Search Results (23)

Fatigue and distracted driving are among the leading causes of traffic accidents, highlighting the importance of developing efficient and non-intrusive driver monitoring systems. Traditional camera-based methods are often limited by lighting variations, occlusions, and privacy concerns. In contrast, millimeter-wave (mmWave) radar offers a non-contact, privacy-preserving, and environment-robust solution, providing a forward-looking alternative. This study introduces a novel deep learning model, RTSFN (radar-based temporal-spatial fusion network), which simultaneously analyzes the temporal motion changes and spatial posture features of the driver. RTSFN incorporates a cross-gated fusion mechanism that dynamically integrates multi-modal information, enhancing feature complementarity and stabilizing behavior recognition. Experimental results show that RTSFN effectively detects dangerous driving states with an average F1 score of 94% and recognizes specific high-risk behaviors with an average F1 score of 97% and can run in real-time on edge devices such as the NVIDIA Jetson Orin Nano, demonstrating its strong potential for deployment in intelligent transportation and in-vehicle safety systems. Full article

Understanding human perceptual strategies in high-stakes environments, such as crime scene investigations, is essential for developing cognitive models that reflect expert decision-making. This study presents an immersive experimental framework that utilizes virtual reality (VR) and eye-tracking technologies to capture and analyze visual attention during simulated forensic tasks. A360° panoramic crime scene, constructed using the Nikon KeyMission 360 camera, was integrated into a VR system with HTC Vive and Tobii Pro eye-tracking components. A total of 46 undergraduate students aged 19 to 24–23, from the National University of Singapore in Singapore and 23 from the Central Police University in Taiwan—participated in the study, generating over 2.6 million gaze samples (IRB No. 23-095-B). The collected eye-tracking data were analyzed using statistical summarization, temporal alignment techniques (Earth Mover’s Distance and Needleman-Wunsch algorithms), and machine learning models, including K-means clustering, random forest regression, and support vector machines (SVMs). Clustering achieved a classification accuracy of 78.26%, revealing distinct visual behavior patterns across participant groups. Proficiency prediction models reached optimal performance with a random forest regression ($R^2$ = 0.7034), highlighting scan-path variability and fixation regularity as key predictive features. These findings demonstrate that eye-tracking metrics—particularly sequence-alignment-based features—can effectively capture differences linked to both experiential training and cultural context. Beyond its immediate forensic relevance, the study contributes a structured methodology for encoding visual attention strategies into analyzable formats, offering valuable insights for cognitive modeling, training systems, and human-centered design in future perceptual intelligence applications. Furthermore, our work advances the development of autonomous vehicles by modeling how humans visually interpret complex and potentially hazardous environments. By examining expert and novice gaze patterns during simulated forensic investigations, we provide insights that can inform the design of autonomous systems required to make rapid, safety-critical decisions in similarly unstructured settings. The extraction of human-like visual attention strategies not only enhances scene understanding, anomaly detection, and risk assessment in autonomous driving scenarios, but also supports accelerated learning of response patterns for rare, dangerous, or otherwise exceptional conditions—enabling autonomous driving systems to better anticipate and manage unexpected real-world challenges. Full article

Accurate detection of dangerous driving behaviors is crucial for improving the safety of intelligent transportation systems. However, existing methods often struggle with limited feature extraction capabilities and insufficient attention to multiscale and contextual information. To overcome these limitations, we propose YOLO-AFR (YOLO with Adaptive Feature Refinement) for dangerous driving behavior detection. YOLO-AFR builds upon the YOLOv12 architecture and introduces three key innovations: (1) the redesign of the original A2C2f module by introducing a Feature-Refinement Feedback Network (FRFN), resulting in a new A2C2f-FRFN structure that adaptively refines multiscale features, (2) the integration of self-calibrated convolution (SC-Conv) modules in the backbone to enhance multiscale contextual modeling, and (3) the employment of a SEAM-based detection head to improve global contextual awareness and prediction accuracy. These three modules combine to form a Calibration-Refinement Loop, which progressively reduces redundancy and enhances discriminative features layer by layer. We evaluate YOLO-AFR on two public driver behavior datasets, YawDD-E and SfdDD. Experimental results show that YOLO-AFR significantly outperforms the baseline YOLOv12 model, achieving improvements of 1.3% and 1.8% in mAP@0.5, and 2.6% and 12.3% in mAP@0.5:0.95 on the YawDD-E and SfdDD datasets, respectively, demonstrating its superior performance in complex driving scenarios while maintaining high inference speed. Full article

