Search

Vehicle-camel collision is a persistent issue in countries where population of camels is high such as Saudi Arabia. The purpose of the research is to introduce a new solution to eliminate this issue. Previous solutions, such as fencing the sides of the roads, designing better camel warning signs and fining camel owners when camels cross high traffic roads, are either expensive, ineffective, or hard to implement. Therefore, in this work, we harness the power of deep learning to tackle this problem. In particular, we use state-of-the-art deep learning object detectors to detect camels on roads with high accuracy. Results show that all implemented models were capable of detecting camels on or near roads. Moreover, the single-stage detector Yolo v3 was found to be the most accurate and is as fast as its successor Yolo v4. Findings of this work helped select the deep learning model needed for a reliable and automatic vehicle-camel collision avoidance system.

For the problem of insufficient small target detection ability of the existing network model, a vehicle target detection method based on the improved YOLO V3 network model is proposed in the article. The improvement of the algorithm model can effectively improve the detection ability of small target vehicles in aerial photography. The optimization and adjustment of the anchor box and the improvement of the network residual module have improved the small target detection effect of the algorithm. Furthermore, the introduction of the rectangular prediction frame with orientation angles into the model of this article can improve the vehicle positioning efficiency of the algorithm, greatly reduce the problem of wrong detection and missed detection of vehicles in the model, and provide ideas for solving related problems. Experiments show that the accuracy rate of the improved algorithm model is 89.3%. Compared to the YOLO V3 algorithm, it is improved by 15.9%. The recall rate is improved by 16%, and the F1 value is also improved by 15.9%, which greatly increased the detection efficiency of aerial vehicles.

Ecological biodiversity is declining at an unprecedented rate. To combat such irreversible changes in natural ecosystems, biodiversity conservation initiatives are being conducted globally. However, the lack of a feasible methodology to quantify biodiversity in real-time and investigate population dynamics in spatiotemporal scales prevents the use of ecological data in environmental planning. Traditionally, ecological studies rely on the census of an animal population by the “capture, mark and recapture” technique. In this technique, human field workers manually count, tag and observe tagged individuals, making it time-consuming, expensive, and cumbersome to patrol the entire area. Recent research has also demonstrated the potential for inexpensive and accessible sensors for ecological data monitoring. However, stationary sensors collect localised data which is highly specific on the placement of the setup. In this research, we propose the methodology for biodiversity monitoring utilising state-of-the-art deep learning (DL) methods operating in real-time on sample payloads of mobile robots. Such trained DL algorithms demonstrate a mean average precision (mAP) of 90.51% in an average inference time of 67.62 milliseconds within 6,000 training epochs. We claim that the use of such mobile platform setups inferring real-time ecological data can help us achieve our goal of quick and effective biodiversity surveys. An experimental test payload is fabricated, and online as well as offline field surveys are conducted, validating the proposed methodology for species identification that can be further extended to geo-localisation of flora and fauna in any ecosystem.

Object detection is used to identify objects in real time using some deep learning algorithms. In this work, wheat plant data set around the world is collected to study the wheat heads. Using global data, a common solution for measuring the amount and size of wheat heads is formulated. YOLO V3 (You Look Only Once Version 3) and Faster RCNN is a real time object detection algorithm which is used to identify objects in videos and images. The global wheat detection dataset is used for the prediction which contains 3000+ training images and few test images with csv files which have information about the ground box labels of the images. To build a data pipeline for the model Tensorflow data API or Keras Data Generators is used.

IntroductionThe primary factor for cardiovascular disease and upcoming cardiovascular events is atherosclerosis. Recently, carotid plaque texture, as observed on ultrasonography, is varied and difficult to classify with the human eye due to substantial inter-observer variability. High-resolution magnetic resonance (MR) plaque imaging offers naturally superior soft tissue contrasts to computed tomography (CT) and ultrasonography, and combining different contrast weightings may provide more useful information. Radiation freeness and operator independence are two additional benefits of M RI. However, other than preliminary research on MR texture analysis of basilar artery plaque, there is currently no information addressing MR radiomics on the carotid plaque.MethodsFor the automatic segmentation of MRI scans to detect carotid plaque for stroke risk assessment, there is a need for a computer-aided autonomous framework to classify MRI scans automatically. We used to detect carotid plaque from MRI scans for stroke risk assessment pre-trained models, fine-tuned them, and adjusted hyperparameters according to our problem.ResultsOur trained YOLO V3 model achieved 94.81% accuracy, RCNN achieved 92.53% accuracy, and MobileNet achieved 90.23% in identifying carotid plaque from MRI scans for stroke risk assessment. Our approach will prevent incorrect diagnoses brought on by poor image quality and personal experience.ConclusionThe evaluations in this work have demonstrated that this methodology produces acceptable results for classifying magnetic resonance imaging (MRI) data.

