Vehicle detection algorithm based on light pairing and tracking at nighttime

An adaptive confidence algorithm for vehicle detection is proposed. Shortcomings of traditional vehicle detection method of deep learning with fixed confidence threshold are analyzed. To deal with false alarms and false negatives brought by these shortcomings, an adaptive confidence threshold algorithm for vehicle detection is raised. Two datasets are set up to test and compare the detection performance of the adaptive confidence algorithm with fixed confidence on MS-CNN. The experimental results show that the proposed algorithm could effectively reduce the false alarm rate and improve the detection performance of MS-CNN. It is of certain significance for the application of deep learning technology to vehicle detection.

Automatic vehicle detection and counting are considered vital in improving traffic control and management. This work presents an effective algorithm for vehicle detection and counting in complex traffic scenes by combining both convolution neural network (CNN) and the optical flow feature tracking-based methods. In this algorithm, both the detection and tracking procedures have been linked together to get robust feature points that are updated regularly every fixed number of frames. The proposed algorithm detects moving vehicles based on a background subtraction method using CNN. Then, the vehicle’s robust features are refined and clustered by motion feature points analysis using a combined technique between KLT tracker and K-means clustering. Finally, an efficient strategy is presented using the detected and tracked points information to assign each vehicle label with its corresponding one in the vehicle’s trajectories and truly counted it. The proposed method is evaluated on videos representing challenging environments, and the experimental results showed an average detection and counting precision of 96.3% and 96.8%, respectively, which outperforms other existing approaches.

In complex traffic scenarios, there are many problems such as inaccurate vehicle positioning, low recognition rate, and missed detection of vehicles for instability of the traffic environment. This paper proposes an improved Faster R-CNN algorithm for accurate vehicle detection. We use feature maps of depth images to supplement vehicle details by adding a depth channel into the detection model. When training the model, we add a hard sample mining strategy. We evaluate our newly proposed approach using KITTI dataset. The experimental results show that our proposed approach has a significant improvement in recognition accuracy by 5%.

With the rapid development of intelligent transportation systems, vehicle detection and traffic flow statistics have become increasingly critical in traffic management and the construction of smart cities. However, complex weather conditions lead to challenges in vehicle detection algorithms, increasing false negatives and false positives. Additionally, the rapid growth of vehicle ownership makes traditional algorithms inadequate for meeting practical application needs. Therefore, this paper proposes a collaborative optimization-based method combining YOLOv11 for vehicle detection and traffic flow analysis under complex weather conditions. Vehicle information is accurately extracted through object detection and tracking methods, and further analyzed using Logistic Regression to assess traffic congestion. The main contributions of this study are: (1) Integration of the CBAM attention mechanism into YOLOv11, enhancing the vehicle feature extraction ability through collaborative channel and spatial attention, thereby improving interference resistance under complex weather conditions. (2) Adoption of the Shape-IoU loss function, with dynamic weight allocation to optimize the accuracy of detecting smaller vehicles and the precision of bounding box regression in images where vehicles are located at a greater distance. (3) Construction of a traffic congestion prediction model based on the detection results, integrated with Logistic Regression. The proposed method's effectiveness is validated on the public dataset UA-DETRAC. Through the synergistic effect of the CBAM attention mechanism and Shape-IoU loss function, the improved model's mAP50-95 shows a 0.3 percentage point increase over the YOLOv11 baseline, providing efficient and reliable technical support for intelligent transportation systems. This study enhances the prediction performance of traffic states under complex weather conditions by effectively calculating traffic flow parameters such as vehicle count and density, thus offering foundational data support for traffic management decision-making. The research conclusions are of practical significance for urban traffic improvement.

Automatically counting vehicles in complex traffic scenes from videos is challenging. Detection and tracking algorithms may fail due to occlusions, scene clutters, and large variations of viewpoints and vehicle types. We propose a new approach of counting vehicles through exploiting contextual regularities from scene structures. It breaks the problem into simpler problems, which count vehicles on each path separately. The model of each path and its source and sink add strong regularization on the motion and the sizes of vehicles and can thus significantly improve the accuracy of vehicle counting. Our approach is based on tracking and clustering feature points and can be summarized in threefold. First, an algorithm is proposed to automatically learn the models of scene structures. A traffic scene is segmented into local semantic regions by exploiting the temporal cooccurrence of local motions. Local semantic regions are connected into global complete paths using the proposed fast marching algorithm. Sources and sinks are estimated from the models of semantic regions. Second, an algorithm is proposed to cluster trajectories of feature points into objects and to estimate average vehicle sizes at different locations from initial clustering results. Third, trajectories of features points are often fragmented due to occlusions. By integrating the spatiotemporal features of trajectory clusters with contextual models of paths and sources and sinks, trajectory clusters are assigned into different paths and connected into complete trajectories. Experimental results on a complex traffic scene show the effectiveness of our approach.