Traffic safety experiments are often conducted in virtual environments in order to avoid dangerous situations and conduct the experiments more cost-efficiently. This means that attention must be paid to the fidelity of the traffic scenario reproduction, because the pedestrians’ judgments have to be close to reality. To understand behavior in relation to the prevailing audio rendering systems better, a listening test was conducted which focused on perceptual differences between simulation and playback methods. Six vehicle driving-by-scenes were presented using two different simulation methods and three different playback methods, and binaural recordings from the test track acquired during the recordings of the vehicle sound sources for the simulation were additionally incorporated. Each vehicle driving-by-scene was characterized by different vehicle types and different speeds. Participants rated six attributes of the perceptual dimensions: “timbral balance”, “naturalness”, “room-related”, “source localization”, “loudness” and “speed perception”. While the ratings showed a high degree of similarity among the ratings of the sound attributes in the different reproduction systems, there were minor differences in the speed and loudness estimations and the different perceptions of brightness stood out. A comparison of the loudness ratings in the scenes featuring electric and combustion-engine vehicles highlights the issue of reduced detection abilities with regard to the former. Full article

In response to the rising frequency of traffic accidents and growing concerns regarding driving safety, the identification and analysis of dangerous driving behaviors have emerged as critical components in enhancing road safety. In this paper, the research progress in the recognition methods of dangerous driving behavior based on deep learning is analyzed. Firstly, the data collection methods are categorized into four types, evaluating their respective advantages, disadvantages, and applicability. While questionnaire surveys provide limited information, they are straightforward to conduct. The vehicle operation data acquisition method, being a non-contact detection, does not interfere with the driver’s activities but is susceptible to environmental factors and individual driving habits, potentially leading to inaccuracies. The recognition method based on dangerous driving behavior can be monitored in real time, though its effectiveness is constrained by lighting conditions. The precision of physiological detection depends on the quality of the equipment. Then, the collected big data are utilized to extract the features related to dangerous driving behavior. The paper mainly classifies the deep learning models employed for dangerous driving behavior recognition into three categories: Deep Belief Network (DBN), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN). DBN exhibits high flexibility but suffers from relatively slow processing speeds. CNN demonstrates excellent performance in image recognition, yet it may lead to information loss. RNN possesses the capability to process sequential data effectively; however, training these networks is challenging. Finally, this paper concludes with a comprehensive analysis of the application of deep learning-based dangerous driving behavior recognition methods, along with an in-depth exploration of their future development trends. As computer technology continues to advance, deep learning is progressively replacing fuzzy logic and traditional machine learning approaches as the primary tool for identifying dangerous driving behaviors. Full article

Intelligent transportation systems (ITSs) present new opportunities for enhanced traffic management by leveraging advanced driving behavior sensors and real-time information exchange via vehicle-based and cloud–vehicle communication technologies. Specifically, onboard sensors can effectively detect whether human-driven vehicles are adhering to traffic management directives. However, the formulation and validation of effective strategies for vehicle implementation rely on accurate driving behavior models and reliable model-based testing; in this paper, we focus on large roundabouts as the research scenario. To address this, we proposed the Three-Stage Cellular Automata (TSCA) model based on empirical observations, dividing the vehicle journey over roundabouts into three stages: entrance, following, and exit. Furthermore, four optimization strategies were developed based on empirical observations and simulation results, using the traffic efficiency, delay time, and dangerous interaction frequency as key evaluation indicators. Numerical tests reveal that dangerous interactions and delays primarily occurred when the roundabout Road Occupancy Rate ($\rho$) ranged from 0.12 to 0.24, during which times the vehicle speed also decreased rapidly. Among the strategies, the Path Selection Based on Road Occupancy Rate Recognition Strategy (Simulation 4) demonstrated the best overall performance, increasing the traffic efficiency by 15.65% while reducing the delay time, dangerous interactions, and frequency by 6.50%, 28.32%, and 38.03%, respectively. Additionally, the Entrance Facility Optimization Strategy (Simulation 1) reduced the delay time by 6.90%. While space-based optimization strategies had a more moderate overall impact, they significantly improved the local traffic efficiency at the roundabout by approximately 25.04%. Our findings hold significant practical value, particularly with the support of onboard sensors, which can effectively detect non-compliance and provide real-time warnings to guide drivers in adhering to the prescribed traffic management strategies. Full article

