A Real-Time Small Target Vehicle Detection Algorithm with an Improved YOLOv5m Network Model

To address the challenges of high complexity,poor real-time performance,and low detection rates for small target vehicles in existing vehicle object detection algorithms,this paper proposes a real-time lightweight architecture based on You Only Look Once(YOLO)v5m.Firstly,a lightweight upsampling operator called Content-Aware Reassembly of Features(CARAFE)is introduced in the feature fusion layer of the network to maximize the extraction of deep-level features for small target vehicles,reducing the missed detection rate and false detection rate.Secondly,a new prediction layer for tiny targets is added,and the feature fusion network is redesigned to enhance the detection capability for small targets.Finally,this paper applies L1 regularization to train the improved network,followed by pruning and fine-tuning operations to remove redundant channels,reducing computational and parameter complexity and enhancing the detection efficiency of the network.Training is conducted on the VisDrone2019-DET dataset.The experimental results show that the proposed algorithmreduces parameters and computation by 63.8% and 65.8%,respectively.The average detection accuracy improves by 5.15%,and the detection speed reaches 47 images per second,satisfying real-time requirements.Compared with existing approaches,including YOLOv5m and classical vehicle detection algorithms,our method achieves higher accuracy and faster speed for real-time detection of small target vehicles in edge computing.

Context-Aware Feature Extraction Network for High-Precision UAV-Based Vehicle Detection in Urban Environments

The integration of Unmanned Aerial Vehicles(UAVs)into Intelligent Transportation Systems(ITS)holds trans-formative potential for real-time traffic monitoring,a critical component of emerging smart city infrastructure.UAVs offer unique advantages over stationary traffic cameras,including greater flexibility in monitoring large and dynamic urban areas.However,detecting small,densely packed vehicles in UAV imagery remains a significant challenge due to occlusion,variations in lighting,and the complexity of urban landscapes.Conventional models often struggle with these issues,leading to inaccurate detections and reduced performance in practical applications.To address these challenges,this paper introduces CFEMNet,an advanced deep learning model specifically designed for high-precision vehicle detection in complex urban environments.CFEMNet is built on the High-Resolution Network(HRNet)architecture and integrates a Context-aware Feature Extraction Module(CFEM),which combines multi-scale feature learning with a novel Self-Attention and Convolution layer setup within a Multi-scale Feature Block(MFB).This combination allows CFEMNet to accurately capture fine-grained details across varying scales,crucial for detecting small or partially occluded vehicles.Furthermore,the model incorporates an Equivalent Feed-Forward Network(EFFN)Block to ensure robust extraction of both spatial and semantic features,enhancing its ability to distinguish vehicles from similar objects.To optimize computational efficiency,CFEMNet employs a local window adaptation of Multi-head Self-Attention(MSA),which reduces memory overhead without sacrificing detection accuracy.Extensive experimental evaluations on the UAVDT and VisDrone-DET2018 datasets confirm CFEMNet’s superior performance in vehicle detection compared to existing models.This new architecture establishes CFEMNet as a benchmark for UAV-enabled traffic management,offering enhanced precision,reduced computational demands,and scalability for deployment in smart city applications.The advancements presented in CFEMNet contribute significantly to the evolution of smart city technologies,providing a foundation for intelligent and responsive traffic management systems that can adapt to the dynamic demands of urban environments.

