Welcome to Journal of Beijing Institute of Technology
Cheng Zhang, Cheng Xu, Hongzhe Liu. PF-YOLO: An Improved YOLOv8 for Small Object Detection in Fisheye Images[J]. JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY, 2025, 34(1): 57-70. DOI: 10.15918/j.jbit1004-0579.2024.077
Citation: Cheng Zhang, Cheng Xu, Hongzhe Liu. PF-YOLO: An Improved YOLOv8 for Small Object Detection in Fisheye Images[J]. JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY, 2025, 34(1): 57-70. DOI: 10.15918/j.jbit1004-0579.2024.077

PF-YOLO: An Improved YOLOv8 for Small Object Detection in Fisheye Images

  • Top-view fisheye cameras are widely used in personnel surveillance for their broad field of view, but their unique imaging characteristics pose challenges like distortion, complex scenes, scale variations, and small objects near image edges. To tackle these, we proposed peripheral focus you only look once (PF-YOLO), an enhanced YOLOv8n-based method. Firstly, we introduced a cutting-patch data augmentation strategy to mitigate the problem of insufficient small-object samples in various scenes. Secondly, to enhance the model’s focus on small objects near the edges, we designed the peripheral focus loss, which uses dynamic focus coefficients to provide greater gradient gains for these objects, improving their regression accuracy. Finally, we designed the three dimensional (3D) spatial-channel coordinate attention C2f module, enhancing spatial and channel perception, suppressing noise, and improving personnel detection. Experimental results demonstrate that PF-YOLO achieves strong performance on the challenging events for person detection from overhead fisheye images (CEPDTOF) and in-the-wild events for people detection and tracking from overhead fisheye cameras (WEPDTOF) datasets. Compared to the original YOLOv8n model, PF-YOLO achieves improvements on CEPDTOF with increases of 2.1%, 1.7% and 2.9% in mean average precision 50 ( \mathrmmAP\ 50 ), \mathrmmAP\ 50-95 , and \mathrmrecall , reaching 95.7%, 65.8% and 95.5%, respectively. On WEPDTOF, PF-YOLO achieves substantial improvements with increases of 31.4%, 14.9%, 61.1% and 21.0% in \mathrmmAP\ 50 , \mathrmmAP\ 50-95 , \mathrmprecision and \mathrmrecall reaching 53.1%, 22.8%, 91.2% and 57.2%, respectively.
  • loading

Catalog

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return
    Baidu
    map