Search

Once realized, autonomous aerial refueling will revolutionize unmanned aviation by removing current range and endurance limitations. Previous attempts at establishing vision-based solutions have come close but rely heavily on near perfect extrinsic camera calibrations that often change midflight. In this paper, we propose dual object detection, a technique that overcomes such requirement by transforming aerial refueling imagery directly into receiver aircraft reference frame probe-to-drogue vectors regardless of camera position and orientation. These vectors are precisely what autonomous agents need to successfully maneuver the tanker and receiver aircraft in synchronous flight during refueling operations. Our method follows a common 4-stage process of capturing an image, finding 2D points in the image, matching those points to 3D object features, and analytically solving for the object pose. However, we extend this pipeline by simultaneously performing these operations across two objects instead of one using machine learning and add a fifth stage that transforms the two pose estimates into a relative vector. Furthermore, we propose a novel supervised learning method using bounding box corrections such that our trained artificial neural networks can accurately predict 2D image points corresponding to known 3D object points. Simulation results show that this method is reliable, accurate (within 3 cm at contact), and fast (45.5 fps). [ABSTRACT FROM AUTHOR]

A monocular vehicle speed detection method based on improved YOLOX and DeepSORT is proposed for the simple scene of fixed shooting angle without high precision but requiring control cost. For continuous video frames collected from a monocular fixed perspective, the vehicle is first identified by using the YOLOX object detection network improved by ELAN module and the CAENet attention mechanism constructed by CA attention and ECANet. Then, the DeepSORT target tracking algorithm is used to match the recognition results of the object detection network output in the before and after frames to find the same target in different frames. Finally, a coordinate system transformation algorithm is used to convert the position distance of the target moving in different frame images into the actual ground plane distance and divide it by the detection interval time to obtain the vehicle speed. The experimental results show that our improved object detection model can increase mAP by 2% to 4% compared with YOLOX in different versions. Compared with the original model, the target tracking using the improved YOLOX is improved by 4.3% on MOTA. The speed limiting precision of speed detection is 75% in the corresponding speed range in experimental testing site 1 and the mean error of the effective velocity value measured by our speed measurement method is 2.10 km/h in experimental testing site 2, which is better than the mean error of 5.46 km/h obtained by the radar pistol velocimeter. This detection method enables economical and efficient vehicle speed detection in simple scenes. [ABSTRACT FROM AUTHOR]

Safe and efficient navigation is critical for a mobile robot in a highly constrained workspace. Autonomous navigation is to be performed safely and robustly in the environment map with obstacles of various geometric shapes, sizes and colors positioned at random locations. In this paper, we present an approach to perform autonomous navigation by detecting the obstacles in the map and by generating auxiliary collision-free waypoints in obstacle-free space map. In achieving this, the object detection is done using SSDMobileNetV2 model and auxiliary collision-free navigation waypoints are generated using the Deepway neural network model. Further, the RRT path planner is applied to analyze the waypoints generated and to find the a global path between start and goal locations. An optimal local path is achieved using the A* path planner. Extensive simulations of various scenarios are performed and the proposed model is evaluated. The results reveal that the proposed model achieves significant improvements in terms of time, distance and F1-score. [ABSTRACT FROM AUTHOR]

One of the most popular techniques for changing the purpose of an image or resizing a digital image with content awareness is the seam-carving method. The performance of image resizing algorithms based on seam machining shows that these algorithms are highly dependent on the extraction of importance map techniques and the detection of salient objects. So far, various algorithms have been proposed to extract the importance map. In this paper, a new method based on Rényi entropy is proposed to extract the importance map. Also, a deep learning network has been used to detect salient objects. The simulator results showed that combining Rényi's importance map with a deep network of salient object detection performed better than classical seam-carving and other extended seam-carving algorithms based on deep learning. [ABSTRACT FROM AUTHOR]

Simple Summary: Simple Summary: Pig tracking provides strong support for refined management in pig farms and can assist in realizing customized, automated, and intellectualized management. However, there are many complex factors in actual production that result in pigs not being tracked consistently over time. To address this issue, we proposed a long-term video tracking method for group-housed pigs based on improved StrongSORT. The experimental results proved that our study demonstrates high practicality, catering to the needs of practical production. It improved the efficiency of farming personnel and lays the foundation for the automated monitoring of pigs. Additionally, it is worth mentioning that we have also released a dataset specifically designed for long-term pig tracking in this paper. Pig tracking provides strong support for refined management in pig farms. However, long and continuous multi-pig tracking is still extremely challenging due to occlusion, distortion, and motion blurring in real farming scenarios. This study proposes a long-term video tracking method for group-housed pigs based on improved StrongSORT, which can significantly improve the performance of pig tracking in production scenarios. In addition, this research constructs a 24 h pig tracking video dataset, providing a basis for exploring the effectiveness of long-term tracking algorithms. For object detection, a lightweight pig detection network, YOLO v7-tiny_Pig, improved based on YOLO v7-tiny, is proposed to reduce model parameters and improve detection speed. To address the target association problem, the trajectory management method of StrongSORT is optimized according to the characteristics of the pig tracking task to reduce the tracking identity (ID) switching and improve the stability of the algorithm. The experimental results show that YOLO v7-tiny_Pig ensures detection applicability while reducing parameters by 36.7% compared to YOLO v7-tiny and achieving an average video detection speed of 435 frames per second. In terms of pig tracking, Higher-Order Tracking Accuracy (HOTA), Multi-Object Tracking Accuracy (MOTP), and Identification F1 (IDF1) scores reach 83.16%, 97.6%, and 91.42%, respectively. Compared with the original StrongSORT algorithm, HOTA and IDF1 are improved by 6.19% and 10.89%, respectively, and Identity Switch (IDSW) is reduced by 69%. Our algorithm can achieve the continuous tracking of pigs in real scenarios for up to 24 h. This method provides technical support for non-contact pig automatic monitoring. [ABSTRACT FROM AUTHOR]

