Explore the vast range of titles available.

To improve the detection accuracy of the drone-based oriented vehicle object detection network and establish high-accuracy vehicle trajectory datasets, we present a freeway on-ramp vehicle (FRVehicle) detection dataset with oriented bounding box annotations for vehicles in freeway on-ramp scenes from drone videos. Based on this dataset, we analyzed the dimension and angle distribution patterns of road vehicle object oriented bounding boxes and designed an Asymmetric Selective Kernel Network. This algorithm dynamically adjusts the receptive field of the backbone network’s feature extraction to accommodate the detection requirements for vehicles of different sizes. Additionally, we estimate vehicle heights with high-precision object detection results, further enhancing the accuracy of the vehicle trajectory. Comparative experimental results demonstrate that the proposed Asymmetric Selective Kernel Network achieved varying degrees of improvement in detection accuracy on both the FRVehicle dataset and DroneVehicle dataset compared to the symmetric selective kernel network in most scenarios, validating the effectiveness of the method.

Recently, deep learning techniques have had a practical role in vehicle detection. While much effort has been spent on applying deep learning to vehicle detection, the effective use of training data has not been thoroughly studied, although it has great potential for improving training results, especially in cases where the training data are sparse. In this paper, we proposed using hard example mining (HEM) in the training process of a convolutional neural network (CNN) for vehicle detection in aerial images. We applied HEM to stochastic gradient descent (SGD) to choose the most informative training data by calculating the loss values in each batch and employing the examples with the largest losses. We picked 100 out of both 500 and 1000 examples for training in one iteration, and we tested different ratios of positive to negative examples in the training data to evaluate how the balance of positive and negative examples would affect the performance. In any case, our method always outperformed the plain SGD. The experimental results for images from New York showed improved performance over a CNN trained in plain SGD where the F1 score of our method was 0.02 higher.

To constructively ameliorate and enhance traffic safety measures in Saudi Arabia, a prolific number of AI (Artificial Intelligence) traffic surveillance technologies have emerged, including Saher, throughout the past years. However, rapidly detecting a vehicle incident can play a cardinal role in ameliorating the response speed of incident management, which in turn minimizes road injuries that have been induced by the accident’s occurrence. To attain a permeating effect in increasing the entailed demand for road traffic security and safety, this paper presents a real-time traffic incident detection and alert system that is based on a computer vision approach. The proposed framework consists of three models, each of which is integrated within a prototype interface to fully visualize the system’s overall architecture. To begin, the vehicle detection and tracking model utilized the YOLOv5 object detector with the DeepSORT tracker to detect and track the vehicles’ movements by allocating a unique identification number (ID) to each vehicle. This model attained a mean average precision (mAP) of 99.2%. Second, a traffic accident and severity classification model attained a mAP of 83.3% while utilizing the YOLOv5 algorithm to accurately detect and classify an accident’s severity level, sending an immediate alert message to the nearest hospital if a severe accident has taken place. Finally, the ResNet152 algorithm was utilized to detect the ignition of a fire following the accident’s occurrence; this model achieved an accuracy rate of 98.9%, with an automated alert being sent to the fire station if this perilous event occurred. This study employed an innovative parallel computing technique for reducing the overall complexity and inference time of the AI-based system to run the proposed system in a concurrent and parallel manner.

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

In bridge maintenance, particularly with regard to fatigue damage in steel bridges, it is important to determine the displacement response of the entire bridge under a live load as well as that of each member. Knowing the displacement response enables the identification of dynamic deformations that can cause stresses and ultimately lead to damage and thus also allows the undertaking of appropriate countermeasures. In theory, the displacement response can be calculated from the double integration of the measured acceleration. However, data measured by an accelerometer include measurement errors caused by the limitations of the analog-to-digital conversion process and sensor noise. These errors distort the double integration results. Furthermore, as bridges in service are constantly vibrating because of passing vehicles, estimating the boundary conditions for the numerical integration is difficult. To address these problems, this paper proposes a method for determining the displacement of a bridge in service from its acceleration based on its free vibration. To verify the effectiveness of the proposed method, field measurements were conducted using nine different accelerometers. Based on the results of these measurements, the proposed method was found to be highly accurate in comparison with the reference displacement obtained using a contact displacement gauge.

Accurate and transparent vehicle speed data are crucial for enforcing speed limits and other important applications. However, attaining the required levels of accuracy and transparency remains a challenge that needs to be addressed. The potential for further improvement is brought by technological advancements. To address this, it is necessary to understand the current developments in speed detection methods, technologies used in speed detection systems, and challenges of existing systems. This work reviews vehicle speed detection methods and provides a guideline for selecting an appropriate method. This work also reviews technologies for implementing smart systems and proposes an integrated approach for enhancing intelligence, interconnection, and transparency. Not only this, but this work also evaluates existing vehicle speed detection systems and highlights the need for further research. Furthermore, this work proposes a conceptual framework that integrates the Internet of Things, Artificial Intelligence, cloud computing, and blockchain technologies to enhance vehicle speed detection systems, particularly for developing countries. The Internet of Things facilitates data collection and transmission, ensuring system interconnectivity, while Artificial Intelligence is used for data pre-processing in cloud computing to improve system intelligence and scalability. Meanwhile, blockchain guarantees data security and transparency. A proof-of-concept demonstrator was implemented to validate the proposed conceptual framework. Evaluation results demonstrate an auspicious performance regarding end-to-end data delivery and transmission latency. This work provides both theoretical and practical insights regarding smart and transparent vehicle speed detection systems.

We have already proposed a method for detecting vehicle positions and their movements (henceforth referred to as “our previous method”) using thermal images taken with an infrared thermal camera. Our experiments have shown that our previous method detects vehicles robustly under four different environmental conditions which involve poor visibility conditions in snow and thick fog. Our previous method uses the windshield and its surroundings as the target of the Viola-Jones detector. Some experiments in winter show that the vehicle detection accuracy decreases because the temperatures of many windshields approximate those of the exterior of the windshields. In this paper, we propose a new vehicle detection method (henceforth referred to as “our new method”). Our new method detects vehicles based on tires’ thermal energy reflection. We have done experiments using three series of thermal images for which the vehicle detection accuracies of our previous method are low. Our new method detects 1,417 vehicles (92.8%) out of 1,527 vehicles, and the number of false detection is 52 in total. Therefore, by combining our two methods, high vehicle detection accuracies are maintained under various environmental conditions. Finally, we apply the traffic information obtained by our two methods to traffic flow automatic monitoring, and show the effectiveness of our proposal.

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

In this paper, we propose a novel hierarchical scheme for detection and tracking of vehicles using a vehicle-mounted camera in nighttime under urban environment, where a vehicle can be represented by a pair of taillights and various types of lights are commonplace. The proposed scheme, therefore, mainly focuses on devising robust detection and pairing of taillights in spite of their inherent diversity and continuous transformation in appearance. Thus the appearance symmetry, which many conventional methods rely on, for paring is not guaranteed to be available all the times. Each of the three layers in the scheme is devised to identify a vehicle from individual lights and clutters detected in a hierarchical manner. Robust detection of a pair of taillights, which can be regarded as a vehicle, is sought by successive groupings of the components in a layer and checking not only the intra-layer but the inter-layer relations between them. A structural Kalman filter is employed to maintain the temporal consistency in the motion of the components and their relations as well. Exploiting such relational information increases accuracy in tracking of individual components by reducing effects from fluctuation in positions and shapes, and eventually compensating possible failures in detection of them. As a result, the proposed scheme achieves enhancement in detection and tracking of vehicles in nighttime as proven by experiments on videos including crowded urban traffic scenes.