Abstract Background The correct identification of pills is very important to ensure the safe administration of drugs to patients. Here, we use three current mainstream object detection models, namely RetinaNet, Single Shot Multi-Box Detector (SSD), and You Only Look Once v3(YOLO v3), to identify pills and compare the associated performance. Methods In this paper, we introduce the basic principles of three object detection models. We trained each algorithm on a pill image dataset and analyzed the performance of the three models to determine the best pill recognition model. The models were then used to detect difficult samples and we compared the results. Results The mean average precision (MAP) of RetinaNet reached 82.89%, but the frames per second (FPS) is only one third of YOLO v3, which makes it difficult to achieve real-time performance. SSD does not perform as well on the indicators of MAP and FPS. Although the MAP of YOLO v3 is slightly lower than the others (80.69%), it has a significant advantage in terms of detection speed. YOLO v3 also performed better when tasked with hard sample detection, and therefore the model is more suitable for deployment in hospital equipment. Conclusion Our study reveals that object detection can be applied for real-time pill identification in a hospital pharmacy, and YOLO v3 exhibits an advantage in detection speed while maintaining a satisfactory MAP.

Purpose: In order to improve the accuracy of liquid level detection in intravenous left auxiliary vein infusion and reduce the pain of patients with blood returning from intravenous infusion, we propose a deep learning based liquid level detection model of infusion levels to facilitate this operation. Method: We implemented a Yolo v3-based detection model of infusion level images in intravenous infusion, and at the same time, compare it with SURF image processing technique, RCNN, and Fast-RCNN methods. Results: The model in this paper is better than the comparison algorithm in Intersection over Union (IoU), precision, recall and test time. The liquid level detection model based on Yolo v3 has a precision of 0.9768, a recall rate of 0.9688, an IoU of 0.8943, and a test time of 2.9 s. Conclusion: The experimental results prove that the liquid level detection method based on deep learning has the characteristics of high accuracy and good real-time performance. This method can play a certain auxiliary role in the hospital environment and improve work efficiency of medical workers.

Based on the detection and recognition technology of YOLO v3 deep convolution neural network, an automatic recognition method of digital borehole image fractures is proposed. Firstly, the target detection principle of new version YOLO v3 is described in detail, then the borehole image of coal mine is selected to make data sets on VOC 2007, and the network structure of Darknet-53 is used for data training. The experimental results show that the detection method of borehole image fractures based on YOLO v3 can identify the feature information quickly and accurately, which provides a new technical support for the visual recognition of the surrounding rock fractures.

Convolutional Neural Networks (CNN) achieves perfection in traffic sign identification with enough annotated training data. The dataset determines the quality of the complete visual system based on CNN. Unfortunately, databases for traffic signs from the majority of the world’s nations are few. In this scenario, Generative Adversarial Networks (GAN) may be employed to produce more realistic and varied training pictures to supplement the actual arrangement of images. The purpose of this research is to describe how the quality of synthetic pictures created by DCGAN, LSGAN, and WGAN is determined. Our work combines synthetic images with original images to enhance datasets and verify the effectiveness of synthetic datasets. We use different numbers and sizes of images for training. Likewise, the Structural Similarity Index (SSIM) and Mean Square Error (MSE) were employed to assess picture quality. Our study quantifies the SSIM difference between the synthetic and actual images. When additional images are used for training, the synthetic image exhibits a high degree of resemblance to the genuine image. The highest SSIM value was achieved when using 200 total images as input and $32\times 32$ image size. Further, we augment the original picture dataset with synthetic pictures and compare the original image model to the synthesis image model. For this experiment, we are using the latest iterations of Yolo, Yolo V3, and Yolo V4. After mixing the real image with the synthesized image produced by LSGAN, the recognition performance has been improved, achieving an accuracy of 84.9% on Yolo V3 and an accuracy of 89.33% on Yolo V4.