Object detection is one of the core technologies for autonomous driving. Current road object detection mainly relies on visible light, which is prone to missed detections and false alarms in rainy, night-time, and foggy scenes. Multispectral object detection based on the fusion of RGB and infrared images can effectively address the challenges of complex and changing road scenes, improving the detection performance of current algorithms in complex scenarios. However, previous multispectral detection algorithms suffer from issues such as poor fusion of dual-mode information, poor detection performance for multi-scale objects, and inadequate utilization of semantic information. To address these challenges and enhance the detection performance in complex road scenes, this paper proposes a novel multispectral object detection algorithm called MRD-YOLO. In MRD-YOLO, we utilize interaction-based feature extraction to effectively fuse information and introduce the BIC-Fusion module with attention guidance to fuse different modal information. We also incorporate the SAConv module to improve the model's detection performance for multi-scale objects and utilize the AIFI structure to enhance the utilization of semantic information. Finally, we conduct experiments on two major public datasets, FLIR_Aligned and M3FD. The experimental results demonstrate that compared to other algorithms, the proposed algorithm achieves superior detection performance in complex road scenes. [ABSTRACT FROM AUTHOR]

The detection of objects on water surfaces is a pivotal technology for the perceptual systems of unmanned surface vehicles (USVs). This paper proposes a novel real-time target detection system designed to address the challenges posed by indistinct bottom boundaries and foggy imagery. Our method enhances the YOLOv8s model by incorporating the convolutional block attention module (CBAM) and a self-attention mechanism, examining their impact at various integration points. A dynamic sample assignment strategy was introduced to enhance the precision of our model and accelerate its convergence. To address the challenge of delineating bottom boundaries with clarity, our model employs a two-strategy approach: a threshold filter and a feedforward neural network (FFN) that provides targeted guidance for refining these boundaries. Our model demonstrated exceptional performance, achieving a mean average precision (mAP) of 47.1% on the water surface object dataset, which represents a 1.7% increase over the baseline YOLOv8 model. The dynamic sample assignment strategy contributes a 1.0% improvement on average precision at the intersection over union (IoU) threshold of 0.5 (AP0.5), while the FFN strategy fine-tunes the bottom boundaries and achieves an additional 0.8% improvement in average precision at IoU threshold of 0.75 (AP0.75). Furthermore, ablation studies have validated the versatility of our approach, confirming its potential for integration into various detection frameworks. [ABSTRACT FROM AUTHOR]

Deep learning models have significantly improved object detection, which is essential for visual sensing. However, their increasing complexity results in higher latency and resource consumption, making real-time object detection challenging. In order to address the challenge, we propose a new lightweight filtering method called L-filter to predict empty video frames that include no object of interest (e.g., vehicles) with high accuracy via hybrid time series analysis. L-filter drops those frames deemed empty and conducts object detection for nonempty frames only, significantly enhancing the frame processing rate and scalability of real-time object detection. Our evaluation demonstrates that L-filter improves the frame processing rate by 31–47% for a single traffic video stream compared to three standalone state-of-the-art object detection models without L-filter. Additionally, L-filter significantly enhances scalability; it can process up to six concurrent video streams in one commodity GPU, supporting over 57 fps per stream, by working alongside the fastest object detection model among the three models. [ABSTRACT FROM AUTHOR]

The sky may seem big enough for two flying vehicles to collide, but the facts show that mid-air collisions still occur occasionally and are a significant concern. Pilots learn manual tactics to avoid collisions, such as see-and-avoid, but these rules have limitations. Automated solutions have reduced collisions, but these technologies are not mandatory in all countries or airspaces, and they are expensive. These problems have prompted researchers to continue the search for low-cost solutions. One attractive solution is to use computer vision to detect obstacles in the air due to its reduced cost and weight. A well-trained deep learning solution is appealing because object detection is fast in most cases, but it relies entirely on the training data set. The algorithm chosen for this study is optical flow. The optical flow vectors can help us to separate the motion caused by camera motion from the motion caused by incoming objects without relying on training data. This paper describes the development of an optical flow-based airborne obstacle detection algorithm to avoid mid-air collisions. The approach uses the visual information from a monocular camera and detects the obstacles using morphological filters, optical flow, focus of expansion, and a data clustering algorithm. The proposal was evaluated using realistic vision data obtained with a self-developed simulator. The simulator provides different environments, trajectories, and altitudes of flying objects. The results showed that the optical flow-based algorithm detected all incoming obstacles along their trajectories in the experiments. The results showed an F-score greater than 75% and a good balance between precision and recall. [ABSTRACT FROM AUTHOR]

With the progression of smart vehicles, i.e., connected autonomous vehicles (CAVs), and wireless technologies, there has been an increased need for substantial computational operations for tasks such as path planning, scene recognition, and vision-based object detection. Managing these intensive computational applications is concerned with significant energy consumption. Hence, for this article, a low-cost and sustainable solution using computational offloading and efficient resource allocation at edge devices within the Internet of Vehicles (IoV) framework has been utilised. To address the quality of service (QoS) among vehicles, a trade-off between energy consumption and computational time has been taken into consideration while deciding on the offloading process and resource allocation. The offloading process has been assigned at a minimum wireless resource block level to adapt to the beyond 5G (B5G) network. The novel approach of joint optimisation of computational resources and task offloading decisions uses the meta-heuristic particle swarm optimisation (PSO) algorithm and decision analysis (DA) to find the near-optimal solution. Subsequently, a comparison is made with other proposed algorithms, namely CTORA, CODO, and Heuristics, in terms of computational efficiency and latency. The performance analysis reveals that the numerical results outperform existing algorithms, demonstrating an 8% and a 5% increase in energy efficiency. [ABSTRACT FROM AUTHOR]

