Pedestrian detection algorithm in overhead fisheye images based on improved Yolov5

Qing Tian; Zhan Li; Zheng Zhang; Nan Lyu; Jie Liu; Hao Cheng

doi:10.1117/12.2681074

8 June 2023 Pedestrian detection algorithm in overhead fisheye images based on improved Yolov5

Qing Tian, Zhan Li, Zheng Zhang, Nan Lyu, Jie Liu, Hao Cheng

Proceedings Volume 12707, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023); 127074T (2023) https://doi.org/10.1117/12.2681074
Event: International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023), 2023, Changsha, China

Abstract

Pedestrian target detection based on fisheye scene is a challenging task. Due to natural cylindrical and radial distortion of fisheye images, it is difficult to ensure the accuracy and real-time of detection by conventional methods. The original feature pyramid network in YOLOv5 is replaced with an improved BiFPN in this paper, and the problem of information loss during feature graph construction is reduced by adding residual links and module stacking. Secondly, by replacing the deformable convolution module, the network's feature extraction ability is significantly improved. A vast number of experimental findings on the WEPDTOF dataset validate the method's effectiveness and superiority when compared to various advanced approaches.

Citation Download Citation

Qing Tian, Zhan Li, Zheng Zhang, Nan Lyu, Jie Liu, and Hao Cheng "Pedestrian detection algorithm in overhead fisheye images based on improved Yolov5", Proc. SPIE 12707, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023), 127074T (8 June 2023); https://doi.org/10.1117/12.2681074

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available