ZDZhenyu Ding

Zhenyu Ding

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zhenyu Ding has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Pothole detection‐you only look once: Deformable convolution based road pothole detection

    by Pei Tang, Mao Lv, Zhenyu Ding, Weikai Xu, Minnan Jiang

    The detection of road potholes plays a crucial role in ensuring passenger comfort and the structural safety of vehicles. To address the challenges of pothole detection in complex road environments, this paper proposes a model focusing on shape features (pothole detection you only look once, PD‐YOLO). The model aims to overcome the limitations of multi‐scale feature learning caused by the use of fixed convolutional kernels in the baseline model, by constructing a feature extraction module that better adapts to variations in the shape of potholes. Subsequently, a cross‐stage partial network was designed using a one‐time aggregation method, simplifying the model while enabling the network to fuse information between feature maps at different stages. Additionally, a dynamic sparse attention mechanism is introduced to select relevant features, reducing redundancy and suppressing background noise. Experiments conducted on the VOC2007 and GRDDC2020_Pothole datasets reveal that compared to the baseline model YOLOv8, PD‐YOLO achieves improvements of 3.9% and 2.8% in mean average precision, with a frame rate of approximately 290 frames per second, effectively meeting the accuracy and real‐time requirements for pothole detection. The code and dataset for this paper are located at: https://github.com/woyijiankou/PD‐YOLO .


  • Open Access

    LBT-YOLO: A Lightweight Road Targeting Algorithm Based on Task Aligned Dynamic Detection Heads

    by Pei Tang, Zhen Yu Ding, Min Nan Jiang, Wei Kai Xu, Mao Lv

    Aiming at the problem of limited computing power of mobile driving platforms, this paper proposes an improved algorithm based on YOLOv8n-LBT-YOLO.The algorithm is improved in three aspects: firstly, replacing part of the traditional convolutional layers by linear deformable convolution, and designing a new C2L module by optimizing the C2F module, so as to reduce the number of model parameters and maintain the detection accuracy at the same time. Secondly, a new neck network structure BCFPN (Bidirectional Collocated Feature Pyramid Network) is designed based on the weighted bidirectional feature pyramid network, which enhances the feature fusion and the interaction of contextual information, and improves the detection accuracy of the model. Finally, a new detection head TADDH (Task Aligned Dynamic Detection Head) is proposed. This detection head reduces the number of parameters by sharing the neck network features, and performs task decomposition alignment to achieve high accuracy target detection using dynamic convolution and dynamic feature selection. After a series of improvements, LBT-YOLO outperforms YOLOv8n and other detection algorithms (such as Faster RCNN, YOLOv5n, and SSD) on the Autonomous Driving BDD100K dataset, with an average accuracy improvement of 2.4% while reducing the number of model parameters by 48.2%.


  • Open Access

    Research on multi-objective topology optimization of unmanned sightseeing vehicle frame based on Analytic Hierarchy Process

    by Pei Tang, Weikai Xu, Zhenyu Ding, Minnan Jiang, Mao Lv

    To optimize the frame of a sightseeing vehicle, this paper proposes a multi-objective topology optimization method combining Analytic Hierarchy Process (AHP) and topology optimization. Firstly, the edges of the unmanned sightseeing car are statically analyzed. The rectangular steel frame structure of the original frame is replaced with square plates, the basic model of the unmanned sightseeing car frame is established, and a single-objective topology optimization mathematical model of the frame is established to optimize the topology design of the frame. Then, in order to design a frame structure that meets all the working conditions at the same time, a mathematical model of multi-working condition topology optimization is established, and the weights of each working condition are determined by using AHP, and the multi-working condition topology optimization design of the frame is carried out. Finally, a comparison of the comprehensive performance of the frame before and after optimization shows that the proposed method enables the optimized frame to meet the strength requirements under various working conditions, resulting in a weight reduction of 16.5 kg.


  • Open Access

    YOLO‐RSFM: An efficient road small object detection method

    by Pei Tang, Zhenyu Ding, Mao Lv, Minnan Jiang, Weikai Xu

    To tackle challenges in road multi‐object detection, such as object occlusion, small object detection, and multi‐scale object detection difficulties, a new YOLOv8n‐RSFM structure is proposed. The key improvement of this structure lies in the introduction of the transformer decoder head, which optimizes the matching between the ground truth and predicted boxes, thereby effectively addressing issues of object overlap and multi‐scale detection. Additionally, a small object detection layer is incorporated to retain crucial information beneficial for detecting small objects, significantly improving the detection accuracy for small targets. To enhance learning capacity and reduce redundant computations, the FasterNet backbone is employed to replace CSPDarknet53, thus accelerating the training process. Finally, the INNER‐MPDIoU loss function is introduced to replace the original algorithm's complete IoU to accelerate the convergence and obtain more accurate regression results. A series of experiments were conducted on different datasets. The experimental results show that the proposed model YOLOv8N‐RSFM outperforms the original model YOLOv8n in small target detection. On the VisDrone, TinyPerson, and VSCrowd datasets, the mean accuracy percentage improved by 7.9%, 12.3%, and 4.5%, respectively.