Traditional object detection model uses artificial object features, resulting in poor detection accuracy. Object detection model based on deep learning has high detection accuracy. However, for application of coal mine rescue robot with high real -time and accuracy requirements, the obtained image information is less and object features are not obvious, resulting in poor object detection effect. In order to improve accuracy and speed of object detection, on the basis of YOLO V3 model, an object detection model of coal mine rescue robot based on multi -scale feature fusion is proposed. The model mainly includes feature extraction module and feature fusion module. The feature extraction module uses hole bottleneck and multi -scale convolution to obtain more abundant image feature information, so as to enhance expression ability of object feature and improve object classification accuracy and detection speed. The feature fusion module introduces spatial attention mechanism into feature pyramid to effectively fuse high -level feature map with rich semantic information and low -level feature map with rich location information, which makes up for lack of position information expression ability of high -level feature map, and improves object positioning accuracy. The model is deployed on embedded NVIDIA Jetson TX2 platform in coal mine rescue robot for post -disaster environment object detection experiment. The detection accuracy is 88.73% and detection speed is 28 frames per second, which meet real -time and precision requirements of object detection of coal mine rescue robot.

Abstract This study deals with the problem of rea-time obtaining quality data on the road traffic parameters based on the static street video surveillance camera data. The existing road traffic monitoring solutions are based on the use of traffic cameras located directly above the carriageways, which allows one to obtain fragmentary data on the speed and movement pattern of vehicles. The purpose of the study is to develop a system of high-quality and complete collection of real-time data, such as traffic flow intensity, driving directions, and average vehicle speed. At the same time, the data is collected within the entire functional area of intersections and adjacent road sections, which fall within the street video surveillance camera angle. Our solution is based on the use of the YOLOv3 neural network architecture and SORT open-source tracker. To train the neural network, we marked 6000 images and performed augmentation, which allowed us to form a dataset of 4.3 million vehicles. The basic performance of YOLO was improved using an additional mask branch and optimizing the shape of anchors. To determine the vehicle speed, we used a method of perspective transformation of coordinates from the original image to geographical coordinates. Testing of the system at night and in the daytime at six intersections showed the absolute percentage accuracy of vehicle counting, of no less than 92%. The error in determining the vehicle speed by the projection method, taking into account the camera calibration, did not exceed 1.5 km/h.

With the development of industrial automation, articulated robots have gradually replaced labor in the field of bolt installation. Although the installation efficiency has been improved, installation defects may still occur. Bolt installation defects can considerably affect the mechanical properties of structures and even lead to safety accidents. Therefore, in order to ensure the success rate of bolt assembly, an efficient and timely detection method of incorrect or missing assembly is needed. At present, the automatic detection of bolt installation defects mainly depends on a single type of sensor, which is prone to mis-inspection. Visual sensors can identify the incorrect or missing installation of bolts, but it cannot detect torque defects. Torque sensors can only be judged according to the torque and angel information, but cannot accurately identify the incorrect or missing installation of bolts. To solve this problem, a detection method of bolt installation defects based on multiple sensors is proposed. The trained YOLO (You Only Look Once) v3 network is used to judge the images collected by the visual sensor, and the recognition rate of visual detection is up to 99.75%, and the average confidence of the output is 0.947. The detection speed is 48 FPS, which meets the real-time requirement. At the same time, torque and angle sensors are used to judge the torque defects and whether bolts have slipped. Combined with the multi-sensor judgment results, this method can effectively identify defects such as missing bolts and sliding teeth. Finally, this paper carried out experiments to identify bolt installation defects such as incorrect, missing torque defects, and bolt slips. At this time, the traditional detection method based on a single type of sensor cannot be effectively identified, and the detection method based on multiple sensors can be accurately identified.

The obstacle avoidance system uses a YOLO model to detect obstacles in real-time and provide spatial information about their location and size. This information is then passed to the GTTS system, which generates audio alerts to notify the user of the presence of an obstacle and its location. The audio alerts are generated in a natural-sounding voice to provide the user with clear and concise information. To evaluate the effectiveness of our proposed system, we conducted experiments with visually impaired individuals in real-world scenarios. The results show that our system can significantly improve obstacle detection and avoidance performance compared to traditional methods. The participants reported high levels of satisfaction with the system’s performance and ease of use.

There are some problems with estrus detection in ewes in large-scale meat sheep farming: mainly, the manual detection method is labor-intensive and the contact sensor detection method causes stress reactions in ewes. To solve the abovementioned problems, we proposed a multi-objective detection layer neural network-based method for ewe estrus crawling behavior recognition. The approach we proposed has four main parts. Firstly, to address the problem of mismatch between our constructed ewe estrus dataset and the YOLO v3 anchor box size, we propose to obtain a new anchor box size by clustering the ewe estrus dataset using the K-means++ algorithm. Secondly, to address the problem of low model recognition precision caused by small imaging of distant ewes in the dataset, we added a 104 × 104 target detection layer, making the total target detection layer reach four layers, strengthening the model’s ability to learn shallow information and improving the model’s ability to detect small targets. Then, we added residual units to the residual structure of the model, so that the deep feature information of the model is not easily lost and further fused with the shallow feature information to speed up the training of the model. Finally, we maintain the aspect ratio of the images in the data-loading module of the model to reduce the distortion of the image information and increase the precision of the model. The experimental results show that our proposed model has 98.56% recognition precision, while recall was 98.04%, F1 value was 98%, mAP was 99.78%, FPS was 41 f/s, and model size was 276 M, which can meet the accurate and real-time recognition of ewe estrus behavior in large-scale meat sheep farming.