Machine learning and deep learning technologies are rapidly advancing the capabilities of sensing technologies, bringing about significant improvements in accuracy, sensitivity, and adaptability. These advancements are making a notable impact across a broad spectrum of fields, including industrial automation, robotics, biomedical engineering, and civil infrastructure monitoring. The core of this transformative shift lies in the integration of artificial intelligence (AI) with sensor technology, focusing on the development of efficient algorithms that drive both device performance enhancements and novel applications in various biomedical and engineering fields. This review delves into the fusion of ML/DL algorithms with sensor technologies, shedding light on their profound impact on sensor design, calibration and compensation, object recognition, and behavior prediction. Through a series of exemplary applications, the review showcases the potential of AI algorithms to significantly upgrade sensor functionalities and widen their application range. Moreover, it addresses the challenges encountered in exploiting these technologies for sensing applications and offers insights into future trends and potential advancements. [ABSTRACT FROM AUTHOR]

Carbon fiber laminates have become popular in the manufacturing industry for their many desirable properties, like good vibration damping, high strength-to-weight ratio, toughness, high dimensional stability, and low coefficient of thermal expansion. During the manufacturing process, undesirable foreign objects, such as peel-ply strips, gloving material, and Kapton film, can be introduced into the part which can lead to a localized weakness. These manufacturing defects can function as stress concentration points and oftentimes cause a premature catastrophic failure. In this study, a method using high-resolution pulse-echo ultrasound testing is employed for the detection and quantification of the dimensions of foreign object debris (FOD) embedded within carbon fiber laminates. This research presents a method to create high-resolution C-scans using an out of immersion tank portable housing ultrasound scanning system, with similar capabilities to that of a full immersion system. From the full-waveform dataset, we extract the FOD depth and planar dimensions with an automatic edge detection technique. Results from several carbon fiber laminates are investigated with embedded foreign objects that are often considered undetectable. Results are presented for FOD identification for two different shapes: circles with diameters ranging from 7.62 mm to 12.7 mm, and 3-4-5 triangles with hypotenuses ranging from 7.6 mm to 12.7 mm. CT imaging is used to confirm proper FOD placement and that the FOD was not damaged or altered during manufacturing. Of importance for the ultrasound inspection results, in every single case studied, the FOD is detected, the layer depth is properly identified, and the typical error is less than 1.5 mm for the primary dimension. [ABSTRACT FROM AUTHOR]

In the context of small unmanned aerial vehicles (UAVs), infrared imaging faces challenges such as low quality, difficulty in detecting small targets, high false alarm rates, and computational resource constraints. To address these issues, we introduce AIMED-Net, an enhancing infrared small target detection net in UAVs with multi-layer feature enhancement for edge computing. Initially, the network encompasses a multi-layer feature enhancement architecture for infrared small targets, including a generative adversarial-based shallow-feature enhancement network and a detection-oriented deep-feature enhancement network. Specifically, an infrared image-feature enhancement method is proposed for the shallow-feature enhancement network, employing multi-scale enhancement to bolster target detection performance. Furthermore, within the YOLOv7 framework, we have developed an improved object detection network integrating multiple feature enhancement techniques, optimized for infrared targets and edge computing conditions. This design not only reduces the model's complexity but also enhances the network's robustness and accuracy in identifying small targets. Experimental results obtained from the HIT-UAV public dataset indicate that, compared to YOLOv7s, our method achieves a 2.5% increase in F1 score, a 6.1% rise in AP for detecting OtherVehicle targets, and a 2.6% improvement in mAP across all categories, alongside a 15.2% reduction in inference time on edge devices. Compared to existing state-of-the-art approaches, our method strikes a balance between detection efficiency and accuracy, presenting a practical solution for deployment in aerial edge computing scenarios. [ABSTRACT FROM AUTHOR]

Salient object detection is an increasingly popular topic in the computer vision field, particularly for images with complex backgrounds and diverse object parts. Background information is an essential factor in detecting salient objects. This paper suggests a robust and effective methodology for salient object detection. This method involves two main stages. The first stage is to produce a saliency detection map based on the dense and sparse reconstruction of image regions using a refined background dictionary. The refined background dictionary uses a boundary conductivity measurement to exclude salient object regions near the image's boundary from a background dictionary. In the second stage, the CascadePSP network is integrated to refine and correct the local boundaries of the saliency mask to highlight saliency objects more uniformly. Using six evaluation indexes, experimental outcomes conducted on three datasets show that the proposed approach performs effectively compared to the state-of-the-art methods in salient object detection, particularly in identifying the challenging salient objects located near the image's boundary. These results demonstrate the potential of the proposed framework for various computer vision applications. [ABSTRACT FROM AUTHOR]

Remote sensing detection is a difficult task that requires not only identifying objects with complex background, quality, and angle issues, but also being lightweight enough to be carried by edge devices. In real remote sensing scenarios, achieving accurate, fast, and low-resource-consumption automated detection remains a significant challenge. Therefore, this paper proposes an efficient balanced network (EB-Net) for real remote sensing devices. First, a dynamic sparse attention (DSA) mechanism is proposed and has been proven with high performance via the complexity analysis. In addition, a new dynamic sparse transformer (DSFormer) is constructed using DSA, which enhances feature information and adapts to image resolution by self-attention and multi-headed attention, and achieves more flexible computation by random sampling. Then, three versions of discrete distribution IoU (DDIoU) are defined for adapting various scenarios and tasks in remote sensing, and this loss function makes the model achieve high accuracy and more lightweight. Finally, to make the model more lightweight, a cropped SPPF (CroSPPF) is presented, which significantly improves the computational efficiency by the lightweight of the sequence structure and activation function. Ablation experiments are conducted on the NWPU VHR-10 dataset, and demonstrate the effectiveness of the proposed methods. Numerous comparisons with state-of-the-art detectors are conducted on the NWPU VHR-10, RSOD and DOTA datasets. The experiments show that EB-Net outperforms state-of-the-art remote sensing detection models in comprehensive performance and achieves end-to-end accurate and lightweight detection. [ABSTRACT FROM AUTHOR]

