 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

Accurate traffic data is crucial for a range of different applications such as quantifying vehicle emissions, and transportation planning and management. However, the availability of traffic data is geographically fragmented and is rarely held in an accessible form. Therefore, there is an urgent need for a common approach to developing large urban traffic data sets. Utilising satellite data to estimate traffic data offers a cost-effective and standardized alternative to ground-based traffic monitoring. This study used high-resolution satellite imagery (WorldView-2 and 3) and Deep Learning (DL) to identify vehicles, road by road, in Barcelona (2017–2019). The You Only Look Once (YOLOv3) object detection model was trained and model accuracy was investigated via parameters such as training data set specific anchor boxes, network resolution, image colour band composition and input image size. The best performing vehicle detection model configuration had a precision (proportion of positive detections that were correct) of 0.69 and a recall (proportion of objects in the image correctly identified) of 0.79. We demonstrated that high-resolution satellite imagery and object detection models can be utilised to identify vehicles at a city scale. However, the approach highlights challenges relating to identifying vehicles on narrow roads, in shadow, under vegetation, and obstructed by buildings. This is the first time that DL has been used to identify vehicles at a city scale and demonstrates the possibility of applying these methods to cities globally where data are often unavailable. [ABSTRACT FROM AUTHOR]

Traffic flow analysis is essential to develop smart urban mobility solutions. Although numerous tools have been proposed, they employ only a small number of parameters. To overcome this limitation, an edge computing solution is proposed based on nine traffic parameters, namely, vehicle count, direction, speed, and type, flow, peak hour factor, density, time headway, and distance headway. The proposed low-cost solution is easy to deploy and maintain. The sensor node is comprised of a Raspberry Pi 4, Pi camera, Intel Movidius Neural Compute Stick 2, Xiaomi MI Power Bank, and Zong 4G Bolt+. Pre-trained models from the OpenVINO Toolkit are employed for vehicle detection and classification, and a centroid tracking algorithm is used to estimate vehicle speed. The measured traffic parameters are transmitted to the ThingSpeak cloud platform via 4G. The proposed solution was field-tested for one week (7 h/day), with approximately 10,000 vehicles per day. The count, classification, and speed accuracies obtained were 79.8%, 93.2%, and 82.9%, respectively. The sensor node can operate for approximately 8 h with a 10,000 mAh power bank and the required data bandwidth is 1.5 MB/h. The proposed edge computing solution overcomes the limitations of existing traffic monitoring systems and can work in hostile environments. [ABSTRACT FROM AUTHOR]

A YOLOv7-based vehicle detection method was proposed for the vehicle leakage detection problem under road monitor. Firstly, vehicle dataset were established from the angle of a transportation surveillance. Then GhostNet was combined with YOLOv7 to lighten the network. At last, a channel attention module was added for the effective feature layer to lower the probability of leak detection. The experimental results show that detection accuracy of the improved YOLOv7 is 90.37%, which is 1.73 percentage points better than the original YOLOv7. Additionally, the model parameter size has been reduced by 14.83% and the floating-point computation has decreased by 54.73%. The improved method effectively improves the vehicle target detection accuracy while lightweighting the model, which can provide a reference for vehicle detection in traffic monitoring. [ABSTRACT FROM AUTHOR]

Summary: Several autonomous traffic monitoring systems have been created as a result of the growing number of vehicles in urban areas. Traffic surveillance systems that use roadside cameras, in particular, are becoming widely used for traffic management. For an efficient traffic control and vehicle navigation system, accurate traffic flow information must be obtained based on the vehicles detected in surveillance videos. However, vehicles of various scales are difficult to spot in traffic surveillance videos due to the presence of barricades, other vehicles, and the impact of poor lighting. Also, adverse weather conditions like snow, fog, and heavy rain diminish the visual quality of the surveillance footage. This paper proposes multi‐scale dense nested deep CNN (MSDN‐DCNN) and regional search grasshopper optimization algorithm (RS‐GOA) framework to accurately detect the vehicles, estimate the traffic flow, and find the optimal path with less travel time. First, the surveillance videos are pre‐processed, which includes frame conversion, redundancy removal, and image enhancement. The pre‐processed frames are given as input to the MSDN‐DCNN for multi‐scale vehicle detection. The detected results are used for vehicle counting and estimating the traffic flow. Finally, the optimal path is chosen based on the traffic flow information by using the RS‐GOA algorithm. The performance of the proposed method is compared with the existing vehicle detection and path selection techniques. The results illustrate that the proposed Deep CNN‐RS‐GOA framework has improved performance with high detection accuracy (91.03%), high speed (53.9 fps), less running time (1,000 ms), less travel time, and faster convergence. [ABSTRACT FROM AUTHOR]