Fast and high-accuracy detection of underwater targets based on side scan sonar images has great potential for marine fisheries, underwater security, marine mapping, underwater engineering and other applications. The following problems, however, must be addressed when using low-resolution side scan sonar images for underwater target detection: (1) the detection performance is limited due to the restriction on the input of multi-scale images; (2) the widely used deep learning algorithms have a low detection effect due to their complex convolution layer structures; (3) the detection performance is limited due to insufficient model complexity in training process; and (4) the number of samples is not enough because of the bad dataset preprocessing methods. To solve these problems, an improved neural network for underwater target detection—which is based on side scan sonar images and fully utilizes spatial pyramid pooling and online dataset preprocessing based on the You Look Only Once version three (YOLO V3) algorithm—is proposed. The methodology of the proposed approach is as follows: (1) the AlexNet, GoogleNet, VGGNet and the ResNet networks and an adopted YOLO V3 algorithm were the backbone networks. The structure of the YOLO V3 model is more mature and compact and has higher target detection accuracy and better detection efficiency than the other models; (2) spatial pyramid pooling was added at the end of the convolution layer to improve detection performance. Spatial pyramid pooling breaks the scale restrictions when inputting images to improve feature extraction because spatial pyramid pooling enables the backbone network to learn faster at high accuracy; and (3) online dataset preprocessing based on YOLO V3 with spatial pyramid pooling increases the number of samples and improves the complexity of the model to further improve detection process performance. Three-side scan imagery datasets were used for training and were tested in experiments. The quantitative evaluation using Accuracy, Recall, Precision, mAP and F1-Score metrics indicates that: for the AlexNet, GoogleNet, VGGNet and ResNet algorithms, when spatial pyramid pooling is added to their backbone networks, the average detection accuracy of the three sets of data was improved by 2%, 4%, 2% and 2%, respectively, as compared to their original formulations. Compared with the original YOLO V3 model, the proposed ODP+YOLO V3+SPP underwater target detection algorithm model has improved detection performance through the mAP qualitative evaluation index has increased by 6%, the Precision qualitative evaluation index has increased by 13%, and the detection efficiency has increased by 9.34%. These demonstrate that adding spatial pyramid pooling and online dataset preprocessing can improve the target detection accuracy of these commonly used algorithms. The proposed, improved neural network with spatial pyramid pooling and online dataset preprocessing based on the YOLO V3 method achieves the highest scores for underwater target detection results for sunken ships, fish flocks and seafloor topography, with mAP scores of 98%, 91% and 96% for the above three kinds of datasets, respectively.

Convolutional neural networks (CNNs) have shown strong learning capabilities in computer vision tasks such as classification and detection. Especially with the introduction of excellent detection models such as YOLO (V1, V2 and V3) and Faster R-CNN, CNNs have greatly improved detection efficiency and accuracy. However, due to the special angle of view, small size, few features, and complicated background, CNNs that performs well in the ground perspective dataset, fails to reach a good detection accuracy in the remote sensing image dataset. To this end, based on the YOLO V3 model, we used feature maps of different depths as detection outputs to explore the reasons for the poor detection rate of small targets in remote sensing images by deep neural networks. We also analyzed the effect of neural network depth on small target detection, and found that the excessive deep semantic information of neural network has little effect on small target detection. Finally, the verification on the VEDAI dataset shows, that the fusion of shallow feature maps with precise location information and deep feature maps with rich semantics in the CNNs can effectively improve the accuracy of small target detection in remote sensing images.

Convolutional neural networks (CNNs) have shown strong learning capabilities in computer vision tasks such as classification and detection. Especially with the introduction of excellent detection models such as YOLO (V1, V2 and V3) and Faster R-CNN, CNNs have greatly improved detection efficiency and accuracy. However, due to the special angle of view, small size, few features, and complicated background, CNNs that performs well in the ground perspective dataset, fails to reach a good detection accuracy in the remote sensing image dataset. To this end, based on the YOLO V3 model, we used feature maps of different depths as detection outputs to explore the reasons for the poor detection rate of small targets in remote sensing images by deep neural networks. We also analyzed the effect of neural network depth on small target detection, and found that the excessive deep semantic information of neural network has little effect on small target detection. Finally, the verification on the VEDAI dataset shows, that the fusion of shallow feature maps with precise location information and deep feature maps with rich semantics in the CNNs can effectively improve the accuracy of small target detection in remote sensing images.