Surface defect detection is an essential task for ensuring the quality of products. Many excellent object detectors have been employed to detect surface defects in resent years, which has achieved outstanding success. To further improve the detection performance, a defect detector based on state‐of‐the‐art YOLOv8, named improved YOLOv8 by neck, head and data (NHD‐YOLO), is proposed. Specifically, YOLOv8 from three crucial aspects including neck, head and data is improved. First, a shortcut feature pyramid network is designed to effectively fuse features from backbone by improving the information transmission. Then, an adaptive decoupled head is proposed to alleviate the feature spatial misalignment between the classification and regression tasks. Finally, to enhance the training on small objects, a data augmentation method named selective small object copy and paste is proposed. Extensive experiments are conducted on three real‐world datasets: detection dataset from Northeastern University (NEU‐DET), printed circuit boards from Peking University (PKU‐Market‐PCB) and common objects in context (COCO). According to the results, NHD‐YOLO achieves the highest detection accuracy and exhibits outstanding inference speed and generalisation performance. [ABSTRACT FROM AUTHOR]

Multi‐label image recognition (MLR) is a significant branch of image classification that aims to assign multiple categorical labels to each input. Previous research has focused on enhancing the learning of category‐related regional features. However, the potential impact of multi‐scale distributions in intra‐ and inter‐category targets on MLR tends to be neglected. Besides, semantic consistency for categories is restricted to be considered on single‐scale features, resulting in suboptimal feature extraction. To address the limitations of above, a Multi‐stage Feature Aggregation (MSFA) network is proposed. In MSFA, a novel local feature extraction method is suggested to progressively extract category‐related high‐resolution local features in both spatial and channel dimensions. Subsequently, local and global features are fused without additional up‐ and down‐sampling to enrich the scale diversity of the features while incorporating refined class‐specific information. Furthermore, a hierarchical prediction scheme for MLR is proposed, which generates classification confidence corresponding to different scales under hierarchical loss supervision. Consequently, the final output of the network comes from the joint prediction by the classifiers on multi‐scale features, ensuring a stronger feature extraction capability. The extensive experiments have been carried on VOC and MS‐COCO datasets, and the superiority of MSFA over existing mainstream methods has been verified. [ABSTRACT FROM AUTHOR]

To address the challenges of detecting a large number of objects and a high proportion of small objects in aerial drone imagery, an aerial dense small object detection algorithm called coordinate position attention module you only look once (CPAM‐YOLO) is proposed based on the coordinate position attention module (CPAM). In the backbone network of CPAM‐YOLO, a CPAM is proposed and embedded that decomposes channel attention into two 1D feature encoding processes, and selectively combines the features of each position through the weighted sum of all position features. Finally, features are aggregated along two spatial directions, increasing the effective information utilization of input feature positions and channels. The backbone network, feature enhancement network, and detection heads have been optimized to improve detection accuracy while ensuring a lightweight detection network. Using lightweight backbone networks to significantly reduce the number of parameters while using high‐resolution feature enhancement networks to retain more semantic and detailed features. The algorithm's performance was evaluated using the publicly available VisDrone2019 dataset. Compared to the baseline network YOLOv5l, CPAM‐YOLO achieved a 4.5% improvement in mAP0.5 and a 3.2% improvement in mAP0.95. These experimental results demonstrate the strong practicality of the CPAM‐YOLO object detection network for detecting dense small objects in aerial image. [ABSTRACT FROM AUTHOR]

Person re‐identification represents a pivotal sub‐problem in image retrieval, boasting broad application prospects in fields such as intelligent security and video surveillance. However, most existing person re‐identification methods predominantly focus solely on visual features pertaining to the person targets, thereby disregarding some supporting information closely related to the scene context. In the context of athlete re‐identification during sports event scenes, the athlete bib number is fully considered, an important clue that can provide different athletes' identities, and the traditional visual features of the person and high‐level semantic information of the bib number text are fused. A multi‐source information mutual gain mechanism is designed to improve the accuracy of the person re‐identification task. In the existing only publicly available marathon bib number dataset RBNR, the recognition accuracy of this method is significantly superior to that of the existing person re‐identification method. In addition, this paper constructs and publishes an athlete re‐identification dataset (HNNU‐ReID8000) for mainstream sports events, and the mean average precision (mAP) value of this method reaches 96.1% on this dataset, significantly ahead of existing state‐of‐the‐art person re‐identification methods. The code and the HNNU‐ReID8000 dataset will be released at https://github.com/yanbin‐zhu/zyb_person‐reid. [ABSTRACT FROM AUTHOR]

Due to the large computational requirements of object detection algorithms, high-resolution remote sensing vehicle detection always involves numerous small objects, high level of background complexity, and challenges in balancing model accuracy and parameter count. The attention mechanism and efficient architecture lightweight-YOLO (AMEA-YOLO) is proposed in this paper. A lightweight network as the backbone network of AMEA-YOLO is designed, and it could maintain model accuracy and ensure good lightweight. FasterNet is employed to accelerate model training speed. The enhanced deep second-order channel attention module (EnhancedSOCA) is utilized to improve the image high-resolution. In addition, a lightweight module is devised to further reduce the model's weight. The implementation of the HardSwish activation function improves model accuracy. The experimental results indicate that the AMEA-YOLO algorithm could ensure model lightweight and accurate performance. [ABSTRACT FROM AUTHOR]