Deep Transfer Learning Techniques in Intrusion Detection System-Internet of Vehicles: A State-of-the-Art Review

The high performance of IoT technology in transportation networks has led to the increasing adoption of Internet of Vehicles(IoV)technology.The functional advantages of IoV include online communication services,accident prevention,cost reduction,and enhanced traffic regularity.Despite these benefits,IoV technology is susceptible to cyber-attacks,which can exploit vulnerabilities in the vehicle network,leading to perturbations,disturbances,non-recognition of traffic signs,accidents,and vehicle immobilization.This paper reviews the state-of-the-art achievements and developments in applying Deep Transfer Learning(DTL)models for Intrusion Detection Systems in the Internet of Vehicles(IDS-IoV)based on anomaly detection.IDS-IoV leverages anomaly detection through machine learning and DTL techniques to mitigate the risks posed by cyber-attacks.These systems can autonomously create specific models based on network data to differentiate between regular traffic and cyber-attacks.Among these techniques,transfer learning models are particularly promising due to their efficacy with tagged data,reduced training time,lower memory usage,and decreased computational complexity.We evaluate DTL models against criteria including the ability to transfer knowledge,detection rate,accurate analysis of complex data,and stability.This review highlights the significant progress made in the field,showcasing how DTL models enhance the performance and reliability of IDS-IoV systems.By examining recent advancements,we provide insights into how DTL can effectively address cyber-attack challenges in IoV environments,ensuring safer and more efficient transportation networks.

A New Vehicle Detection Framework Based on Feature-Guided in the Road Scene

Vehicle detection plays a crucial role in the field of autonomous driving technology.However,directly applying deep learning-based object detection algorithms to complex road scene images often leads to subpar performance and slow inference speeds in vehicle detection.Achieving a balance between accuracy and detection speed is crucial for real-time object detection in real-world road scenes.This paper proposes a high-precision and fast vehicle detector called the feature-guided bidirectional pyramid network(FBPN).Firstly,to tackle challenges like vehicle occlusion and significant background interference,the efficient feature filtering module(EFFM)is introduced into the deep network,which amplifies the disparities between the features of the vehicle and the background.Secondly,the proposed global attention localization module(GALM)in the model neck effectively perceives the detailed position information of the target,improving both the accuracy and inference speed of themodel.Finally,the detection accuracy of small-scale vehicles is further enhanced through the utilization of a four-layer feature pyramid structure.Experimental results show that FBPN achieves an average precision of 60.8% and 97.8% on the BDD100K and KITTI datasets,respectively,with inference speeds reaching 344.83 frames/s and 357.14 frames/s.FBPN demonstrates its effectiveness and superiority by striking a balance between detection accuracy and inference speed,outperforming several state-of-the-art methods.

A Fault Detection Method for Electric Vehicle Battery System Based on Bayesian Optimization SVDD Considering a Few Faulty Samples

Accurate and reliable fault detection is essential for the safe operation of electric vehicles.Support vector data description(SVDD)has been widely used in the field of fault detection.However,constructing the hypersphere boundary only describes the distribution of unlabeled samples,while the distribution of faulty samples cannot be effectively described and easilymisses detecting faulty data due to the imbalance of sample distribution.Meanwhile,selecting parameters is critical to the detection performance,and empirical parameterization is generally timeconsuming and laborious and may not result in finding the optimal parameters.Therefore,this paper proposes a semi-supervised data-driven method based on which the SVDD algorithm is improved and achieves excellent fault detection performance.By incorporating faulty samples into the underlying SVDD model,training deals better with the problem of missing detection of faulty samples caused by the imbalance in the distribution of abnormal samples,and the hypersphere boundary ismodified to classify the samplesmore accurately.The Bayesian Optimization NSVDD(BO-NSVDD)model was constructed to quickly and accurately optimize hyperparameter combinations.In the experiments,electric vehicle operation data with four common fault types are used to evaluate the performance with other five models,and the results show that the BO-NSVDD model presents superior detection performance for each type of fault data,especially in the imperceptible early and minor faults,which has seen very obvious advantages.Finally,the strong robustness of the proposed method is verified by adding different intensities of noise in the dataset.