Aiming at the problems of electrical connector defect detection, such as low automation, low detection accuracy, slow detection speed, and poor robustness, an improved Yolo v3 algorithm was proposed in this paper to detect electrical connector defects. First, the K-means clustering algorithm is used to perform cluster analysis on the data set of this paper to obtain three kinds of candidate frames with aspect ratios, aiming at improving the detection accuracy for the defective objects in this paper; the 8-fold downsampled feature map outputted by the third residual block of the backbone network is upsampled 4 times, and the obtained feature map is merged with the 2-fold downsampled feature map outputted by the second residual block to obtain the fusion feature detection layer; the 6 DBL units passed by the target detection layer are changed to 2 DBL unit plus 2 residual units to improve feature reuse and acquisition; In addition, single-scale feature maps are chose for target detection in this paper instead of multi-scale prediction of the original network, which not only saves the calculation amount, but also avoids false detection to a certain extent.; A new detection method is proposed for relative rotation defects between the inner ring area and the outer ring area of the electrical connector. The qualitative and quantitative experimental results show that the improved Yolo v3 algorithm in this paper has better performance and speed for defect detection of various types of electrical connectors, with an accuracy rate of 93.5%, which is more accurate than Faster R-CNN. The original Yolo v3 is faster and basically meets the requirements of the industrial field for electrical connector testing.

The obtainment of road condition information during driving is extremely important for a driver. However, drivers usually cannot notice multiple information at the same time, which definitely increases certain safety risks. Considering this problem, this paper designs a road information collection plus alarm system based on artificial intelligence to monitor road information. The underlying core algorithm of this system adopts the YOLO v3 network with the best comprehensive detection performance in the end-to-end network. We use this network's advantage of fast detection speed to optimize on its original basis, and propose to “copy” part of the backbone network to build an auxiliary network, which enhances its feature extraction capability. Further, we apply the attention mechanism to the feature information fusion of the auxiliary network and the backbone network, suppress the invalid information channel, and improve the network processing efficiency. Besides, the training part of the network is optimized, and the mAP (mean Average Precision) is improved by setting the scale that meets the target to be detected. Through the test, the average test accuracy of the optimized network model reaches 84.76%, and the real-time detection speed on the 2080Ti reaches 41FPS. Compared with the previous network, the detection accuracy increases by 5.43% after optimization.

Road discrepancies such as potholes and road cracks are often present in our day-to-day commuting and travel. The cost of damage repairs caused by potholes has always been a concern for owners of any type of vehicle. Thus, an early detection processes can contribute to the swift response of road maintenance services and the prevention of pothole related accidents. In this paper, automatic detection of potholes is performed using the computer vision model library, You Look Only Once version 3, also known as Yolo v3. Light and weather during driving naturally affect our ability to observe road damage. Such adverse conditions also negatively influence the performance of visual object detectors. The aim of this work was to examine the effect adverse conditions have on pothole detection. The basic design of this study is therefore composed of two main parts: (1) dataset creation and data processing, and (2) dataset experiments using Yolo v3. Additionally, Sparse R-CNN was incorporated into our experiments. For this purpose, a dataset consisting of subsets of images recorded under different light and weather was developed. To the best of our knowledge, there exists no detailed analysis of pothole detection performance under adverse conditions. Despite the existence of newer libraries, Yolo v3 is still a competitive architecture that provides good results with lower hardware requirements.

We propose a lightweight neural network-based method to detect the estrus behavior of ewes. Our suggested method is mainly proposed to solve the problem of not being able to detect ewe estrus behavior in a timely and accurate manner in large-scale meat sheep farms. The three main steps of our proposed methodology include constructing the dataset, improving the network structure, and detecting the ewe estrus behavior based on the lightweight network. First, the dataset was constructed by capturing images from videos with estrus crawling behavior, and the data enhancement was performed to improve the generalization ability of the model at first. Second, the original Darknet-53 was replaced with the EfficientNet-B0 for feature extraction in YOLO V3 neural network to make the model lightweight and the deployment easier, thus shortening the detection time. In order to further obtain a higher accuracy of detecting the ewe estrus behavior, we joined the feature layers to the SENet attention module. Finally, the comparative results demonstrated that the proposed method had higher detection accuracy and FPS, as well as a smaller model size than the YOLO V3. The precision of the proposed scheme was 99.44%, recall was 95.54%, F1 value was 97%, AP was 99.78%, FPS was 48.39 f/s, and Model Size was 40.6 MB. This study thus provides an accurate, efficient, and lightweight detection method for the ewe estrus behavior in large-scale mutton sheep breeding.