Aiming at the problems about the incompleteness and low accuracy in classifying image feature extraction in existing image object detection methods. First, an improved image object detection method based on faster Region-Convolutional Neural Network (RCNN) is proposed, and Region of Interest (ROI) align is used instead of RoI pooling to reduce the error in the pooling process. Second, it adds the layer of convolution before adding network full-connection layer, thus reducing its parameters, enhance the performance of the classifier and avoid over-fitting. Finally, the combination of softmax and central loss functions is for training network-based model to increase the differences between categories and reduce the changes within categories, and thus the model with network could have more targeted and diversified features. Research results found that in total, method average accuracy is 91.04%, indicating higher than the accuracy of other methods and has good image target detection ability. [ABSTRACT FROM AUTHOR]

As an important method of image processing, image differentiation enables edge detection of targets to achieve recognition of object features and information compression and the computation speed can be boosted by optical information techniques. Traditional optical image differentiation methods mainly rely on spatial spectrum filtering by using classical 4f system, while some work focus on 1D or single‐direction differentiation. It is only in recent years that the rapid development of metasurfaces has facilitated image differentiation methods. In this work, a Laplace operation device is demonstrated based on a silicon hollow brick dielectric resonant metasurface for incident light field. The optical transfer function (OTF) required by the optical Laplace operation can be obtained by exciting an angularly selective toroidal dipole (TD) resonance supported by the metasurface. This hollow silicon brick differentiator not only realizes 2D second‐order edge detection but also has a numerical aperture close to 0.4 and a broad working wavelength range >100 nm and can be directly integrated with imaging systems. Such metadevice may be potentially applied in the fields of optical sensing, microscopy, machine vision, biomedical imaging, etc. [ABSTRACT FROM AUTHOR]

Background: The detection of internal defects in seeds via non-destructive imaging techniques is a topic of high interest to optimize the quality of seed lots. In this context, X-ray imaging is especially suited. Recent studies have shown the feasibility of defect detection via deep learning models in 3D tomography images. We demonstrate the possibility of performing such deep learning-based analysis on 2D X-ray radiography for a faster yet robust method via the X-Robustifier pipeline proposed in this article. Results: 2D X-ray images of both defective and defect-free seeds were acquired. A deep learning model based on state-of-the-art object detection neural networks is proposed. Specific data augmentation techniques are introduced to compensate for the low ratio of defects and increase the robustness to variation of the physical parameters of the X-ray imaging systems. The seed defects were accurately detected (F1-score >90%), surpassing human performance in computation time and error rates. The robustness of these models against the principal distortions commonly found in actual agro-industrial conditions is demonstrated, in particular, the robustness to physical noise, dimensionality reduction and the presence of seed coating. Conclusion: This work provides a full pipeline to automatically detect common defects in seeds via 2D X-ray imaging. The method is illustrated on sugar beet and faba bean and could be efficiently extended to other species via the proposed generic X-ray data processing approach (X-Robustifier). Beyond a simple proof of feasibility, this constitutes important results toward the effective use in the routine of deep learning-based automatic detection of seed defects. [ABSTRACT FROM AUTHOR]

There are numerous reports of enhanced or emerged visual arts abilities in patients with semantic impairment. These reports led to the theory that a loss of function on the language side of the brain can result in changes of ability to draw and/or to paint. Further, the left posterior middle temporal gyrus (l-pMTG) has been revealed to contribute to the higher control semantic mechanisms with objects recognition and integration of visual information, within a widely distributed network of the left hemisphere. Nevertheless, the theory has not been fully studied in neural bases. The aim of this study is to examine role of the l-pMTG on shape recognition and its reconstruction within drawing behavior, by using a combining method of the repetitive transcranial magnetic stimulation (rTMS) and functional near-infrared spectroscopy (fNIRS). Eighteen healthy participants received a low frequency inhibitory rTMS to their l-pMTG during the drawing task of the Benton Visual Retention Test (BVRT). There was a significant decrease of the mean accuracy of reproductions in the Complex designs of the BVRT, compared to the Simple and Medium designs. The fNIRS data showed strong negative correlations with the results of the BVRT. Though our hypothesis had a contradiction that rTMS would have inhibited the brain activity in the stimulated site, the results suggest that shape recognition and its reconstruction such as the BVRT require neural activations of the l-TL as well as that of the l-pMTG. [ABSTRACT FROM AUTHOR]

This work concerns how to effectively detect the fire in early stage using computer vision method. As known, the flame of early fire is small and cannot be effectively detected by traditional fire detectors. Inspired by color characteristics of flame, we proposed a Shallow Guide Deep Network (SGDNet) to address the problems in existing early fire detection models. We first investigate the feature of fire in YCbCr color space, then design an SGD module to fuse shallow features, so as to guide the fusion of deep features. Backbone, anchors, head and IoU of model are redesigned according to the features of early fire to not only fuse the deep features but also reduce the size and infer time. Finally, we implement a Early Stage Fire Detection System based on our SGDNet, using embedded device as computing platform, connecting 4 IP cameras for test. Multithread is widely utilized in system for detecting and the reading and conversion operations of video streams, which effectively improves the execution efficiency and reduces the delay of system. Experimental results on dataset show high performance of our model with the advantage of small size and parameter. Application in actual scenarios proves that the delay for detection is about 1.2 s, which fulfills the requirement of early fire warning. [ABSTRACT FROM AUTHOR]

