Opto-Electronic Engineering, Volume. 51, Issue 4, 240025-1(2024)

PAW-YOLOv7: algorithm for detection of tiny floating objects in river channels

Qinglei Luan1,2, Xinyu Chang1,2, Ye Wu1,2, Conglong Deng1,2、*, Yanqiong Shi1,2, and Zihua Chen1,2
Author Affiliations
  • 1School of Mechanical and Electrical Engineering, Anhui Jianzhu University, Hefei, Anhui 230601, China
  • 2Anhui Province Key Laboratory of Intelligent Manufacturing of Construction Machinery, Hefei, Anhui 230601, China
  • show less
    Figures & Tables(13)
    YOLOv7 network structure
    PConv structure diagram
    The process of calculating ODConv
    ACmix structure diagram
    PAW-YOLOv7 network structure diagram
    Results of different data expansion methods
    Object scale distribution of the dataset
    Target detection results of different algorithms in different scenes. Left: detection image, Center: YOLOv7 model, Right: algorithm of this paper
    Comparison of detection accuracy of self-built datasets
    Comparison results of heat maps with different algorithms
    • Table 1. Results of ablation experiments

      View table
      View in Article

      Table 1. Results of ablation experiments

      组别HeadACmixODCBSWIoUPC-ELANmAP/%FLOPs/GFPS
      179.9105.4101
      281.1119.586
      385.6101.675
      480.8109.897
      581.5105.4108
      678.183.7124
      787.3115.356
      888.2119.247
      990.8119.248
      1089.797.854
    • Table 2. Comparative experimental data of each algorithm on FloW-Img dataset

      View table
      View in Article

      Table 2. Comparative experimental data of each algorithm on FloW-Img dataset

      算法mAP/%FPSFLOPs/GParams/M
      SSD73.37178.426.3
      Faster R-CNN76.86375.1137.1
      YOLOv385.712596.361.5
      YOLOv5s84.123664.710.7
      TPH-YOLOv582.369125.626.1
      YOLOv779.9101105.437.2
      YOLOv8l86.4117155.443.6
      PAW-YOLOv789.75497.825.4
    • Table 3. Comparative experimental data of each algorithm on self-constructed dataset

      View table
      View in Article

      Table 3. Comparative experimental data of each algorithm on self-constructed dataset

      算法mAP/%FPSFLOPs/GParams/M
      SSD57.96778.426.3
      Faster R-CNN61.36175.1137.1
      YOLOv359.713796.361.5
      YOLOv5s66.524264.310.7
      TPH-YOLOv563.774125.626.1
      YOLOv768.198105.137.2
      YOLOv8l65.9106155.443.6
      PAW-YOLOv771.86897.725.4
    Tools

    Get Citation

    Copy Citation Text

    Qinglei Luan, Xinyu Chang, Ye Wu, Conglong Deng, Yanqiong Shi, Zihua Chen. PAW-YOLOv7: algorithm for detection of tiny floating objects in river channels[J]. Opto-Electronic Engineering, 2024, 51(4): 240025-1

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Article

    Received: Jan. 25, 2024

    Accepted: Mar. 12, 2024

    Published Online: Jul. 8, 2024

    The Author Email: Conglong Deng (邓从龙)

    DOI:10.12086/oee.2024.240025

    Topics