Vehicle detection using data fusion techniques from overhead platforms (RGB/MSI imagery and LiDAR point clouds) with vector and shape data can be a powerful tool in a variety of fields, including, but not limited to, national security, disaster relief efforts, and traffic monitoring. Knowing the location and number of vehicles in a given area can provide insight into the surrounding activities and patterns of life, as well as support decision-making processes. While researchers have developed many approaches to tackling this problem, few have exploited the multi-data approach with a classical technique. In this paper, a primarily LiDAR-based method supported by RGB/MSI imagery and road network shapefiles has been developed to detect stationary vehicles. The addition of imagery and road networks, when available, offers an improved classification of points from LiDAR data and helps to reduce false positives. Furthermore, detected vehicles can be assigned various 3D, relational, and spectral attributes, as well as height profiles. This method was evaluated on the Houston, TX dataset provided by the IEEE 2018 GRSS Data Fusion Contest, which includes 1476 ground truth vehicles from LiDAR data. On this dataset, the algorithm achieved a 92% precision and 92% recall. It was also evaluated on the Vaihingen, Germany dataset provided by ISPRS, as well as data simulated using an image generation model called DIRSIG. Some known limitations of the algorithm include false positives caused by low vegetation and the inability to detect vehicles (1) in extremely close proximity with high precision and (2) from low-density point clouds. [ABSTRACT FROM AUTHOR]

In the field of object detection algorithms, the task of infrared vehicle detection holds significant importance. By utilizing infrared sensors, this approach detects the thermal radiation emitted by vehicles, enabling robust vehicle detection even during nighttime or adverse weather conditions, thus enhancing traffic safety and the efficiency of intelligent driving systems. Current techniques for infrared vehicle detection encounter difficulties in handling low contrast, detecting small objects, and ensuring real-time performance. In the domain of lightweight object detection algorithms, certain existing methodologies face challenges in effectively balancing detection speed and accuracy for this specific task. In order to address this quandary, this paper presents an improved algorithm, called YOLO-IR-Free, an anchor-free approach based on improved attention mechanism YOLOv7 algorithm for real-time detection of infrared vehicles, to tackle these issues. We introduce a new attention mechanism and network module to effectively capture subtle textures and low-contrast features in infrared images. The use of an anchor-free detection head instead of an anchor-based detection head is employed to enhance detection speed. Experimental results demonstrate that YOLO-IR-Free outperforms other methods in terms of accuracy, recall rate, and average precision scores, while maintaining good real-time performance. [ABSTRACT FROM AUTHOR]

Remote sensing (RS) data can be attained from different sources, such as drones, satellites, aerial platforms, or street-level cameras. Each source has its own characteristics, including the spectral bands, spatial resolution, and temporal coverage, which may affect the performance of the vehicle detection algorithm. Vehicle detection for urban applications using remote sensing imagery (RSI) is a difficult but significant task with many real-time applications. Due to its potential in different sectors, including traffic management, urban planning, environmental monitoring, and defense, the detection of vehicles from RS data, such as aerial or satellite imagery, has received greater emphasis. Machine learning (ML), especially deep learning (DL), has proven to be effective in vehicle detection tasks. A convolutional neural network (CNN) is widely utilized to detect vehicles and automatically learn features from the input images. This study develops the Improved Deep Learning-Based Vehicle Detection for Urban Applications using Remote Sensing Imagery (IDLVD-UARSI) technique. The major aim of the IDLVD-UARSI method emphasizes the recognition and classification of vehicle targets on RSI using a hyperparameter-tuned DL model. To achieve this, the IDLVD-UARSI algorithm utilizes an improved RefineDet model for the vehicle detection and classification process. Once the vehicles are detected, the classification process takes place using the convolutional autoencoder (CAE) model. Finally, a Quantum-Based Dwarf Mongoose Optimization (QDMO) algorithm is applied to ensure an optimal hyperparameter tuning process, demonstrating the novelty of the work. The simulation results of the IDLVD-UARSI technique are obtained on a benchmark vehicle database. The simulation values indicate that the IDLVD-UARSI technique outperforms the other recent DL models, with maximum accuracy of 97.89% and 98.69% on the VEDAI and ISPRS Potsdam databases, respectively. [ABSTRACT FROM AUTHOR]

By the end of the 2020s, full autonomy in autonomous driving may become commercially viable in certain regions. However, achieving Level 5 autonomy requires crucial collaborations between vehicles and infrastructure, necessitating high-speed data processing and low-latency capabilities. This paper introduces a vehicle tracking algorithm based on roadside LiDAR (light detection and ranging) infrastructure to reduce the latency to 100 ms without compromising the detection accuracy. We first develop a vehicle detection architecture based on ResNet18 that can more effectively detect vehicles at a full frame rate by improving the BEV mapping and the loss function of the optimizer. Then, we propose a new three-stage vehicle tracking algorithm. This algorithm enhances the Hungarian algorithm to better match objects detected in consecutive frames, while time–space logicality and trajectory similarity are proposed to address the short-term occlusion problem. Finally, the system is tested on static scenes in the KITTI dataset and the MATLAB/Simulink simulation dataset. The results show that the proposed framework outperforms other methods, with F1-scores of 96.97% and 98.58% for vehicle detection for the KITTI and MATLAB/Simulink datasets, respectively. For vehicle tracking, the MOTA are 88.12% and 90.56%, and the ID-F1 are 95.16% and 96.43%, which are better optimized than the traditional Hungarian algorithm. In particular, it has a significant improvement in calculation speed, which is important for real-time transportation applications. [ABSTRACT FROM AUTHOR]