In recent years, many deep learning-based object detection methods have performed well in various applications, especially in large-scale object detection. However, when detecting small targets, previous object detection algorithms cannot achieve good results due to the characteristics of the small targets themselves. To address the aforementioned issues, we propose the small object algorithm model MCF-YOLOv5, which has undergone three improvements based on YOLOv5. Firstly, a data augmentation strategy combining Mixup and Mosaic is used to increase the number of small targets in the image and reduce the interference of noise and changes in detection. Secondly, in order to accurately locate the position of small targets and reduce the impact of unimportant information on small targets in the image, the attention mechanism coordinate attention is introduced in YOLOv5's neck network. Finally, we improve the Feature Pyramid Network (FPN) structure and add a small object detection layer to enhance the feature extraction ability of small objects and improve the detection accuracy of small objects. The experimental results show that, with a small increase in computational complexity, the proposed MCF-YOLOv5 achieves better performance than the baseline on both the VisDrone2021 dataset and the Tsinghua Tencent100K dataset. Compared with YOLOv5, MCF-YOLOv5 has improved detection APsmall by 3.3% and 3.6%, respectively. [ABSTRACT FROM AUTHOR]

In this study, we introduce an innovative methodology for the detection of helmet usage violations among motorcyclists, integrating the YOLOv8 object detection algorithm with deep convolutional generative adversarial networks (DCGANs). The objective of this research is to enhance the precision of existing helmet violation detection techniques, which are typically reliant on manual inspection and susceptible to inaccuracies. The proposed methodology involves model training on an extensive dataset comprising both authentic and synthetic images, and demonstrates high accuracy in identifying helmet violations, including scenarios with multiple riders. Data augmentation, in conjunction with synthetic images produced by DCGANs, is utilized to expand the training data volume, particularly focusing on imbalanced classes, thereby facilitating superior model generalization to real-world circumstances. The stand-alone YOLOv8 model exhibited an F1 score of 0.91 for all classes at a confidence level of 0.617, whereas the DCGANs + YOLOv8 model demonstrated an F1 score of 0.96 for all classes at a reduced confidence level of 0.334. These findings highlight the potential of DCGANs in enhancing the accuracy of helmet rule violation detection, thus fostering safer motorcycling practices. [ABSTRACT FROM AUTHOR]

Image understanding plays a pivotal role in various computer vision tasks, such as extraction of essential features from images, object detection, and segmentation. At a higher level of granularity, both semantic and instance segmentation are necessary for fully grasping a scene. In recent times, the concept of panoptic segmentation has emerged as a field of study that unifies semantic and instance segmentation. This article sheds light on the pivotal role of panoptic segmentation as a visualization tool for understanding scene components, including object detection, categorization, and precise localization of scene elements. Advancements in achieving panoptic segmentation and suggested improvements to the predicted outputs through a top-down approach are discussed. Furthermore, datasets relevant to both scene recognition and panoptic segmentation are explored to facilitate a comparative analysis. Finally, the article outlines certain promising directions in image recognition and analysis by underlining the ongoing evolution in image understanding methodologies. [ABSTRACT FROM AUTHOR]

Ancient Chinese characters known as oracle bone inscriptions (OBIs) were inscribed on turtle shells and animal bones, and they boast a rich history dating back over 3600 years. The detection of OBIs is one of the most basic tasks in OBI research. The current research aimed to determine the precise location of OBIs with rubbing images. Given the low clarity, severe noise, and cracks in oracle bone inscriptions, the mainstream networks within the realm of deep learning possess low detection accuracy on the OBI detection dataset. To address this issue, this study analyzed the significant research progress in oracle bone script detection both domestically and internationally. Then, based on the YOLOv8 algorithm, according to the characteristics of OBI rubbing images, the algorithm was improved accordingly. The proposed algorithm added a small target detection head, modified the loss function, and embedded a CBAM. The results show that the improved model achieves an F-measure of 84.3%, surpassing the baseline model by approximately 1.8%. [ABSTRACT FROM AUTHOR]

To solve the problem of poor localization accuracy and robustness of visual simultaneous localization and mapping (SLAM) systems in highly dynamic environments, this paper proposes a dynamic visual SLAM algorithm called FFD-SLAM that fuses the target detection network with the optical flow method. The algorithm considers ORB-SLAM2 as the basic framework, joins the semantic thread in parallel with its tracking thread, initially obtains the set of feature points through the real-time detection of dynamic objects in the environment through YOLOv5 in the semantic thread, then filters the set of feature points obtained in the semantic thread through the optical flow module, and finally utilizes the remaining static feature points for the matching calculation. Experiments showed that the proposed algorithm showed an improvement of approximately 97% in the localization accuracy compared with the ORB-SLAM2 algorithm in a highly dynamic environment, which effectively improves the localization accuracy and robustness of the system. The proposed algorithm also showed a higher real-time performance compared with some excellent dynamic SLAM algorithms. [ABSTRACT FROM AUTHOR]

Object detection in aerial images has become a focus in recent years due to the expansion of its application fields. Aerial objects have the characteristics of multi-scale, arbitrary angle and dense arrangement, which brings considerable challenges to the task. Based on the efficient one-stage detectors, most methods design modules to adaptively align the feature receptive field with the anchors to improve the accuracy of the bounding box regression and calculate loss according to parameter bias. Current methods are not adequately data-driven in feature optimization and the angle parameter regression faces boundary problems. To handle these problems, in this letter, we propose an Align-Focus detector (AFDet) for aerial image object detection. We introduce the ideology of deformable multi-head self-attention to feature optimization and design a new Align-Focus Module (AFM) which can sensitively focus feature encoding response to the real texture area of the objects. In addition, we apply KF-IOU Loss to solve the boundary problem. We conduct necessary experiments on DOTA and HRSC2016 datasets, and AFDet achieves the highest mAP performance compared to the existing methods. [ABSTRACT FROM AUTHOR]