Teeth detection and tooth segmentation are essential for processing Cone Beam Computed Tomography (CBCT) images. The accuracy decides the credibility of the subsequent applications, such as diagnosis, treatment plans in clinical practice or other research that is dependent on automatic dental identification. The main problems are complex noises and metal artefacts which would affect the accuracy of teeth detection and segmentation with traditional algorithms. In this study, we proposed a teeth-detection method to avoid the problems above and to accelerate the operation speed. In our method, (1) a Convolutional Neural Network (CNN) was employed to classify layer classes; (2) images were chosen to perform Region of Interest (ROI) cropping; (3) in ROI regions, we used a YOLO v3 and multi-level combined teeth detection method to locate each tooth bounding box; (4) we obtained tooth bounding boxes on all layers. We compared our method with a Faster R-CNN method which was commonly used in previous studies. The training and prediction time were shortened by 80% and 62% in our method, respectively. The Object Inclusion Ratio (OIR) metric of our method was 96.27%, while for the Faster R-CNN method, it was 91.40%. When testing images with severe noise or with different missing teeth, our method promises a stable result. In conclusion, our method of teeth detection on dental CBCT is practical and reliable for its high prediction speed and robust detection.

The reliability of electrical components affects the stable operation of the power system. Electrical components inspection has long been important issues in the intelligent power system. The main problems of traditional recognition methods of electrical components are low detection accuracy and poor real-time performance, which are challenging to extract necessary features from the inspection images. This paper proposes a way to detect the electrical components in the Unmanned Aerial Vehicle (UAV) inspection image based on You Only Look Once (YOLO) V3 algorithm. Due to some of the inspection images are not clear, which result in the reduction of the available dataset. On this basis, we adopt Super-Resolution Convolutional Neural Network (SRCNN) to realize super-resolution reconstruction on the blurred image, which achieves the expansion of the dataset. We compare the performance of the proposed method with other popular recognition methods. The results of experiment verify the effectiveness of the proposed method, and the technique reaches high recognition accuracy, good robustness, and strong real-time performance for UAV power inspection system.

Multi-object tracking has been a key research subject in many computer vision applications. We propose a novel approach based on multi-agent deep reinforcement learning (MADRL) for multi-object tracking to solve the problems in the existing tracking methods, such as a varying number of targets, non-causal, and non-realtime. At first, we choose YOLO V3 to detect the objects included in each frame. Unsuitable candidates were screened out and the rest of detection results are regarded as multiple agents and forming a multi-agent system. Independent Q-Learners (IQL) is used to learn the agents' policy, in which, each agent treats other agents as part of the environment. Then, we conducted offline learning in the training and online learning during the tracking. Our experiments demonstrate that the use of MADRL achieves better performance than the other state-of-art methods in precision, accuracy, and robustness.

This paper proposes a new Image-to-Image Translation (Pix2Pix) enabled deep learning method for traveling wave-based fault location. Unlike the previous methods that require a high sampling frequency of the PMU, the proposed method can translate the scale 1 detail component image provided by the low frequency PMU data to higher frequency ones via the Pix2Pix. This allows us to significantly improve the fault location accuracy. Test results via the YOLO v3 object recognition algorithm show that the images generated by pix2pix can be accurately identified. This enables to improve the estimation accuracy of the arrival time of the traveling wave head, leading to better fault location outcomes.

COVID-19 (Coronavirus) has affected our daily life and is slackening the global economy. In this fight against the COVID-19, social-distancing is proving to be an effective measure to slow down the transmission of coronavirus. In order to control the spread of transmission of COVID-19, social distancing is the best measure which aims to avoid close contact of people. In order to control the spread of transmission of COVID-19, social distancing is the best measure which aims to avoid close contact of people. With the aim of ensuring social- distancing norms in workplace and public places, we can develop a social-distancing detection tool that monitors if people are staying at a safe distance from each other. This can be done by examining real-time video streams from the cameras. In order to provide an effective solution, we are developing a model which has mainly two phases - firstly object detection phase where people will be detected from the video streams. Secondly showing the statistical analysis in the form of dashboards and sending alerts to concerned authorities to take necessary actions.