Nowadays, deploying an intelligent vehicle detection system (IVDS) in diverse traffic is a work priority. It provides real-time traffic information with vehicle counts and types of vehicles. IVDS deployment in diverse traffic is challenging because different vehicle classes occlude each other on the road. In recent years, convolutional neural network (CNN) based deep learning (DL) methods have attained incredible progress in implementing IVDS. However, most CNN-based DL methods do not include diverse traffic conditions in Asian countries. Also, due to existing feature extraction backbones, they cannot accurately detect multi-scale vehicles. This work proposes an advanced visual computing deep learning (AVCDL) method with a vast labeled vehicle dataset to detect vehicles in diverse traffic. It includes an ensemble backbone and an improved multi-stage vehicle detection head (MSVDH). An ensemble CNN backbone extracts the vehicle features and combines them on a single channel via a feature concatenation. The final detection is carried out by an improved MSVDH that classifies the target vehicles. The proposed method is examined, tested, and evaluated using traffic statistics. It is contrasted with current cutting-edge vehicle detection techniques. It achieves 86.32% mean average precision (mAP) on self-collected diverse traffic labeled dataset (DTLD) and 86.17% mAP on KITTI. Moreover, the real-time performance is validated with NVIDIA Jetson Tx2 and Nano boards. It achieves 15 frames per second (FPS) on Jetson Tx2 and 7 FPS on Jetson Nano. [ABSTRACT FROM AUTHOR]

As an essential technology for intelligent transportation management and traffic risk prevention and control, vehicle detection plays a significant role in the comprehensive evaluation of the intelligent transportation system. However, limited by the small size of vehicles in satellite remote sensing images and lack of sufficient texture features, its detection performance is far from satisfactory. In view of the unclear edge structure of small objects in the super-resolution (SR) reconstruction process, deep convolutional neural networks are no longer effective in extracting small-scale feature information. Therefore, a vehicle detection network based on remote sensing images (VDNET-RSI) is constructed in this article. The VDNET-RSI contains a two-stage convolutional neural network for vehicle detection. In the first stage, a partial convolution-based padding adopts the improved Local Implicit Image Function (LIIF) to reconstruct high-resolution remote sensing images. Then, the network associated with the results from the first stage is used in the second stage for vehicle detection. In the second stage, the super-resolution module, detection heads module and convolutional block attention module adopt the increased object detection framework to improve the performance of small object detection in large-scale remote sensing images. The publicly available DIOR dataset is selected as the experimental dataset to compare the performance of VDNET-RSI with that of the state-of-the-art models in vehicle detection based on satellite remote sensing images. The experimental results demonstrated that the overall precision of VDNET-RSI reached 62.9%, about 6.3%, 38.6%, 39.8% higher than that of YOLOv5, Faster-RCNN and FCOS, respectively. The conclusions of this paper can provide a theoretical basis and key technical support for the development of intelligent transportation. [ABSTRACT FROM AUTHOR]

The rise of surveillance systems has led to exponential growth in collected data, enabling several advances in Deep Learning to exploit them and automate tasks for autonomous systems. Vehicle detection is a crucial task in the fields of Intelligent Vehicle Systems and Intelligent Transport systems, making it possible to control traffic density or detect accidents and potential risks. This paper presents an optimal meta-method that can be applied to any instant segmentation model, such as Mask R-CNN or YOLACT++. Using the initial detections obtained by these models and super-resolution, an optimized re-inference is performed, allowing the detection of elements not identified a priori and improving the quality of the rest of the detections. The direct application of super-resolution is limited because instance segmentation models process images according to a fixed dimension. Therefore, in cases where the super-resolved images exceed this fixed size, the model will rescale them again, thus losing the desired effect. The advantages of this meta-method lie mainly in the fact that it is not required to modify the model architecture or re-train it. Regardless of the size of the images given as input, super-resolved areas that fit the defined dimension of the object segmentation model will be generated. After applying our proposal, experiments show an improvement of up to 8.1% for the YOLACT++ model used in the Jena sequence of the CityScapes dataset. [ABSTRACT FROM AUTHOR]

The detection of infrared vehicle targets by UAVs poses significant challenges in the presence of complex ground backgrounds, high target density, and a large proportion of small targets, which result in high false alarm rates. To alleviate these deficiencies, a novel YOLOv7-based, multi-scale target detection method for infrared vehicle targets is proposed, which is termed YOLO-ViT. Firstly, within the YOLOV7-based framework, the lightweight MobileViT network is incorporated as the feature extraction backbone network to fully extract the local and global features of the object and reduce the complexity of the model. Secondly, an innovative C3-PANet neural network structure is delicately designed, which adopts the CARAFE upsampling method to utilize the semantic information in the feature map and improve the model's recognition accuracy of the target region. In conjunction with the C3 structure, the receptive field will be increased to enhance the network's accuracy in recognizing small targets and model generalization ability. Finally, the K-means++ clustering method is utilized to optimize the anchor box size, leading to the design of anchor boxes better suited for detecting small infrared targets from UAVs, thereby improving detection efficiency. The present article showcases experimental findings attained through the use of the HIT-UAV public dataset. The results demonstrate that the enhanced YOLO-ViT approach, in comparison to the original method, achieves a reduction in the number of parameters by 49.9% and floating-point operations by 67.9%. Furthermore, the mean average precision (mAP) exhibits an improvement of 0.9% over the existing algorithm, reaching a value of 94.5%, which validates the effectiveness of the method for UAV infrared vehicle target detection. [ABSTRACT FROM AUTHOR]