Improved YOLOv8s-Based Night Vehicle Detection

With the gradual development of automatic driving technology,people’s attention is no longer limited to daily automatic driving target detection.In response to the problem that it is difficult to achieve fast and accurate detection of visual targets in complex scenes of automatic driving at night,a detection algorithm based on improved YOLOv8s was proposed.Firsly,By adding Triplet Attention module into the lower sampling layer of the original model,the model can effectively retain and enhance feature information related to target detection on the lower-resolution feature map.This enhancement improved the robustness of the target detection network and reduced instances of missed detections.Secondly,the Soft-NMS algorithm was introduced to address the challenges of dealing with dense targets,overlapping objects,and complex scenes.This algorithm effectively reduced false and missed positives,thereby improved overall detection performance when faced with highly overlapping detection results.Finally,the experimental results on the MPDIoU loss function dataset showed that compared with the original model,the improved method,in which mAP and accuracy are increased by 2.9%and 2.8%respectively,can achieve better detection accuracy and speed in night vehicle detection.It can effectively improve the problem of target detection in night scenes.

Efficient and Cost-Effective Vehicle Detection in Foggy Weather for Edge/Fog-Enabled Traffic Surveillance and Collision Avoidance Systems

Vision-based vehicle detection in adverse weather conditions such as fog,haze,and mist is a challenging research area in the fields of autonomous vehicles,collision avoidance,and Internet of Things(IoT)-enabled edge/fog computing traffic surveillance and monitoring systems.Efficient and cost-effective vehicle detection at high accuracy and speed in foggy weather is essential to avoiding road traffic collisions in real-time.To evaluate vision-based vehicle detection performance in foggy weather conditions,state-of-the-art Vehicle Detection in Adverse Weather Nature(DAWN)and Foggy Driving(FD)datasets are self-annotated using the YOLO LABEL tool and customized to four vehicle detection classes:cars,buses,motorcycles,and trucks.The state-of-the-art single-stage deep learning algorithms YOLO-V5,and YOLO-V8 are considered for the task of vehicle detection.Furthermore,YOLO-V5s is enhanced by introducing attention modules Convolutional Block Attention Module(CBAM),Normalized-based Attention Module(NAM),and Simple Attention Module(SimAM)after the SPPF module as well as YOLO-V5l with BiFPN.Their vehicle detection accuracy parameters and running speed is validated on cloud(Google Colab)and edge(local)systems.The mAP50 score of YOLO-V5n is 72.60%,YOLOV5s is 75.20%,YOLO-V5m is 73.40%,and YOLO-V5l is 77.30%;and YOLO-V8n is 60.20%,YOLO-V8s is 73.50%,YOLO-V8m is 73.80%,and YOLO-V8l is 72.60%on DAWN dataset.The mAP50 score of YOLO-V5n is 43.90%,YOLO-V5s is 40.10%,YOLO-V5m is 49.70%,and YOLO-V5l is 57.30%;and YOLO-V8n is 41.60%,YOLO-V8s is 46.90%,YOLO-V8m is 42.90%,and YOLO-V8l is 44.80%on FD dataset.The vehicle detection speed of YOLOV5n is 59 Frame Per Seconds(FPS),YOLO-V5s is 47 FPS,YOLO-V5m is 38 FPS,and YOLO-V5l is 30 FPS;and YOLO-V8n is 185 FPS,YOLO-V8s is 109 FPS,YOLO-V8m is 72 FPS,and YOLO-V8l is 63 FPS on DAWN dataset.The vehicle detection speed of YOLO-V5n is 26 FPS,YOLO-V5s is 24 FPS,YOLO-V5m is 22 FPS,and YOLO-V5l is 17 FPS;and YOLO-V8n is 313 FPS,YOLO-V8s is 182 FPS,YOLO-V8m is 99 FPS,and YOLO-V8l is 60 FPS on FD dataset.YOLO-V5s,YOLO-V5s variants and YOLO-V5l_BiFPN,and YOLO-V8 algorithms are efficient and cost-effective solution for real-time vision-based vehicle detection in foggy weather.