Existing machine-learning-based vehicle detection algorithms for intelligent vehicles have an obvious disadvantage in that the detection effect decreases dramatically when the distribution of training samples and the scene target samples do not match. To address this issue, a scene-adaptive vehicle detection algorithm based on a composite deep structure is proposed in this paper. Inspired by the Bagging (Bootstrap aggregating) mechanism, multiple relatively independent source samples are first used to build multiple classifiers and then voting is used to generate target training samples with confidence scores. The automatic feature extraction ability of deep convolutional neural network is then used to perform source-target scene feature similarity calculations with a deep auto-encoder in order to design a composite deep-structure-based scene-adaptive classifier and its training method. Experiments on the KITTI data set and a data set captured by our group demonstrate that the proposed method performs better than existing machine-learning-based vehicle detection methods. In addition, compared with existing scene-adaptive object detection methods, our method improves the detection rate by an average of approximately 3%.

Vehicle detection in aerial images has attracted great attention as an approach to providing the necessary information for transportation road network planning and traffic management. However, because of the low resolution, complex scene, occlusion, shadows, and high requirement for detection efficiency, implementing vehicle detection in aerial images is challenging. Therefore, we propose an efficient and scene-adaptive algorithm for vehicle detection in aerial images using an improved YOLOv3 framework, and it is applied to not only aerial still images but also videos composed of consecutive frame images. First, rather than directly using the traditional YOLOv3 network, we construct a new structure with fewer layers to improve the detection efficiency. Then, since complex scenes in aerial images can cause the partial occlusion of vehicles, we construct a context-aware-based feature map fusion to make full use of the information in the adjacent frames and accurately detect partially occluded vehicles. The traditional YOLOv3 network adopts a horizontal bounding box, which can attain the expected detection effects only for vehicles with small length–width ratio. Moreover, vehicles that are close to each other are liable to cause lower accuracy and a higher detection error rate. Hence, we design a sloping bounding box attached to the angle of the target vehicles. This modification is conducive to predicting not only the position but also the angle. Finally, two data sets were used to perform extensive experiments and comparisons. The results show that the proposed algorithm generates the desired and excellent performance.

Aiming at the defects and shortages of traditional moving vehicles detection algorithms, by the analysis and comparison of the existing detection algorithms, we propose an algorithm that combined with frames with symmetric difference and background difference to detect moving vehicle in this paper. First, two different difference images by using frames with symmetric difference and background difference are gained respectively and two binary images can be gained by the appropriate threshold, then the contour of moving vehicles can be extracted by applying OR operation in the two binary images. Finally, the precise moving vehicles will be gained by mathematic morphological methods. In this paper we use Harris operator, Feature Points such as edges and corners are extracted, followed by block-matching to track the Feature Points in successive viedo frames. Many vehicles can be tracked at the same time automatically since the information is obtained from video sequences. DOI: http://dx.doi.org/10.11591/telkomnika.v11i6.2613

Lane vehicle detection is fundamental to vehicle driving systems and self-driving. The proposed concept is to employ the pixel difference in the intended lane line backdrop to isolate the lane and the road surface, and then, the curve fitting model is used to identify the lane in the image. A histogram on gradient, histogram graph, and binary spatial features are extracted from the vehicle and non-vehicle images. For vehicle detection, support vector machine classifier is employed to separate the vehicle and non-vehicle images using the extracted features. But many methods are constrained by light conditions and road circumstances, such as weak light, fog, rain, etc., which may result in invisible lane lines. Feature extraction is the lane images being picked using various filters. Our work focuses on a lane detection technique founded on the Sobel filter and curve fitting model for lane line tracking in different conditions. Preprocessing encompasses the mitigation of noise as well as getting the image ready for the subsequent procedure. To achieve this, HLS color space was performed which identifies the lane by adding pixel values. The main aim is to increase the accuracy and reduce the computation time compared to other existing methods.KeywordsSobel filterCurve fitting modelLane detectionVehicle detectionSliding windowSupport vector machine