In this paper, an ensemble deep transfer learning (EDTL) based on Faster R-CNN is introduced for the vehicle detection in UAV images. We perform a weighted-averaging ensemble transfer learning comprising six base learners using a ResNet50 that have already pre-trained on ImageNet dataset. The weights of the six base learners as well as the final decision threshold are adaptively optimized via genetic algorithm, to maximize the total accuracy, precision, and recall. Simulation results on AU-AIR dataset demonstrate the superiority of the EDTL against the existing techniques, in terms of the total accuracy, and the trade-off between precision and recall. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicles (UAVs) open up new opportunities for transportation monitoring. However, the vehicle targets in UAV images are situated in dynamic scenarios, such as uncertain background, dramatically varying arrangement density, multi-scale, and arbitrary-oriented. Most strategies for UAV-based monitoring require complex manoeuvring and still lack accurate abilities and lightweight structures. Consequently, designing effective detection methods with both speed and accuracy is challenging. This paper proposes a lightweight YOLO-based arbitrary-oriented vehicle detector via precise positional information encoding and bidirectional feature fusion to address the above issues. First, an additional angular classification prediction branch is added to the YOLO head network to significantly improve the detection performance for arbitrary-oriented vehicles without incurring the extra computational complexity and burden. Second, a C3 module embedded coordinate attention (C3CA) is presented to capture long-range dependencies and preserve vehicles' precise positional information in feature maps. Then, a fully connected bidirectional feature fusion module (FC-BiFPN) is applied at the neck of the YOLO detection framework, which is helpful for multi-scale vehicle detection. This module can efficiently aggregate features at different resolutions and automatically enhance information interaction. Finally, experiments and comparisons on vehicle and remote sensing datasets demonstrate that our approach outperforms the state-of-the-art methods in balancing precision and efficiency. In addition, the overall network design follows the lightweight concept, which better meets the real-time requirements of the UAV urban traffic monitoring platform in realistic scenarios. [ABSTRACT FROM AUTHOR]

The detection of vehicle targets in wide-area Synthetic Aperture Radar (SAR) images is crucial for real-time reconnaissance tasks and the widespread application of remote sensing technology in military and civilian fields. However, existing detection methods often face difficulties in handling large-scale images and achieving high accuracy. In this study, we address the challenges of detecting vehicle targets in wide-area SAR images and propose a novel method that combines coarse-grained judgment with fine-grained detection to overcome these challenges. Our proposed vehicle detection model is based on YOLOv5, featuring a CAM attention module, CAM-FPN network, and decoupled detection head, and it is strengthened with background-assisted supervision and coarse-grained judgment. These various techniques not only improve the accuracy of the detection algorithms, but also enhance SAR image processing speed. We evaluate the performance of our model using the Wide-area SAR Vehicle Detection (WSVD) dataset. The results demonstrate that the proposed method achieves a high level of accuracy in identifying vehicle targets in wide-area SAR images. Our method effectively addresses the challenges of detecting vehicle targets in wide-area SAR images, and has the potential to significantly enhance real-time reconnaissance tasks and promote the widespread application of remote sensing technology in various fields. [ABSTRACT FROM AUTHOR]

The stable detection and tracking of high-speed vehicles on the road by using LiDAR can input accurate information for the decision-making module and improve the driving safety of smart cars. This paper proposed a novel LiDAR-based robust vehicle detection method including three parts: point cloud clustering, bounding box fitting and point cloud recognition. Firstly, aiming at the problem of clustering quality degradation caused by the uneven distribution of LiDAR point clouds and the difference in clustering radius between point cloud clusters in traditional DBSCAN (TDBSCAN) obstacle clustering algorithms, an improved DBSCAN algorithm based on distance-adaptive clustering radius (ADBSCAN) is designed, and a point cloud KD-Tree data structure is constructed to speed up the traversal of the algorithm; meanwhile, the OPTICS algorithm is introduced to enhance the performance of the proposed algorithm. Then, by adopting different fitting strategies for vehicle contour points in various states, the adaptability of the bounding box fitting algorithm is improved; Moreover, in view of the shortcomings of the poor robustness of the L-shape algorithm, the principal component analysis method (PCA) is introduced to obtain stable bounding box fitting results. Finally, considering the time-consuming and low-accuracy training of traditional machine learning algorithms, advanced PointNet in deep learning technique is built to send the point cloud within the bounding box of a high-confidence vehicle into PointNet to complete vehicle recognition. Experiments based on our autonomous driving perception platform and the KITTI dataset prove that the proposed method can stably complete vehicle target recognition and achieve a good balance between time-consuming and accuracy. [ABSTRACT FROM AUTHOR]

