Research on small target pedestrian detection based on improved YOLO

被引：1
|
作者：
Xu X. [1 ]
Wang K. [1 ]
Zhao Y. [2 ]
机构：
[1] School of Mechanical and Energy Engineering, Zhejiang University of Science and Technology, Hangzhou, Zhejiang
[2] School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou, Zhejiang
来源：
International Journal of Wireless and Mobile Computing | 2021年 / 20卷 / 03期
基金：
中国国家自然科学基金;
关键词：
Deep learning; Pedestrian detection; Small target; YOLO;
D O I：
10.1504/IJWMC.2021.115659
中图分类号：
学科分类号：
摘要：
Aiming at the problems of low detection accuracy and speed for small target pedestrian in traffic scenes, the YOLO-SP based on YOLO-v4 is proposed. Firstly, the KITTI and INRIA data sets are used to make the new data set, and k-means algorithm is used to cluster the anchor box. Secondly, in the feature fusion phase (Neck), we increase the number of fused channels and simplify the number of output channels. Finally, to optimise the loss function, GIOU is used to calculate the coordinate loss, Focal is used to calculate the confidence loss. The test shows that all the improvement measures show better effect on small and overlapping pedestrians, the final detection accuracy (AP) is increased by 4.0%, the detection speed is accelerated by 11.3%. YOLO-SP has a certain practicality in the small target pedestrian detection. Copyright © 2021 Inderscience Enterprises Ltd.
引用
收藏
页码：281 / 289
页数：8
相关论文
共 50 条
  • [1] Research on Small Target Detection in Driving Scenarios Based on Improved Yolo Network
    Xu, Qiwei
    Lin, Runzi
    Yue, Han
    Huang, Hong
    Yang, Yun
    Yao, Zhigang
    IEEE ACCESS, 2020, 8 : 27574 - 27583
  • [2] Research on Target Detection Algorithm Based on Improved YOLO
    Chen, Zhigang
    Liu, Guangxin
    Fan, Shengwen
    2022 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, COMPUTER VISION AND MACHINE LEARNING (ICICML), 2022, : 485 - 489
  • [3] Improved Target Detection Algorithm Based on YOLO
    Yan, Fengxi
    Xu, Yinxia
    2021 4TH INTERNATIONAL CONFERENCE ON ROBOTICS, CONTROL AND AUTOMATION ENGINEERING (RCAE 2021), 2021, : 21 - 25
  • [4] Research on Tiny Target Detection Technology of Fabric Defects Based on Improved YOLO
    Yue, Xi
    Wang, Qing
    He, Lei
    Li, Yuxia
    Tang, Dan
    APPLIED SCIENCES-BASEL, 2022, 12 (13):
  • [5] Research on Pedestrian Detection Algorithm Based on MobileNet-YoLo
    Liu, Lisang
    Ke, Chengyang
    Lin, He
    Xu, Hui
    COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2022, 2022
  • [6] An improved YOLO algorithm with multisensing for pedestrian detection
    Gong, Lixiong
    Wang, Yuanyuan
    Huang, Xiao
    Liang, Jiale
    Fan, Yanmiao
    SIGNAL IMAGE AND VIDEO PROCESSING, 2024, 18 (8-9) : 5893 - 5906
  • [7] Small Pedestrian Target Detection in Subway Scene Based on Improved SSD Algorithm
    Zhang, Xiuzai
    Qiu, Ye
    Shen, Tao
    Jisuanji Yanjiu yu Fazhan/Computer Research and Development, 2025, 62 (02): : 397 - 407
  • [8] MULTI-SMALL TARGET DETECTION AND TRACKING BASED ON IMPROVED YOLO AND SIFT FOR DRONES
    Lu, Pancheng
    Ding, Yong
    Wang, Changjian
    INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2021, 17 (01): : 205 - 224
  • [9] Road small target detection based on improved YOLO v5 algorithm
    Song, Cunli
    Chai, Weiqin
    Zhang, Xuesong
    Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics, 2024, 46 (10): : 3271 - 3278
  • [10] Ship Target Detection Based on Improved YOLO Network
    Huang, Hong
    Sun, Dechao
    Wang, Renfang
    Zhu, Chun
    Liu, Bangquan
    MATHEMATICAL PROBLEMS IN ENGINEERING, 2020, 2020
12345