Vision-Based On-Road Nighttime Vehicle Detection and Tracking Using Taillight and Headlight Features

An important and challenging aspect of developing an intelligent transportation system is the identification of nighttime vehicles. Most accidents occur at night owing to the absence of night lighting conditions. Vehicle detection has become a vital subject for research to ensure safety and avoid accidents. New vision-based on-road nighttime vehicle detection and tracking system are suggested in this survey paper using taillight and headlight features. Using computer vision and some image processing techniques, the proposed system can identify vehicles based on taillight and headlight features. For vehicle tracking, a centroid tracking algorithm has been used. Euclidean Distance method has been used for measuring the distances between two neighboring objects and tracks the nearest neighbor. In the proposed system two flexible fixed Region of Interest (ROI) have been used, one is the Headlight ROI, and another is the Taillight ROI that could adapt to different resolutions of the images and videos. The achievement of this research work is that the proposed two ROIs can work simultaneously in a frame to identify oncoming and preceding vehicles at night. The segmentation techniques and double thresholding method have been used to extract the red and white components from the scene to identify the vehicle headlights and taillights. To evaluate the capability of the proposed process, two types of datasets have been used. Experimental findings indicate that the performance of the proposed technique is reliable and effective in distinct nighttime environments for detection and tracking of vehicles. The proposed method has been able to detect and track double lights as well as single light such as motorcycle light and achieved average accuracy and average processing time of vehicle detection about 97.22% and 0.01 s per frame respectively.

Design of a road vehicle detection system based on monocular vision

In order to decrease vehicle crashes, a new rear view vehicle detection system based on monocular vision is designed. First, a small and flexible hardware platform based on a DM642 digtal signal processor （DSP） micro-controller is built. Then, a two-step vehicle detection algorithm is proposed. In the first step, a fast vehicle edge and symmetry fusion algorithm is used and a low threshold is set so that all the possible vehicles have a nearly 100% detection rate （TP） and the non-vehicles have a high false detection rate （FP）, i. e., all the possible vehicles can be obtained. In the second step, a classifier using a probabilistic neural network （PNN） which is based on multiple scales and an orientation Gabor feature is trained to classify the possible vehicles and eliminate the false detected vehicles from the candidate vehicles generated in the first step. Experimental results demonstrate that the proposed system maintains a high detection rate and a low false detection rate under different road, weather and lighting conditions.

Cycle life prediction and match detection in retired electric vehicle batteries

The lifespan models of commercial 18650-type lithium ion batteries （nominal capacity of 1150 mA-h） were presented. The lifespan was extrapolated based on this model. The results indicate that the relationship of capacity retention and cycle number can be expressed by Gaussian function. The selecting function and optimal precision were verified through actual match detection and a range of alternating current impedance testing. The cycle life model with high precision （〉99%） is beneficial to shortening the orediction time and cutting the prediction cost.

Traffic light detection and recognition in intersections based on intelligent vehicle

To ensure revulsive driving of intelligent vehicles at intersections, a method is presented to detect and recognize the traffic lights. First, the stabling siding at intersections is detected by applying Hough transformation. Then, the colors of traffic lights are detected with color space transformation. Finally, self-associative memory is used to recognize the countdown characters of the traffic lights. Test results at 20 real intersections show that the ratio of correct stabling siding recognition reaches up to 90%;and the ratios of recognition of traffic lights and divided characters are 85% and 97%, respectively. The research proves that the method is efficient for the detection of stabling siding and is robust enough to recognize the characters from images with noise and broken edges.

Vehicle detection method for expressway by MPEG compressed domain

A method which extracts traffic information from an MPEG-2 compressed video is proposed. According to the features of vehicle motion, the motion vector of a macro-block is used to detect moving vehicles in daytime, and a filter algorithm for removing noises of motion vectors is given. As the brightness of the headlights is higher than that of the background in night images, discrete cosine transform （DCT）coefficient of image block is used to detect headlights of vehicles at night, and an algorithm for calculating the DCT coefficients of P-frames is introduced. In order to prevent moving objects outside the expressway and video shot changes from disturbing the detection, a driveway location method and a video-shot-change detection algorithm are suggested. The detection rate is 97.4% in daytime and 95.4% in nighttime by this method. The results prove that this vehicle detection method is effective.