Aerial vehicle detection has significant applications in aerial surveillance and traffic control. The pictures captured by the UAV are characterized by many tiny objects and vehicles obscuring each other, significantly increasing the detection challenge. In the research of detecting vehicles in aerial images, there is a widespread problem of missed and false detections. Therefore, we customize a model based on YOLOv5 to be more suitable for detecting vehicles in aerial images. Firstly, we add one additional prediction head to detect smaller-scale objects. Furthermore, to keep the original features involved in the training process of the model, we introduce a Bidirectional Feature Pyramid Network (BiFPN) to fuse the feature information from various scales. Lastly, Soft-NMS (soft non-maximum suppression) is employed as a prediction frame filtering method, alleviating the missed detection due to the close alignment of vehicles. The experimental findings on the self-made dataset in this research indicate that compared with YOLOv5s, the mAP@0.5 and mAP@0.5:0.95 of YOLOv5-VTO increase by 3.7% and 4.7%, respectively, and the two indexes of accuracy and recall are also improved. [ABSTRACT FROM AUTHOR]

The research and development of deep learning methods are heavily reliant on large datasets, and there is currently a lack of scene-rich datasets for synthetic aperture radar (SAR) image vehicle detection. To address this issue and promote the development of SAR vehicle detection algorithms, we constructed the SAR Image dataset for VEhicle Detection (SIVED) using Ka, Ku, and X bands of data. Rotatable bounding box annotations were employed to improve positioning accuracy, and an algorithm for automatic annotation was proposed to improve efficiency. The dataset exhibits three crucial properties: richness, stability, and challenge. It comprises 1044 chips and 12,013 vehicle instances, most of which are situated in complex backgrounds. To construct a baseline, eight detection algorithms are evaluated on SIVED. The experimental results show that all detectors achieved high mean average precision (mAP) on the test set, highlighting the dataset's stability. However, there is still room for improvement in the accuracy with respect to the complexity of the background. In summary, SIVED fills the gap in SAR image vehicle detection datasets and demonstrates good adaptability for the development of deep learning algorithms. [ABSTRACT FROM AUTHOR]

Vehicle detection in parking areas provides the spatial and temporal utilisation of parking spaces. Parking observations are typically performed manually, limiting the temporal resolution due to the high labour cost. This paper uses simulated data and transfer learning to build a robust real-world model for vehicle detection and classification from single-beam LiDAR of a roadside parking scenario. The paper presents a synthetically augmented transfer learning approach for LiDAR-based vehicle detection and the implementation of synthetic LiDAR data. A synthetic augmented transfer learning method was used to supplement the small real-world data set and allow the development of data-handling techniques. In addition, adding the synthetically augmented transfer learning method increases the robustness and overall accuracy of the model. Experiments show that the method can be used for fast deployment of the model for vehicle detection using a LIDAR sensor. [ABSTRACT FROM AUTHOR]

High-precision detection of vehicle position and contour from unmanned aerial vehicles (UAV) provides critical information for vehicle behavior and traffic flow studies. Vehicles in UAV videos present unique features of small target pixels, which pose challenges in accurate detection. In addition, shaking of UAV camera, shadow of vehicle, and ground sign/marking also lead to difficulties in precise vehicle contour detection. The study proposes a novel approach that designs a bidirectional feedback framework (GKB) between optimized Gaussian mixture model and Kernel correlation filter to enhance vehicle detection. The framework predicts vehicle position based on information of continuous and correlated previous frames to achieve improved performance. We also improve the detection of closely spaced and dark vehicles with morphological algorithms and data processing. The approach is tested on two UAV videos with different shooting heights, illumination conditions, and traffic states. The results show that the proposed method significantly improves vehicle detection. The total accuracy of our model is 98%, which is a 11% improvement over the traditional single detect model and a 4% improvement over the track-after-detect method. Our model's detection rate of closely spaced and dark vehicles is improved by 15–25% compared to previous methods. Our model's vehicle contour detection accuracy is over 94%, which is about a 15% improvement over previous methods. [ABSTRACT FROM AUTHOR]

Intelligent transportation system (ITS) is widely employed in dynamic traffic management to alleviate roadside congestion and increase traffic efficiency for solving the increasingly critical traffic congestion problems. With the advancement in ITS, real-time data collection of vehicles on the road has become a reality. A vast amount of traffic data ensures that the state of the road network may be analysed and predicted in real time for vehicle detection. Decision support system plays a significant role in the early decision making based on some defined criteria again available options. If the decision is made in the right and precise way, then eventually, it lead to success. This research investigates and designs a vehicle recognition algorithm and the road environment discrimination algorithm, which greatly increase the accuracy of highway vehicle detection, using a deep learning framework. In this work, we collect the highway video surveillance's images in various environments, create an original database, build a deep learning model of environment discrimination, and train the classification model to achieve real-time highway environment as the basic condition of vehicle recognition and traffic event discrimination. The proposed work uses a decision support system which is feed with basic information for vehicle detection and selection. Labeling the vehicle target and sample preparation of various environments are carried out to improve the accuracy of detecting the vehicles on a highway. The vehicle recognition algorithm is investigated in this context, and a vehicle detection technique based on weather environment recognition and a rapid RCNN model is presented. The performance of the vehicle recognition algorithm developed in this study is then verified by comparing detection accuracy with the existing state-of-the-art approaches. The comparison with these approaches in terms of accuracy, sensitivity, and F-score shows that our algorithm outperforms these approaches for detecting and classifying vehicles on the highway. [ABSTRACT FROM AUTHOR]