Countries around the world have paid increasing attention to the issue of marine security, and sea target detection is a key task to ensure marine safety. Therefore, it is of great significance to propose an efficient and accurate sea-surface target detection algorithm. The anchor-setting method of the traditional YOLO v3 only uses the degree of overlap between the anchor and the ground-truth box as the standard. As a result, the information of some feature maps cannot be used, and the required accuracy of target detection is hard to achieve in a complex sea environment. Therefore, two new anchor-setting methods for the visual detection of sea targets were proposed in this paper: the average method and the select-all method. In addition, cross PANet, a feature fusion structure for cross-feature maps was developed and was used to obtain a better baseline cross YOLO v3, where different anchor-setting methods were combined with a focal loss for experimental comparison in the datasets of sea buoys and existing sea ships, SeaBuoys and SeaShips, respectively. The results showed that the method proposed in this paper could significantly improve the accuracy of YOLO v3 in detecting sea-surface targets, and the highest value of mAP in the two datasets is 98.37% and 90.58%, respectively.

With the recent development of artificial intelligence along with information and communications infrastructure, a new paradigm of online services is being developed. Whereas in the past a service system could only exchange information of the service provider at the request of the user, information can now be provided by automatically analyzing a particular need, even without a direct user request. This also holds for online platforms of used-vehicle sales. In the past, consumers needed to inconveniently determine and classify the quality of information through static data provided by service and information providers. As a result, this service field has been harmful to consumers owing to such problems as false sales, fraud, and exaggerated advertising. Despite significant efforts of platform providers, there are limited human resources for censoring the vast amounts of data uploaded by sellers. Therefore, in this study, an algorithm called YOLOv3+MSSIM Type 2 for automatically censoring the data of used-vehicle sales on an online platform was developed. To this end, an artificial intelligence system that can automatically analyze an object in a vehicle video uploaded by a seller, and an artificial intelligence system that can filter the vehicle-specific terms and profanity from the seller’s video presentation, were also developed. As a result of evaluating the developed system, the average execution speed of the proposed YOLOv3+MSSIM Type 2 algorithm was 78.6 ms faster than that of the pure YOLOv3 algorithm, and the average frame rate per second was improved by 40.22 fps. In addition, the average GPU utilization rate was improved by 23.05%, proving the efficiency.

Artificial intelligence (AI) is widely used in pattern recognition and positioning. In most of the geological exploration applications, it needs to locate and identify underground objects according to electromagnetic wave characteristics from the ground-penetrating radar (GPR) images. Currently, a few robust AI approach can detect targets by real-time with high precision or automation for GPR images recognition. This paper proposes an approach that can be used to identify parabolic targets with different sizes and underground soil or concrete structure voids based on you only look once (YOLO) v3. With the TensorFlow 1.13.0 developed by Google, we construct YOLO v3 neural network to realize real-time pattern recognition of GPR images. We propose the specific coding method for the GPR image samples in Yolo V3 to improve the prediction accuracy of bounding boxes. At the same time, K-means algorithm is also applied to select anchor boxes to improve the accuracy of positioning hyperbolic vertex. For some instances electromagnetic-vacillated signals may occur, which refers to multiple parabolic electromagnetic waves formed by strong conductive objects among soils or overlapping waveforms. This paper deals with the vacillating signal similarity intersection over union (IoU) (V-IoU) methods. Experimental result shows that the V-IoU combined with non-maximum suppression (NMS) can accurately frame targets in GPR image and reduce the misidentified boxes as well. Compared with the single shot multi-box detector (SSD), YOLO v2, and Faster-RCNN, the V-IoU YOLO v3 shows its superior performance even when implemented by CPU. It can meet the real-time output requirements by an average 12 fps detected speed. In summary, this paper proposes a simple and high-precision real-time pattern recognition method for GPR imagery, and promoted the application of artificial intelligence or deep learning in the field of the geophysical science.

