PLPeigang Liu

Peigang Liu

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Peigang Liu has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Three-Dimensional Geological Modeling Method Based on Potential Vector Fields

    by Peigang Liu, Zheng Li, Gang Yu, Zongmin Li

    With the development of 3D geological modeling, implicit modeling methods have gradually gained popularity. However, existing potential field methods cannot directly represent unconformable geological interfaces. In response, an implicit modeling method based on a potential vector field was proposed, which generates geological surface models through the potential vector field method and generalized marching cubes algorithm, and visualizes the modeling results. An experiment was conducted on the study area of a certain mineral deposit, and a 3D geological surface model with consistency and no topological errors was established, demonstrating the effectiveness of the method for the surface modeling of unconformity geological interfaces.


  • Open Access

    RPS-YOLO: A Recursive Pyramid Structure-Based YOLO Network for Small Object Detection in Unmanned Aerial Vehicle Scenarios

    by Penghui Lei, Chenkang Wang, Peigang Liu

    The fast advancement of unmanned aerial vehicle (UAV) technology has facilitated its use across a wide range of scenarios. Due to the high mobility and flexibility of drones, the images they capture often exhibit significant scale variations and severe object occlusions, leading to a high density of small objects. However, the existing object detection algorithms struggle with detecting small objects effectively in cross-scale detection scenarios. To overcome these difficulties, we introduce a new object detection model, RPS-YOLO, based on the YOLOv8 architecture. Unlike the existing methods that rely on traditional feature pyramids, our approach introduces a recursive feature pyramid (RFP) structure. This structure performs two rounds of feature extraction, and we reduce one downsampling step in the first round to enhance attention to small objects during cross-scale detection. Additionally, we design a novel attention mechanism that improves feature representation and mitigates feature degradation during convolution by capturing spatial- and channel-specific details. Another key innovation is the proposed Localization IOU (LIOU) loss function for bounding box regression, which accelerates the regression process by incorporating angular constraints. Experiments conducted on the VisDrone-DET2021 and UAVDT datasets show that RPS-YOLO surpasses YOLOv8s, with an mAP50 improvement of 8.2% and 3.4%, respectively. Our approach demonstrates that incorporating recursive feature extraction and exploiting detailed information for multi-scale detection significantly improves detection performance, particularly for small objects in UAV images.


  • Open Access

    Trajectory Prediction Enhancement Method for Multiple Object Tracking in Complex Scenes

    by Peigang Liu, Ben Wang, Yachuan Li, Zhendong Cui, Junwu Wang, Shaobo Yang, Zongmin Li

    Taking the short-track speed skating match of the Winter Olympics as an example, a multiple object tracking dataset applicable to the short-track speed skating scene is designed based on the athletes’ motion characteristics, such as small distinctions in target appearance, fast motion changes, and frequent mutual occlusion between targets. A multiple object tracking method based on trajectory prediction enhancement was proposed. First, the intersection-over-union of bounding boxes and the cosine distance of appearance features are calculated to jointly judge the similarity between detection and trajectories, solving the problem of similar target appearances. Secondly, the tracking trajectory’s global features and motion clues are used to recover the lost information of occluded targets, improving the re-association ability of interrupted trajectories. Finally, the detection prior is used to control the initialization of new trajectories, reducing the impact of noisy detection on identity exchange during trajectory tracking. Experimental results show that compared with the DeepSORT method, this method can guarantee stable tracking in the short-track speed skating scene and effectively reduce trajectory interruptions, with an increase of 21 percentage points in IDF1 and 14.3 percentage points in multiple object tracking accuracy (MOTA). This method ensures long-term stable tracking in short-track speed skating scenes with small differences in targets and fast motion changes. It has inspirational significance for the application of multiple object tracking in complex scenes.