With the development of deep learning and traditional algorithms in synthetic aperture radar (SAR) image target detection, vehicle target detection under large scenes in SAR images remains a challenging research topic. This is due to various factors: the difficulty of accuracy and speed of target detection; the complexity of background interference in the large scene; partition of small block object detection; and the slow window traversal process of vehicle detection method in large scene under deep learning. To address these limitations, the key is to establish a background-target adaptation model to determine the target position and improve the performance of algorithm detection. A vehicle detection algorithm based on GL-CFAR and PRID RCNN is proposed in this study by combining traditional algorithms with deep learning algorithms. GL-CFAR is used to provide fast position coarse detection of vehicle targets in large SAR scenes, and the proposed PRID RCNN network can effectively adapt to vehicle detection in SAR large scenes, which greatly improves the detection of vehicle under different backgrounds. By adding the Pyramid Real Image Denoising Network (PRID) module to the Faster RCNN network and using the K-means method to reduce the number of detection anchor boxes, reduce background interference, and achieve feature enhancement. Experiment results show that the algorithm proposed in this study has high accuracy and processing speed. [ABSTRACT FROM AUTHOR]

The performance of deep learning based algorithms is significantly influenced by the quantity and quality of the available training and test datasets. Since data acquisition is complex and expensive, especially in the field of airborne sensor data evaluation, the use of virtual simulation environments for generating synthetic data are increasingly sought. In this article, the complete process chain is evaluated regarding the use of synthetic data based on vehicle detection. Among other things, content-equivalent real and synthetic aerial images are used in the process. This includes, in the first step, the learning of models with different training data configurations and the evaluation of the resulting detection performance. Subsequently, a statistical evaluation procedure based on a classification chain with image descriptors as features is used to identify important influencing factors in this respect. The resulting findings are finally incorporated into the synthetic training data generation and in the last step, it is investigated to what extent an increase of the detection performance is possible. The overall objective of the experiments is to derive design guidelines for the generation and use of synthetic data. [ABSTRACT FROM AUTHOR]

Aiming at the characteristics of low detection accuracy and poor robustness of traditional target detection and tracking algorithm, as well as the phenomenon of image and video resource redundancy and high vehicle density at the intersection, a real-time traffic flow detection method based on improved YOLOv5 and DeepSort algorithm model is proposed. This experiment uses a data set combining MS COCO and BDD100k, and uses the improved YOLOv5 algorithm model to realize the small target vehicle detection in video. Then, the deep learning multi-target tracking algorithm (DeepSort algorithm) is used to carry out real-time tracking and counting of the detected vehicles, and the real-time traffic flow detection of the intersection monitoring end-to-end is realized. By analyzing and comparing models with different parameters, the YOLOv5m model is finally selected. Experimental results show that the proposed method has a faster detection speed and better detection effect for vehicles in complex environments, vehicle occlusion and high target density environments, with an average accuracy of 96.6%. This method can fully meet the requirements of real-time detection of targets, and fully meet the effectiveness of vehicle detection at intersections, and meet the actual requirements of use. [ABSTRACT FROM AUTHOR]

Vehicle detection in video frames has been treated the same way detecting vehicle for an isolated image. However, the models designed for the isolated image are blind to fast-moving vehicles and cannot localize the moving targets partially occluded in the scene. In this case, we figure out a way to combine the classic moving target detection method with the neural network method. In this work, first, we propose to add three-differential-frames into the neural network of Yolov3 as the second input which contains the motion information on the front and back frames to detect vehicles partially occluded; second, we reform the network by using Octave Convolution to reduce memory and computational cost while boosting accuracy. We experimentally show that by using the aforementioned methods together, compared with using original YOLOv3 on UA-DETRAC data set, AP is increased by 2.31%, recall is increased by 4.01%, and precision is increased by 3.10%. We demonstrate that the proposed method is indeed effective. [ABSTRACT FROM AUTHOR]

As technology continues to develop, computer vision (CV) applications are becoming increasingly widespread in the intelligent transportation systems (ITS) context. These applications are developed to improve the efficiency of transportation systems, increase their level of intelligence, and enhance traffic safety. Advances in CV play an important role in solving problems in the fields of traffic monitoring and control, incident detection and management, road usage pricing, and road condition monitoring, among many others, by providing more effective methods. This survey examines CV applications in the literature, the machine learning and deep learning methods used in ITS applications, the applicability of computer vision applications in ITS contexts, the advantages these technologies offer and the difficulties they present, and future research areas and trends, with the goal of increasing the effectiveness, efficiency, and safety level of ITS. The present review, which brings together research from various sources, aims to show how computer vision techniques can help transportation systems to become smarter by presenting a holistic picture of the literature on different CV applications in the ITS context. [ABSTRACT FROM AUTHOR]