Due to the flammable and explosive nature of explosives, there are significant potential hazards and risks during transportation. During the operation of explosive transport vehicles, there are often situations where the vehicles around them approach or change lanes abnormally, resulting in insufficient avoidance and collision, leading to serious consequences such as explosions and fires. Therefore, in response to the above issues, this article has developed an explosive transport vehicle driving warning system based on object detection algorithms. Consumer-level cameras are flexibly arranged around the vehicle body to monitor surrounding vehicles. Using the YOLOv4 object detection algorithm to identify and distance surrounding vehicles, using a game theory-based cellular automaton model to simulate the actual operation of vehicles, simulating the driver’s decision-making behavior when encountering other vehicles approaching or changing lanes abnormally during actual driving. The cellular automaton model was used to simulate two scenarios of explosive transport vehicles equipped with and without warning systems. The results show that when explosive transport vehicles encounter the above-mentioned dangerous situations, the warning system can timely issue warnings, remind drivers to make decisions, avoid risks, ensure the safety of vehicle operation, and verify the effectiveness of the warning system. Full article

Human behavior significantly contributes to severe road injuries, underscoring a critical road safety challenge. This study addresses the complex task of predicting dangerous driving behaviors through a comprehensive analysis of over 356,000 trips, enhancing existing knowledge in the field and promoting sustainability and road safety. The research uses advanced machine learning algorithms (e.g., Random Forest, Gradient Boosting, Extreme Gradient Boosting, Multilayer Perceptron, and K-Nearest Neighbors) to categorize driving behaviors into ‘Dangerous’ and ‘Non-Dangerous’. Feature selection techniques are applied to enhance the understanding of influential driving behaviors, while k-means clustering establishes reliable safety thresholds. Findings indicate that Gradient Boosting and Multilayer Perceptron excel, achieving recall rates of approximately 67% to 68% for both harsh acceleration and braking events. This study identifies critical thresholds for harsh events: (a) 48.82 harsh accelerations and (b) 45.40 harsh brakings per 100 km, providing new benchmarks for assessing driving risks. The application of machine learning algorithms, feature selection, and k-means clustering offers a promising approach for improving road safety and reducing socio-economic costs through sustainable practices. By adopting these techniques and the identified thresholds for harsh events, authorities and organizations can develop effective strategies to detect and mitigate dangerous driving behaviors. Full article

Fast detection of the trajectory is the key point to improve the further emergency proposal. Especially for ultra-long highway, prompt detection is labor-intensive. However, automatic detection relies on the accuracy and speed of vehicle detection, and tracking. In multi-camera surveillance system for ultra-long highways, it is often difficult to capture the same vehicle without intervals, which makes vehicle re-recognition crucial as well. In this paper, we present a framework that includes vehicle detection and tracking using improved DeepSORT, vehicle re-identification, feature extraction based on trajectory rules, and behavior recognition based on trajectory analysis. In particular, we design a network architecture based on DeepSORT with YOLOv5s to address the need for real-time vehicle detection and tracking in real-world traffic management. We further design an attribute recognition module to generate matching individuality attributes for vehicles to improve vehicle re-identification performance under multiple neighboring cameras. Besides, the use of bidirectional LSTM improves the accuracy of trajectory prediction, demonstrating its robustness to noise and fluctuations. The proposed model has a high advantage from the cumulative matching characteristic (CMC) curve shown and even improves above 15.38% compared to other state-of-the-art methods. The model developed on the local highway vehicle dataset is comprehensively evaluated, including abnormal trajectory recognition, lane change detection, and speed anomaly recognition. Experimental results demonstrate the effectiveness of the proposed method in accurately identifying various vehicle behaviors, including lane changes, stops, and even other dangerous driving behavior. Full article

Ensuring safety while driving relies heavily on normal driving behavior, making the timely detection of dangerous driving patterns crucial. In this paper, an Hourglass Attention ResNet Network (HAR-Net) is proposed to detect dangerous driving behavior. Uniquely, we separately input optical flow data, RGB data, and RGBD data into the network for spatial–temporal fusion. In the spatial fusion part, we combine ResNet-50 and the hourglass network as the backbone of CenterNet. To improve the accuracy, we add the attention mechanism to the network and integrate center loss into the original Softmax loss. Additionally, a dangerous driving behavior dataset is constructed to evaluate the proposed model. Through ablation and comparative studies, we demonstrate the efficacy of each HAR-Net component. Notably, HAR-Net achieves a mean average precision of 98.84% on our dataset, surpassing other state-of-the-art networks for detecting distracted driving behaviors. Full article

According to the survey statistics, most traffic accidents are caused by the driver’s behavior and status irregularities. Because there is no multi-level dangerous state grading system at home and abroad, this paper proposes a complex state grading system for real-time detection and dynamic tracking of the driver’s state. The system uses OpenMV as the acquisition camera combined with the cradle head tracking system to collect the driver’s current driving image in real-time dynamically, combines the YOLOX algorithm with the OpenPose algorithm to judge the driver’s dangerous driving behavior by detecting unsafe objects in the cab and the driver’s posture, and combines the improved Retinaface face detection algorithm with the Dlib feature-point algorithm to discriminate the fatigue driving state of the driver. The experimental results show that the accuracy of the three driver danger levels (R1, R2, and R3) obtained by the proposed system reaches 95.8%, 94.5%, and 96.3%, respectively. The experimental results of this system have a specific practical significance in driver-distracted driving warnings. Full article