Hyperspectral LiDAR (HSL) has been utilized as an efficacious technique in object classification and recognition based on its unique capability to obtain ranges and spectra synchronously. Different kinds of HSL prototypes with varied structures have been promoted and measured its performance. However, almost all of these HSL prototypes employ complex and large spectroscopic devices, such as an Acousto-Optic Tunable Filter and Liquid-Crystal Tunable Filter, which makes this HSL system bulky and expensive, and then hinders its extensive application in many fields. In this paper, a smart and smaller spectroscopic component, an intergraded optical filter (IOF), is promoted to miniaturize these HSL systems. The system calibration, range precision, and spectral profile experiments were carried out to test the HSL prototype. Although the IOF employed here only covered a wavelength range of 699–758 nm with a six-channel passband and showed a transmittance of less than 50%, the HSL prototype showed excellent performance in ranging and spectral profile collecting. The spectral profiles collected are well in accordance with those acquired based on the AOTF. The spectral profiles of the fruits, vegetables, plants, and ore samples collected by the HSL based on an IOF can effectively reveal the status of the plants, the component materials, and ore species. Finally, we also showed the integrated design of the HSL based on a three-dimensional IOF and combined with a detector. The performance and designs of this HSL system based on an IOF show great potential for miniaturizing in some specific applications. [ABSTRACT FROM AUTHOR]

Facing the significant challenge of 3D object detection in complex weather conditions and road environments, existing algorithms based on single-frame point cloud data struggle to achieve desirable results. These methods typically focus on spatial relationships within a single frame, overlooking the semantic correlations and spatiotemporal continuity between consecutive frames. This leads to discontinuities and abrupt changes in the detection outcomes. To address this issue, this paper proposes a multi-frame 3D object detection algorithm based on a deformable spatiotemporal Transformer. Specifically, a deformable cross-scale Transformer module is devised, incorporating a multi-scale offset mechanism that non-uniformly samples features at different scales, enhancing the spatial information aggregation capability of the output features. Simultaneously, to address the issue of feature misalignment during multi-frame feature fusion, a deformable cross-frame Transformer module is proposed. This module incorporates independently learnable offset parameters for different frame features, enabling the model to adaptively correlate dynamic features across multiple frames and improve the temporal information utilization of the model. A proposal-aware sampling algorithm is introduced to significantly increase the foreground point recall, further optimizing the efficiency of feature extraction. The obtained multi-scale and multi-frame voxel features are subjected to an adaptive fusion weight extraction module, referred to as the proposed mixed voxel set extraction module. This module allows the model to adaptively obtain mixed features containing both spatial and temporal information. The effectiveness of the proposed algorithm is validated on the KITTI, nuScenes, and self-collected urban datasets. The proposed algorithm achieves an average precision improvement of 2.1% over the latest multi-frame-based algorithms. [ABSTRACT FROM AUTHOR]

Point cloud-based detection focuses on land traffic, rarely marine, facing issues with ships: it struggles in bad weather due to reliance on adverse weather data and fails to detect ships effectively due to overlooking size and appearance differences. Addressing the above challenges, our work introduces point cloud data of marine scenarios under realistically simulated adverse weather conditions and a dedicated Ship Detector tailored for marine environments. To adapt to various maritime weather conditions, we simulate realistic rain and fog in collected marine scene point cloud data. Additionally, addressing the issue of losing geometric and height information during feature extraction for large objects, we propose a Ship Detector. It employs a dual-branch sparse convolution layer for extracting multi-scale 3D feature maps, effectively minimizing height information loss. Additionally, a multi-scale 2D convolution module is utilized, which encodes and decodes feature maps and directly employs 3D feature maps for target prediction. To reduce dependency on existing data and enhance model robustness, our training dataset includes simulated point cloud data representing adverse weather conditions. In maritime point cloud ship detection, our Ship Detector, compared to adjusted small object detectors, demonstrates the best performance. [ABSTRACT FROM AUTHOR]

In response to the challenges posed by small objects in remote sensing images, such as low resolution, complex backgrounds, and severe occlusions, this paper proposes a lightweight improved model based on YOLOv8n. During the detection of small objects, the feature fusion part of the YOLOv8n algorithm retrieves relatively fewer features of small objects from the backbone network compared to large objects, resulting in low detection accuracy for small objects. To address this issue, firstly, this paper adds a dedicated small object detection layer in the feature fusion network to better integrate the features of small objects into the feature fusion part of the model. Secondly, the SSFF module is introduced to facilitate multi-scale feature fusion, enabling the model to capture more gradient paths and further improve accuracy while reducing model parameters. Finally, the HPANet structure is proposed, replacing the Path Aggregation Network with HPANet. Compared to the original YOLOv8n algorithm, the recognition accuracy of mAP@0.5 on the VisDrone data set and the AI-TOD data set has increased by 14.3% and 17.9%, respectively, while the recognition accuracy of mAP@0.5:0.95 has increased by 17.1% and 19.8%, respectively. The proposed method reduces the parameter count by 33% and the model size by 31.7% compared to the original model. Experimental results demonstrate that the proposed method can quickly and accurately identify small objects in complex backgrounds. [ABSTRACT FROM AUTHOR]

LiDAR-based 3D object detection and localization are crucial components of autonomous navigation systems, including autonomous vehicles and mobile robots. Most existing LiDAR-based 3D object detection and localization approaches primarily use geometric or structural feature abstractions from LiDAR point clouds. However, these approaches can be susceptible to environmental noise due to adverse weather conditions or the presence of highly scattering media. In this work, we propose an intensity-aware voxel encoder for robust 3D object detection. The proposed voxel encoder generates an intensity histogram that describes the distribution of point intensities within a voxel and is used to enhance the voxel feature set. We integrate this intensity-aware encoder into an efficient single-stage voxel-based detector for 3D object detection. Experimental results obtained using the KITTI dataset show that our method achieves comparable results with respect to the state-of-the-art method for car objects in 3D detection and from a bird's-eye view and superior results for pedestrian and cyclic objects. Furthermore, our model can achieve a detection rate of 40.7 FPS during inference time, which is higher than that of the state-of-the-art methods and incurs a lower computational cost. [ABSTRACT FROM AUTHOR]