Traffic congestion is a serious challenge in urban areas. So, to address this challenge, the intelligent traffic management system (ITMS) is used to manage traffic on road networks. Managing traffic helps to focus on environmental impacts as well as emergency situations. However, the ITMS system has many challenges in analyzing scenes of complex traffic. New technologies such as computer vision (CV) and artificial intelligence (AI) are being used to solve these challenges. As a result, these technologies have made a distinct identity in the surveillance industry, particularly when it comes to keeping a constant eye on traffic scenes. There are many vehicle attributes and existing approaches that are being used in the development of ITMS, along with imaging technologies. In this paper, we reviewed the ITMS-based components that describe existing imaging technologies and existing approaches on the basis of their need for developing ITMS. The first component describes the traffic scene and imaging technologies. The second component talks about vehicle attributes and their utilization in existing vehicle-based approaches. The third component explains the vehicle's behavior on the basis of the second component's outcome. The fourth component explains how traffic-related applications can assist in the management and monitoring of traffic flow, as well as in the reduction of congestion and the enhancement of road safety. The fifth component describes the different types of ITMS applications. The sixth component discusses the existing methods of traffic signal control systems (TSCSs). Aside from these components, we also discuss existing vehicle-related tools such as simulators that work to create realistic traffic scenes. In the last section named discussion, we discuss the future development of ITMS and draw some conclusions. The main objective of this paper is to discuss the possible solutions to different problems during the development of ITMS in one place, with the help of components that would play an important role for an ITMS developer to achieve the goal of developing efficient ITMS. [ABSTRACT FROM AUTHOR]

A convolutional neural network-based multiobject detection and tracking algorithm can be applied to vehicle detection and traffic flow statistics, thus enabling smart transportation. Aiming at the problems of the high computational complexity of multiobject detection and tracking algorithms, a large number of model parameters, and difficulty in achieving high throughput with a low power consumption in edge devices, we design and implement a low-power, low-latency, high-precision, and configurable vehicle detector based on a field programmable gate array (FPGA) with YOLOv3 (You-Only-Look-Once-version3), YOLOv3-tiny CNNs (Convolutional Neural Networks), and the Deepsort algorithm. First, we use a dynamic threshold structured pruning method based on a scaling factor to significantly compress the detection model size on the premise that the accuracy does not decrease. Second, a dynamic 16-bit fixed-point quantization algorithm is used to quantify the network parameters to reduce the memory occupation of the network model. Furthermore, we generate a reidentification (RE-ID) dataset from the UA-DETRAC dataset and train the appearance feature extraction network on the Deepsort algorithm to improve the vehicles' tracking performance. Finally, we implement hardware optimization techniques such as memory interlayer multiplexing, parameter rearrangement, ping-pong buffering, multichannel transfer, pipelining, Im2col+GEMM, and Winograd algorithms to improve resource utilization and computational efficiency. The experimental results demonstrate that the compressed YOLOv3 and YOLOv3-tiny network models decrease in size by 85.7% and 98.2%, respectively. The dual-module parallel acceleration meets the demand of the 6-way parallel video stream vehicle detection with the peak throughput at 168.72 fps. [ABSTRACT FROM AUTHOR]

Small target detection is still a challenging task, especially when looking at fast and accurate solutions for mobile or edge applications. In this work, we present YOLO-S, a simple, fast, and efficient network. It exploits a small feature extractor, as well as skip connection, via both bypass and concatenation, and a reshape-passthrough layer to promote feature reuse across network and combine low-level positional information with more meaningful high-level information. Performances are evaluated on AIRES, a novel dataset acquired in Europe, and VEDAI, benchmarking the proposed YOLO-S architecture with four baselines. We also demonstrate that a transitional learning task over a combined dataset based on DOTAv2 and VEDAI can enhance the overall accuracy with respect to more general features transferred from COCO data. YOLO-S is from 25% to 50% faster than YOLOv3 and only 15–25% slower than Tiny-YOLOv3, outperforming also YOLOv3 by a 15% in terms of accuracy (mAP) on the VEDAI dataset. Simulations on SARD dataset also prove its suitability for search and rescue operations. In addition, YOLO-S has roughly 90% of Tiny-YOLOv3's parameters and one half FLOPs of YOLOv3, making possible the deployment for low-power industrial applications. [ABSTRACT FROM AUTHOR]

Aiming at the problems of high missed detection rates of the YOLOv7 algorithm for vehicle detection on urban roads, weak perception of small targets in perspective, and insufficient feature extraction, the YOLOv7-RAR recognition algorithm is proposed. The algorithm is improved from the following three directions based on YOLOv7. Firstly, in view of the insufficient nonlinear feature fusion of the original backbone network, the Res3Unit structure is used to reconstruct the backbone network of YOLOv7 to improve the ability of the network model architecture to obtain more nonlinear features. Secondly, in view of the problem that there are many interference backgrounds in urban roads and that the original network is weak in positioning targets such as vehicles, a plug-and-play hybrid attention mechanism module, ACmix, is added after the SPPCSPC layer of the backbone network to enhance the network's attention to vehicles and reduce the interference of other targets. Finally, aiming at the problem that the receptive field of the original network Narrows, with the deepening of the network model, leads to a high miss rate of small targets, the Gaussian receptive field scheme used in the RFLA (Gaussian-receptive-field-based label assignment) module is used at the connection between the feature fusion area and the detection head to improve the receptive field of the network model for small objects in the image. Combining the three improvement measures, the first letter of the name of each improvement measure is selected, and the improved algorithm is named the YOLOv7-RAR algorithm. Experiments show that on urban roads with crowded vehicles and different weather patterns, the average detection accuracy of the YOLOv7-RAR algorithm reaches 95.1%, which is 2.4% higher than that of the original algorithm; the AP50:90 performance is 12.6% higher than that of the original algorithm. The running speed of the YOLOv7-RAR algorithm reaches 96 FPS, which meets the real-time requirements of vehicle detection; hence, the algorithm can be better applied to vehicle detection. [ABSTRACT FROM AUTHOR]

