WZWei Zhao

Wei Zhao

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Wei Zhao has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Fusion Algorithm for Pedestrian Anomaly Detection and Tracking on Urban Roads Based on Multi-Module Collaboration and Cross-Frame Matching Optimization

    by Wei Zhao, Xin Gong, Lanlan Li, Luoyang Zuo

    Amid rapid advancements in artificial intelligence, the detection of abnormal human behaviors in complex traffic environments has garnered significant attention. However, detection errors frequently occur due to interference from complex backgrounds, small targets, and other factors. Therefore, this paper proposes a research methodology that integrates the anomaly detection YOLO-SGCF algorithm with the tracking BoT-SORT-ReID algorithm. The detection module uses YOLOv8 as the baseline model, incorporating Swin Transformer to enhance global feature modeling capabilities in complex scenes. CBAM and CA attention are embedded into the Neck and backbone, respectively: CBAM enables dual-dimensional channel-spatial weighting, while CA precisely captures object location features by encoding coordinate information. The Neck layer incorporates GSConv convolutional modules to reduce computational load while expanding feature receptive fields. The loss function is replaced with Focal-EIoU to address sample imbalance issues and precisely optimize bounding box regression. For tracking, to enhance long-term tracking stability, ReID feature distances are incorporated during the BoT-SORT data association phase. This integrates behavioral category information from YOLO-SGCF, enabling the identification and tracking of abnormal pedestrian behaviors in complex environments. Evaluations on our self-built dataset (covering four abnormal behaviors: Climb, Fall, Fight, Phone) show mAP@50%, precision, and recall reaching 92.2%, 90.75%, and 86.57% respectively—improvements of 3.4%, 4.4%, and 6% over the original model—while maintaining an inference speed of 328.49 FPS. Additionally, generalization testing on the UCSD Ped1 dataset (covering six abnormal behaviors: Biker, Skater, Car, Wheelchair, Lawn, Runner) yielded an mAP score of 92.7%, representing a 1.5% improvement over the original model and outperforming existing mainstream models. Furthermore, the tracking algorithm achieved an MOTA of 90.8% and an MOTP of 92.6%, with a 47.6% reduction in IDS, demonstrating superior tracking performance compared to existing mainstream algorithms.


  • Open Access

    CPB-YOLOv8: An Enhanced Multi-Scale Traffic Sign Detector for Complex Road Environment

    by Wei Zhao, Lanlan Li, Xin Gong

    Traffic sign detection is critically important for intelligent transportation systems, yet persistent challenges like multi-scale variation and complex background interference severely degrade detection accuracy and real-time performance. To address these limitations, this study presents CPB-YOLOv8, an advanced multi-scale detection framework based on the YOLOv8 architecture. A Cross-Stage Partial-Partitioned Transformer Block (CSP-PTB) is incorporated into the feature extraction stage to preserve semantic information during downsampling while enhancing global feature representation. For feature fusion, a four-level bidirectional feature pyramid BiFPN integrated with a P2 detection layer significantly improves small-target detection capability. Further enhancement is achieved via an optimized loss function that balances multi-scale objective localization. Comprehensive evaluations were conducted on the TT100K, the CCTSDB, and a custom multi-scenario road image dataset capturing urban and suburban environments at 1920 × 1080 resolution. Results demonstrate compelling performance: On TT100K, CPB-YOLOv8 achieved 90.73% mAP@0.5 with a 12.5 MB model size, exceeding the YOLOv8s baseline by 3.94 percentage points and achieving 6.43% higher small-target recall. On CCTSDB, it attained a near-saturation performance of 99.21% mAP@0.5. Crucially, the model demonstrated exceptional robustness across diverse environmental conditions. Rigorous analysis on partitioned CCTSDB subsets based on weather and illumination, alongside validation using a separate self-collected dataset reserved solely for inference, confirmed strong adaptability to real-world distribution shifts and low-visibility scenarios. Cross-dataset validation and visual comparisons further substantiated the model’s robustness and its effective suppression of background interference.


  • Open Access

    An Innovative Path Planning Algorithm for Complex Obstacle Environments with Adaptive Obstacle Density Adjustment: AODA-PF-RRT*

    by Wei Zhao, Ao Tan, Congcong Ren

    To address the limitations of low node utilization and inadequate adaptability in complex environments encountered by Rapidly-exploring Random Tree (RRT) algorithms during the expansion phase, this study presents an enhanced path planning algorithm—AODA-PF-RRT* (Adaptive Obstacle Density Adjustment-PF-RRT*). The proposed algorithm implements a random extension strategy for nodes that fail collision detection, thereby improving node efficiency. Furthermore, it dynamically partitions the area surrounding sampling points and calculates local obstacle density in real time. By leveraging this density information, the algorithm flexibly adjusts both the number of expansion points and the dichotomy threshold, significantly enhancing its responsiveness to environmental changes. We rigorously demonstrate the algorithm’s probabilistic completeness and asymptotic optimality. Simulation and benchmarking results demonstrate that the AODA-PF-RRT* algorithm not only generates smooth and high-quality paths compared to existing algorithms but also maintains low computational costs in complex environments, showcasing exceptional stability and robustness.