In high-resolution Synthetic Aperture Radar (SAR) ship detection, the number of SAR samples seriously affects the performance of the algorithms based on deep learning. In this paper, aiming at the application requirements of high-resolution ship detection in small samples, a high-resolution SAR ship detection method combining an improved sample generation network, Multiscale Wasserstein Auxiliary Classifier Generative Adversarial Networks (MW-ACGAN) and the Yolo v3 network is proposed. Firstly, the multi-scale Wasserstein distance and gradient penalty loss are used to improve the original Auxiliary Classifier Generative Adversarial Networks (ACGAN), so that the improved network can stably generate high-resolution SAR ship images. Secondly, the multi-scale loss term is added to the network, so the multi-scale image output layers are added, and multi-scale SAR ship images can be generated. Then, the original ship data set and the generated data are combined into a composite data set to train the Yolo v3 target detection network, so as to solve the problem of low detection accuracy under small sample data set. The experimental results of Gaofen-3 (GF-3) 3 m SAR data show that the MW-ACGAN network can generate multi-scale and multi-class ship slices, and the confidence level of ResNet18 is higher than that of ACGAN network, with an average score of 0.91. The detection results of Yolo v3 network model show that the detection accuracy trained by the composite data set is as high as 94%, which is far better than that trained only by the original SAR data set. These results show that our method can make the best use of the original data set, improve the accuracy of ship detection.

In the area of traffic sign detection (TSD) methods, deep learning has been implemented and achieves outstanding performance. The detection of a traffic sign, as it has a dual function in monitoring and directing the driver, is a big concern for driver support systems. A core feature of autonomous vehicle systems is the identification of the traffic sign. This article focuses on the prohibitive sign. The objective is to detect in real-time and reduce processing time considerably. In this study, we implement the spatial pyramid pooling (SPP) principle to boost Yolo V3’s backbone network for the extraction of functionality. Our work uses SPP for more comprehensive learning of multiscale object features. Then, perform a comparative investigation of Yolo V3 and Yolo V3 SPP across various scales to recognize the prohibitory sign. Comparisons with Yolo V3 SPP models reveal that their mean average precision (mAP) is higher than Yolo V3. Furthermore, the test accuracy findings indicate that the Yolo V3 SPP model performs better than Yolo V3 for different sizes.

Agricultural greenhouses (AGs) are an important facility for the development of modern agriculture. Accurately and effectively detecting AGs is a necessity for the strategic planning of modern agriculture. With the advent of deep learning algorithms, various convolutional neural network (CNN)-based models have been proposed for object detection with high spatial resolution images. In this paper, we conducted a comparative assessment of the three well-established CNN-based models, which are Faster R-CNN, You Look Only Once-v3 (YOLO v3), and Single Shot Multi-Box Detector (SSD) for detecting AGs. The transfer learning and fine-tuning approaches were implemented to train models. Accuracy and efficiency evaluation results show that YOLO v3 achieved the best performance according to the average precision (mAP), frames per second (FPS) metrics and visual inspection. The SSD demonstrated an advantage in detection speed with an FPS twice higher than Faster R-CNN, although their mAP is close on the test set. The trained models were also applied to two independent test sets, which proved that these models have a certain transability and the higher resolution images are significant for accuracy improvement. Our study suggests YOLO v3 with superiorities in both accuracy and computational efficiency can be applied to detect AGs using high-resolution satellite images operationally.

Target detection is one of the most important research directions in computer vision. Recently, a variety of target detection algorithms have been proposed. Since the targets have varying sizes in a scene, it is essential to be able to detect the targets at different scales. To improve the detection performance of targets with different sizes, a multi-scale target detection algorithm was proposed involving improved YOLO (You Only Look Once) V3. The main contributions of our work include: (1) a mathematical derivation method based on Intersection over Union (IOU) was proposed to select the number and the aspect ratio dimensions of the candidate anchor boxes for each scale of the improved YOLO V3; (2) To further improve the detection performance of the network, the detection scales of YOLO V3 have been extended from 3 to 4 and the feature fusion target detection layer downsampled by 4× is established to detect the small targets; (3) To avoid gradient fading and enhance the reuse of the features, the six convolutional layers in front of the output detection layer are transformed into two residual units. The experimental results upon PASCAL VOC dataset and KITTI dataset show that the proposed method has obtained better performance than other state-of-the-art target detection algorithms.

To improve the accuracy of lane detection in complex scenarios, an adaptive lane feature learning algorithm which can automatically learn the features of a lane in various scenarios is proposed. First, a two-stage learning network based on the YOLO v3 (You Only Look Once, v3) is constructed. The structural parameters of the YOLO v3 algorithm are modified to make it more suitable for lane detection. To improve the training efficiency, a method for automatic generation of the lane label images in a simple scenario, which provides label data for the training of the first-stage network, is proposed. Then, an adaptive edge detection algorithm based on the Canny operator is used to relocate the lane detected by the first-stage model. Furthermore, the unrecognized lanes are shielded to avoid interference in subsequent model training. Then, the images processed by the above method are used as label data for the training of the second-stage model. The experiment was carried out on the KITTI and Caltech datasets, and the results showed that the accuracy and speed of the second-stage model reached a high level.