Semantic Segmentation and YOLO Detector over Aerial Vehicle Images

Intelligent vehicle tracking and detection are crucial tasks in the realm of highway management.However,vehicles come in a range of sizes,which is challenging to detect,affecting the traffic monitoring system’s overall accuracy.Deep learning is considered to be an efficient method for object detection in vision-based systems.In this paper,we proposed a vision-based vehicle detection and tracking system based on a You Look Only Once version 5(YOLOv5)detector combined with a segmentation technique.The model consists of six steps.In the first step,all the extracted traffic sequence images are subjected to pre-processing to remove noise and enhance the contrast level of the images.These pre-processed images are segmented by labelling each pixel to extract the uniform regions to aid the detection phase.A single-stage detector YOLOv5 is used to detect and locate vehicles in images.Each detection was exposed to Speeded Up Robust Feature(SURF)feature extraction to track multiple vehicles.Based on this,a unique number is assigned to each vehicle to easily locate them in the succeeding image frames by extracting them using the feature-matching technique.Further,we implemented a Kalman filter to track multiple vehicles.In the end,the vehicle path is estimated by using the centroid points of the rectangular bounding box predicted by the tracking algorithm.The experimental results and comparison reveal that our proposed vehicle detection and tracking system outperformed other state-of-the-art systems.The proposed implemented system provided 94.1%detection precision for Roundabout and 96.1%detection precision for Vehicle Aerial Imaging from Drone(VAID)datasets,respectively.

Vehicle detection based on information fusion of vehicle symmetrical contour and license plate position

An efficient vehicle detection approach is proposed for traffic surveillance images, which is based on information fusion of vehicle symmetrical contour and license plate position. The vertical symmetry axis of the vehicle contour in an image is. first detected, and then the vertical and the horizontal symmetry axes of the license plate are detected using the symmetry axis of the vehicle contour as a reference. The vehicle location in an image is determined using license plate symmetry axes and the vertical and the horizontal projection maps of the vehicle edge image. A dataset consisting of 450 images （15 classes of vehicles） is used to test the proposed method. The experimental results indicate that compared with the vehicle contour-based, the license plate location-based, the vehicle texture-based and the Gabor feature-based methods, the proposed method is the best with a detection accuracy of 90.7% and an elapsed time of 125 ms.

A Vehicle Detection Method for Aerial Image Based on YOLO

With the application of UAVs in intelligent transportation systems, vehicle detection for aerial images has become a key engineering technology and has academic research significance. In this paper, a vehicle detection method for aerial image based on YOLO deep learning algorithm is presented. The method integrates an aerial image dataset suitable for YOLO training by pro-cessing three public aerial image datasets. Experiments show that the training model has a good performance on unknown aerial images, especially for small objects, rotating objects, as well as compact and dense objects, while meeting the real-time requirements.

Video Based Vehicle Detection and its Application in Intelligent Transportation Systems

Video based vehicle detection technology is an integral part of Intelligent Transportation System (ITS), due to its non-intrusiveness and comprehensive vehicle behavior data collection capabilities. This paper proposes an efficient video based vehicle detection system based on Harris-Stephen corner detector algorithm. The algorithm was used to develop a stand alone vehicle detection and tracking system that determines vehicle counts and speeds at arterial roadways and freeways. The proposed video based vehicle detection system was developed to eliminate the need of complex calibration, robustness to contrasts variations, and better performance with low resolutions videos. The algorithm performance for accuracy in vehicle counts and speed was evaluated. The performance of the proposed system is equivalent or better compared to a commercial vehicle detection system. Using the developed vehicle detection and tracking system an advance warning intelligent transportation system was designed and implemented to alert commuters in advance of speed reductions and congestions at work zones and special events. The effectiveness of the advance warning system was evaluated and the impact discussed.