  • Open Access

    Study on Nighttime Pedestrian Trajectory-Tracking from the Perspective of Driving Blind Spots

    by Wei Zhao, Congcong Ren, Ao Tan

    With the acceleration of urbanization and the growing demand for traffic safety, developing intelligent systems capable of accurately recognizing and tracking pedestrian trajectories at night or under low-light conditions has become a research focus in the field of transportation. This study aims to improve the accuracy and real-time performance of nighttime pedestrian-detection and -tracking. A method that integrates the multi-object detection algorithm YOLOP with the multi-object tracking algorithm DeepSORT is proposed. The improved YOLOP algorithm incorporates the C2f-faster structure in the Backbone and Neck sections, enhancing feature extraction capabilities. Additionally, a BiFormer attention mechanism is introduced to focus on the recognition of small-area features, the CARAFE module is added to improve shallow feature fusion, and the DyHead dynamic target-detection head is employed for comprehensive fusion. In terms of tracking, the ShuffleNetV2 lightweight module is integrated to reduce model parameters and network complexity. Experimental results demonstrate that the proposed FBCD-YOLOP model improves lane detection accuracy by 5.1%, increases the IoU metric by 0.8%, and enhances detection speed by 25 FPS compared to the baseline model. The accuracy of nighttime pedestrian-detection reached 89.6%, representing improvements of 1.3%, 0.9%, and 3.8% over the single-task YOLO v5, multi-task TDL-YOLO, and the original YOLOP models, respectively. These enhancements significantly improve the model’s detection performance in complex nighttime environments. The enhanced DeepSORT algorithm achieved an MOTA of 86.3% and an MOTP of 84.9%, with ID switch occurrences reduced to 5. Compared to the ByteTrack and StrongSORT algorithms, MOTA improved by 2.9% and 0.4%, respectively. Additionally, network parameters were reduced by 63.6%, significantly enhancing the real-time performance of nighttime pedestrian-detection and -tracking, making it highly suitable for deployment on intelligent edge computing surveillance platforms.


  • Open Access

    SAU-Net: Monocular Depth Estimation Combining Multi-Scale Features and Attention Mechanisms

    by Wei Zhao, Yunqing Song, Tingting Wang

    Monocular depth estimation technology is widely utilized in autonomous driving for sensing and obstacle avoidance. Recent advancements in deep-learning techniques have resulted in significant progress in monocular depth estimation. However, monocular depth estimation is mainly optimized for the luminosity error of pixels, mostly disregarding the related problems of result ambiguity and boundary artifacts in the image. To address these issues, we developed an improved network model called SAU-Net. The superposition of excessive convolutional layers in conventional convolution networks impairs the network’s timeliness and results in the loss of primary information. Therefore, we propose a convolution-free stratified transformer as an image feature extractor at the network’s coding end, which limits self-attention to innumerable windows and leverages sliding windows for characterization to reduce the network delay. This study also addresses the issue of critical information loss. We connect each feature map directly to another from a different scale. In addition, an attention module is introduced to focus on the effective features, which increases the amount of target information in the depth map. We employ the gradient loss function during the training stage to improve the segmentation accuracy of the network and the smoothness of the output image. Training and testing were conducted using the KITTI dataset. To ensure the robustness of the algorithm in practical applications, we also validated the algorithm using a campus dataset that we collected. The experimental results indicated that the accuracy of the algorithm was 89.1%, 96.4%, and 98.5% under three proportional thresholds. The estimated depth map was clear in details and edges, with fewer artifacts.


  • Open Access

    Nighttime Pedestrian Detection Based on a Fusion of Visual Information and Millimeter-Wave Radar

    by Wei Zhao, Tingting Wang, Ao Tan, Congcong Ren

    A target detection algorithm based on the fusion of vision sensors and millimeter wave radar data can effectively improve the safety of self-driving vehicles. However, a single sensor cannot obtain comprehensive category status information on the target in the nighttime environment. To improve pedestrian detection in nighttime traffic scenarios, this paper proposes a nighttime pedestrian detection method based on the fusion of infrared vision information and millimeter wave (MMW) radar data. The lateral localization and category features of the target are obtained using the improved YOLOv5 deep learning algorithm, the distance and velocity information of the target is obtained by preprocessing the MMW radar acquisition data, the pedestrian target is tracked by using the extended Kalman filter for MMW radar detection, the projection of the valid radar target point on the IR image is completed according to the spatiotemporal fusion, and then the correlation gate method is used to correlate the data, and the visual information is inherited to the radar points to get the target multimodal information, and the success associated valid target sequences are weighted to obtain the accurate target position. Finally, a decision-level fusion algorithm framework is proposed to complete the output of pedestrian multimodal information in nighttime traffic scenes. Theoretical analysis and experimental results show that the accuracy and robustness of this method for nighttime pedestrian recognition are better than those of a single sensor.