Vehicle ad hoc networks (VANETs) are vital towards the success and comfort of self-driving as well as semi-automobile vehicles. Such vehicles rely heavily on data management and the exchange of Cooperative Awareness Messages (CAMs) for external communication with the environment. VANETs are vulnerable to a variety of attacks, including Black Hole, Gray Hole, wormhole, and rush attacks. These attacks are aimed at disrupting traffic between cars and on the roadside. The discovery of Black Hole attack has become an increasingly critical problem due to widespread adoption of autonomous and connected vehicles (ACVs). Due to the critical nature of ACVs, delay or failure of even a single packet can have disastrous effects, leading to accidents. In this work, we present a neural network-based technique for detection and prevention of rushed Black and Gray Hole attacks in vehicular networks. The work also studies novel systematic reactions protecting the vehicle against dangerous behavior. Experimental results show a superior detection rate of the proposed system in comparison with state-of-the-art techniques. Full article

Multimodal research is an emerging field of artificial intelligence, and the analysis of dangerous driving behavior is one of the main application scenarios in the field of multimodal fusion. Aiming at the problem of data heterogeneity in the process of behavior classification by multimodal fusion, this paper proposes a low-rank multimodal data fusion method, which utilizes the complementarity between data modalities of different dimensions in order to classify and identify dangerous driving behaviors. This method uses tensor difference matrix data to force low-rank fusion representation, improves the verification efficiency of dangerous driving behaviors through multi-level abstract tensor representation, and solves the problem of output data complexity. A recurrent network based on the attention mechanism, AR-GRU, updates the network input parameter state and learns the weight parameters through its gated structure. This model improves the dynamic connection between modalities on heterogeneous threads and reduces computational complexity. Under low-rank conditions, it can quickly and accurately classify and identify dangerous driving behaviors and give early warnings. Through a large number of experiments, the accuracy of this method is improved by an average of 1.76% compared with the BiLSTM method and the BiGRU-IAAN method in the training and verification of the self-built dataset. Full article

To address the dangerous driving behaviors prevalent among current car drivers, it is necessary to provide real-time, accurate warning and correction of driver’s driving behaviors in a small, movable, and enclosed space. In this paper, we propose a method for detecting dangerous behaviors based on frequency-modulated continuous-wave radar (mm-DSF). The highly packaged millimeter-wave radar chip has good in-vehicle emotion recognition capability. The acquired millimeter-wave differential frequency signal is Fourier-transformed to obtain the intermediate frequency signal. The physiological decomposition of the local micro-Doppler feature spectrum of the target action is then used as the eigenvalue. Matrix signal intensity and clutter filtering are performed by analyzing the signal echo model of the input channel. The signal classification is based on the estimation and variety of the feature vectors of the target key actions using a modified and optimized level fusion method of the SlowFast dual-channel network. Nine typical risky driving behaviors were set up by the Dula Hazard Questionnaire and TEIQue-SF, and the accuracy of the classification results of the self-built dataset was analyzed to verify the high robustness of the method. The recognition accuracy of this method increased by 1.97% compared with the traditional method. Full article

Driving behavior is considered one of the most important factors in all road crashes, accounting for 40% of all fatal and serious accidents. Moreover, aggressive driving is the leading cause of traffic accidents that jeopardize human life and property. By evaluating data collected by various collection devices, it is possible to detect dangerous and aggressive driving, which is a huge step toward altering the situation. The utilization of driving data, which has arisen as a new tool for assessing the style of driving, has lately moved the concentration of aggressive recognition research. The goal of this study is to detect dangerous and aggressive driving profiles utilizing data gathered from motorcyclists and smartphone APPs that run on the Android operating system. A two-stage method is used: first, determine driver profile thresholds (rules), then differentiate between non-aggressive and aggressive driving and show the harmful conduct for producing the needed outcome. The data were collected from motorcycles using -Speedometer GPS-, an application based on the Android system, supplemented with spatiotemporal information. After the completion of data collection, preprocessing of the raw data was conducted to make them ready for use. The next steps were extracting the relevant features and developing the classification model, which consists of the transformation of patterns into features that are considered a compressed representation. Lastly, this study discovered a collection of key characteristics which might be used to categorize driving behavior as aggressive, normal, or dangerous. The results also revealed major safety issues related to driving behavior while riding a motorcycle, providing valuable insight into improving road safety and reducing accidents. Full article