Automatic objects behaviour recognition from compressed video domain

Recently, with the explosive increase of automobiles in cities, parking problems are serious and even worsen in many cities. This paper proposes a street parking system (SPS) based on wireless sensor networks. The system can monitor the state of every parking space by deploying a magnetic sensor node on the space. For accurately detecting a parking car, a vehicle detection algorithm is proposed. And an adaptive sampling mechanism is used to reduce the energy consumption. Eighty-two sensor nodes are deployed on the street parking spaces to evaluate the performance of SPS. By running the system for more than one year, we observed that the vehicle detection accuracy of the SPS is better than 98%, and the lifetime of the sensor node is more than 5 years with a pair of 2500 mAh Li batteries.

In this paper, a novel vehicle detection algorithm is proposed that utilizes the color histogram of the image. The color histogram is used to search the image for regions with shadow, block symmetry, and block non-homogeneity, thereby detecting the vehicle region. First, an integral histogram of the input image is computed to decrease the amount of required computation time for the block color histograms. Then, shadow detection is performed and the block symmetry and block non-homogeneity are checked in a cascade manner to detect the vehicle in the image. Finally, the proposed scheme is applied to both still images taken in a parking lot and an on-road video sequence to demonstrate its effectiveness.

In order to ensure the safety of driving, this paper studies the vehicle detection algorithm based on convolutional neural network which integrates color and depth images. This paper mainly discusses the subject through convolutional network multi-scale forward looking depth imaging positioning model, forward looking variable scale vehicle detection pre-positioning algorithm, and typical model identification algorithm based on transfer learning, and verifies the algorithm performance and model identification algorithm accuracy by combining with simulation test. The results show that the accuracy of the algorithm is 96.89% under different weather conditions, indicating its effectiveness in application. Compared with previous vehicle detection algorithms, the detection accuracy of this algorithm is effectively improved by 3.96%, indicating that this algorithm has innovative significance.

Vehicle detection and tracking from a UAV perspective often encounters omission and misdetection due to the small targets, complex scenes and target occlusion, which finally influences hugely on detection accuracy and target tracking stability. Additionally, the number of parameters of current model is large that makes it is hard to be deployed on mobile devices. Therefore, this paper proposes a YOLO-LMP and NGCTrack-based target detection and tracking algorithm to address these issues. Firstly, the performance of detecting small targets in occluded scenes is enhanced by adding a MODConv to the small-target detection head and increasing its size; In addition, excessive deletion of prediction boxes is prevented by utilizing LSKAttention mechanism to adaptively adjust the target sensing field at the downsampling stage and combining it with the Soft-NMS strategy. Furthermore, the C2f module is replaced by the FPW to reduce the pointless computation and memory utilization of the model. At the target tracking stage, the so-called NGCTrack in our algorithm replaces IOU with GIOU and employs a modified NSA Kalman filter to adjust the state-space aspect ratio for width prediction. Finally, the camera adjustment mechanism was introduced to improve the precision and consistency of tracking. The experimental results show that, compared to YOLOv8, the YOLO-LMP model improves map50 and map50:95 metrics by 10.3 and 12.2%, respectively and the number of parameters is decreased by 47.7%. After combined it with the improved NGCTrack, the number of IDSW reduced by 73.6% compared to the ByteTrack method, while the MOTA and IDF1 increase by 5.2 and 9.8%, respectively.

Attributable to global economic development and rapid urbanization, traffic explosion has been observed. This situation becomes very prominent as the traditional traffic control systems are incapable to efficiently monitor and control the traffic. Therefore, this paper presents automatic vehicle detection from satellite images using deep learning approaches. For this purpose, two most renowned and widely used detection algorithms (YOLOv4 and YOLOv3) have been employed to develop satellite image vehicle detector using publicly available DOTA dataset. This work confirms the supremacy of YOLOv4 over YOLOv3 by large improvements in mAP, IOU, precision, recall, F1-score with increase of 45%, 20%, 11.1%, 45.9%, and 29.5%, respectively. Therefore, these investigational results verify the strength of YOLOv4 algorithm for satellite image vehicle detection and recommend its use for the development of an intelligent traffic control system.KeywordsDeep learningObject detectionIntelligent traffic controlVehicle detectionYOLOv3YOLOv4 algorithm