Structural engineers are often required to draw two-dimensional engineering sketches for quick structural analysis, either by hand calculation or using analysis software. However, calculation by hand is slow and error-prone, and the manual conversion of a hand-drawn sketch into a virtual model is tedious and time-consuming. This paper presents a complete and autonomous framework for converting a hand-drawn engineering sketch into an analyzed structural model using a camera and computer vision. In this framework, a computer vision object detection stage initially extracts information about the raw features in the image of the beam diagram. Next, a computer vision number-reading model transcribes any handwritten numerals appearing in the image. Then, feature association models are applied to characterize the relationships among the detected features in order to build a comprehensive structural model. Finally, the structural model generated is analyzed using OpenSees. In the system presented, the object detection model achieves a mean average precision of 99.1%, the number-reading model achieves an accuracy of 99.0%, and the models in the feature association stage achieve accuracies ranging from 95.1% to 99.5%. Overall, the tool analyzes 45.0% of images entirely correctly and the remaining 55.0% of images partially correctly. The proposed framework holds promise for other types of structural sketches, such as trusses and frames. Moreover, it can be a valuable tool for structural engineers that is capable of improving the efficiency, safety, and sustainability of future construction projects. [ABSTRACT FROM AUTHOR]

Underwater visual detection technology is crucial for marine exploration and monitoring. Given the growing demand for accurate underwater target recognition, this study introduces an innovative architecture, YOLOv8-MU, which significantly enhances the detection accuracy. This model incorporates the large kernel block (LarK block) from UniRepLKNet to optimize the backbone network, achieving a broader receptive field without increasing the model's depth. Additionally, the integration of C2fSTR, which combines the Swin transformer with the C2f module, and the SPPFCSPC_EMA module, which blends Cross-Stage Partial Fast Spatial Pyramid Pooling (SPPFCSPC) with attention mechanisms, notably improves the detection accuracy and robustness for various biological targets. A fusion block from DAMO-YOLO further enhances the multi-scale feature extraction capabilities in the model's neck. Moreover, the adoption of the MPDIoU loss function, designed around the vertex distance, effectively addresses the challenges of localization accuracy and boundary clarity in underwater organism detection. The experimental results on the URPC2019 dataset indicate that YOLOv8-MU achieves an mAP@0.5 of 78.4%, showing an improvement of 4.0% over the original YOLOv8 model. Additionally, on the URPC2020 dataset, it achieves 80.9%, and, on the Aquarium dataset, it reaches 75.5%, surpassing other models, including YOLOv5 and YOLOv8n, thus confirming the wide applicability and generalization capabilities of our proposed improved model architecture. Furthermore, an evaluation on the improved URPC2019 dataset demonstrates leading performance (SOTA), with an mAP@0.5 of 88.1%, further verifying its superiority on this dataset. These results highlight the model's broad applicability and generalization capabilities across various underwater datasets. [ABSTRACT FROM AUTHOR]

In the realm of computer vision, the integration of advanced techniques into the pre-processing of RGB-D camera inputs poses a significant challenge, given the inherent complexities arising from diverse environmental conditions and varying object appearances. Therefore, this paper introduces FusionVision, an exhaustive pipeline adapted for the robust 3D segmentation of objects in RGB-D imagery. Traditional computer vision systems face limitations in simultaneously capturing precise object boundaries and achieving high-precision object detection on depth maps, as they are mainly proposed for RGB cameras. To address this challenge, FusionVision adopts an integrated approach by merging state-of-the-art object detection techniques, with advanced instance segmentation methods. The integration of these components enables a holistic (unified analysis of information obtained from both color RGB and depth D channels) interpretation of RGB-D data, facilitating the extraction of comprehensive and accurate object information in order to improve post-processes such as object 6D pose estimation, Simultanious Localization and Mapping (SLAM) operations, accurate 3D dataset extraction, etc. The proposed FusionVision pipeline employs YOLO for identifying objects within the RGB image domain. Subsequently, FastSAM, an innovative semantic segmentation model, is applied to delineate object boundaries, yielding refined segmentation masks. The synergy between these components and their integration into 3D scene understanding ensures a cohesive fusion of object detection and segmentation, enhancing overall precision in 3D object segmentation. [ABSTRACT FROM AUTHOR]

High-pressure pipelines are critical for transporting hazardous materials over long distances, but they face threats from third-party interference activities. Preventive measures are implemented, but interference accidents can still occur, making the need for high-quality detection strategies vital. This paper proposes an end-to-end Artificial Intelligence of Things (AIoT) solution to detect potential interference threats in real time. The solution involves developing a smart visual sensor capable of processing images using state-of-the-art computer vision algorithms and transmitting alerts to pipeline operators in real time. The system's core is based on the object-detection model (e.g., You Only Look Once version 4 (YOLOv4) and DETR with Improved deNoising anchOr boxes (DINO)), trained on a custom Pipeline Visual Threat Assessment (Pipe-VisTA) dataset. Among the trained models, DINO was able to achieve the best Mean Average Precision (mAP) of 71.2% for the unseen test dataset. However, for the deployment on a limited computational-ability edge computer (i.e., the NVIDIA Jetson Nano), the simpler and TensorRT-optimized YOLOv4 model was used, which achieved a mAP of 61.8% for the test dataset. The developed AIoT device captures the image using a camera, processes on the edge using the trained YOLOv4 model to detect the potential threat, transmits the threat alert to a Fleet Portal via LoRaWAN, and hosts the alert on a dashboard via a satellite network. The device has been fully tested in the field to ensure its functionality prior to deployment for the SEA Gas use-case. The AIoT smart solution has been deployed across the 10km stretch of the SEA Gas pipeline across the Murray Bridge section. In total, 48 AIoT devices and three Fleet Portals are installed to ensure the line-of-sight communication between the devices and portals. [ABSTRACT FROM AUTHOR]