Occupancy grid maps are widely used as an environment model that allows the fusion of different range sensor technologies in real-time for robotics applications. In an autonomous vehicle setting, occupancy grid maps are especially useful for their ability to accurately represent the position of surrounding obstacles while being robust to discrepancies between the fused sensors through the use of occupancy probabilities representing uncertainty. In this article, we propose to evaluate the applicability of real-time vehicle detection on occupancy grid maps. State of the art detectors in sensor-specific domains such as YOLOv2/YOLOv3 for images or PIXOR for LiDAR point clouds are modified to use occupancy grid maps as input and produce oriented bounding boxes enclosing vehicles as output. The five proposed detectors are trained on the Waymo Open automotive dataset and compared regarding the quality of their detections measured in terms of Average Precision (AP) and their real-time capabilities measured in Frames Per Second (FPS). Of the five detectors presented, one inspired from the PIXOR backbone reaches the highest A P 0.7 of 0.82 and runs at 20 FPS. Comparatively, two other proposed detectors inspired from YOLOv2 achieve an almost as good, with a A P 0.7 of 0.79 while running at 91 FPS. These results validate the feasibility of real-time vehicle detection on occupancy grids. [ABSTRACT FROM AUTHOR]

As an integral part of intelligent transportation system, vehicle detection and tracking system is of great research significance and practical application value. In this paper, based on the mixed Gaussian background model, the detection target is segmented by the different methods, and the most matching target track is found by using the location information and color information of the detection target, so as to realize the vehicle tracking. The experiment results show that for the same target, the centroid distance is less than 0.2, the color distance of HSV (hue saturation value) is less than 0.3, the centroid distance of different targets is less than 0.2, the HSV distance is less than 0.3, and the rest are distributed to some extent. When the centroid distance is 0.01, 0.02, 0.03, 0.04, 0.05 and 0.06, respectively, the matching results are 250, 150, 100, 50, 25 and 10, respectively; when the HSV color distance is 0.02, 0.06, 0.1, 0.14 and 0.18, respectively, the matching results are 160, 200, 100, 80 and 50, respectively. Therefore, for the normalized distance between the same targets, including the centroid distance and HSV color, in each possible matching area, the greater the distance is, the less the distribution of matching results. Experimental verification shows that when the vehicle is detected in the detection area, the effective contour is sequentially accessed and tracked through the memory pointer, and the relatively accurate contour of the moving vehicle can be obtained through the improved Gaussian mixture model. The vehicle detection algorithm based on regional method has high real-time accuracy and strong practical value, can meet the needs of intelligent transportation system, and has strong practical value. [ABSTRACT FROM AUTHOR]

Vehicle detection and tracking technology plays an important role in intelligent transportation management and control systems. This paper proposes a novel vehicle detection and tracking method for small target vehicles to achieve high detection and tracking accuracy based on the attention mechanism. We first develop a new vehicle detection model (YOLOv5-NAM) by adding the normalization-based attention module (NAM) to the classical YOLOv5s model. By exploiting the YOLOv5-NAM model as the vehicle detector, we then propose a real-time small target vehicle tracking method (JDE-YN), where the feature extraction process is embedded in the prediction head for joint training. Finally, we present extensive experimental results to verify our method on the UA-DETRAC dataset and to demonstrate that the method can effectively detect small target vehicles in real time. It is shown that compared with the original YOLOv5s model, the mAP value of the YOLOv5-NAM vehicle detection model is improved by 1.6%, while the MOTA value of the JDE-YN method improved by 0.9% compared with the original JDE method. [ABSTRACT FROM AUTHOR]

For a majority of remote sensing applications of unmanned aerial vehicles (UAVs), the data need to be downloaded to ground devices for processing, but this procedure cannot satisfy the demands of real-time target detection. Our objective in this study is to develop a real-time system based on an embedded technology for image acquisition, target detection, the transmission and display of the results, and user interaction while providing support for the interactions between multiple UAVs and users. This work is divided into three parts: (1) We design the technical procedure and the framework for the implementation of a real-time target detection system according to application requirements. (2) We develop an efficient and reliable data transmission module to realize real-time cross-platform communication between airborne embedded devices and ground-side servers. (3) We optimize the YOLOv4 algorithm by using the K-Means algorithm and TensorRT inference to improve the accuracy and speed of the NVIDIA Jetson TX2. In experiments involving static detection, it had an overall confidence of 89.6% and a rate of missed detection of 3.8%; in experiments involving dynamic detection, it had an overall confidence and a rate of missed detection of 88.2% and 4.6%, respectively. [ABSTRACT FROM AUTHOR]