Patch-based vehicle logo detection with patch intensity and weight matrix

A patch-based method for detecting vehicle logos using prior knowledge is proposed.By representing the coarse region of the logo with the weight matrix of patch intensity and position,the proposed method is robust to bad and complex environmental conditions.The bounding-box of the logo is extracted by a thershloding approach.Experimental results show that 93.58% location accuracy is achieved with 1100 images under various environmental conditions,indicating that the proposed method is effective and suitable for the location of vehicle logo in practical applications.

Multiobjective fault detection and isolation for flexible air-breathing hypersonic vehicle

An application of the multiobjective fault detection and isolation（FDI） approach to an air-breathing hypersonic vehicle（HSV） longitudinal dynamics subject to disturbances is presented.Maintaining sustainable and safe flight of HSV is a challenging task due to its strong coupling effects,variable operating conditions and possible failures of system components.A common type of system faults for aircraft including HSV is the loss of effectiveness of its actuators and sensors.To detect and isolate multiple actuator/sensor failures,a faulty linear parameter-varying（LPV） model of HSV is derived by converting actuator/system component faults into equivalent sensor faults.Then a bank of LPV FDI observers is designed to track individual fault with minimum error and suppress the effects of disturbances and other fault signals.The simulation results based on the nonlinear flexible HSV model and a nominal LPV controller demonstrate the effectiveness of the fault estimation technique for HSV.

Enhancement Dataset for Low Altitude Unmanned Aerial Vehicle Detection

In recent years,the number of incidents involved with unmanned aerial vehicles(UAVs)has increased conspicuously,resulting in an increasingly urgent demand for developing anti-UAV systems. The vast requirements of high detection accuracy with respect to low altitude UAVs are put forward. In addition,the methods of UAV detection based on deep learning are of great potential in low altitude UAV detection. However,such methods need high-quality datasets to cope with the problem of high false alarm rate(FAR)and high missing alarm rate(MAR)in low altitude UAV detection,special high-quality low altitude UAV detection dataset is still lacking. A handful of known datasets for UAV detection have been rejected by their proposers for authorization and are of poor quality. In this paper,a comprehensive enhanced dataset containing UAVs and jamming objects is proposed. A large number of high-definition UAV images are obtained through real world shooting, web crawler, and data enhancement.Moreover,to cope with the challenge of low altitude UAV detection in complex backgrounds and long distance,as well as the puzzle caused by jamming objects,the noise with jamming characteristics is added to the dataset. Finally,the dataset is trained,validated,and tested by four mainstream deep learning models. The results indicate that by using data enhancement,adding noise contained jamming objects and images of UAV with complex backgrounds and long distance,the accuracy of UAV detection can be significantly improved. This work will promote the development of anti-UAV systems deeply,and more convincing evaluation criteria are provided for models optimization for UAV detection.

Vehicle Detection Based on Visual Saliency and Deep Sparse Convolution Hierarchical Model

Traditional vehicle detection algorithms use traverse search based vehicle candidate generation and hand crafted based classifier training for vehicle candidate verification.These types of methods generally have high processing times and low vehicle detection performance.To address this issue,a visual saliency and deep sparse convolution hierarchical model based vehicle detection algorithm is proposed.A visual saliency calculation is firstly used to generate a small vehicle candidate area.The vehicle candidate sub images are then loaded into a sparse deep convolution hierarchical model with an SVM-based classifier to perform the final detection.The experimental results demonstrate that the proposed method is with 94.81% correct rate and 0.78% false detection rate on the existing datasets and the real road pictures captured by our group,which outperforms the existing state-of-the-art algorithms.More importantly,high discriminative multi-scale features are generated by deep sparse convolution network which has broad application prospects in target recognition in the field of intelligent vehicle.