Paper
10 October 2023 Research on pedestrian flow detection algorithm based on Ghostnetv2 lightweight network
Jin Lyu, Jing Yang, Ruping Shao, Wang Zhou
Author Affiliations +
Proceedings Volume 12799, Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023); 1279912 (2023) https://doi.org/10.1117/12.3006107
Event: 3rd International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023), 2023, Kuala Lumpur, Malaysia
Abstract
To solve the problems of a large number of parameters, low detection accuracy, slow detection speed of human flow target detection model, this paper proposes a YOLOv5 human flow target detection model based on GhostNetv2. The convolution in the first layer of CBS is retained to replace the remaining convolutions with Ghost Conv, and the C3Ghostv2 module is constructed to replace the original CSP structure, reducing the number of parameters, reducing the calculation cost and improving the calculation speed. Finally, the Deep-Sort algorithm tracks and realizes real-time statistics of people flow. The experimental results indicate that the accuracy of the improved YOLOv5 model is 2.4 percentage points higher than that of the original algorithm, the parameter quantity is compressed by 28 %, and the detection speed has also increased.
(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Jin Lyu, Jing Yang, Ruping Shao, and Wang Zhou "Research on pedestrian flow detection algorithm based on Ghostnetv2 lightweight network", Proc. SPIE 12799, Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023), 1279912 (10 October 2023); https://doi.org/10.1117/12.3006107
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Detection and tracking algorithms

Object detection

Convolution

Target detection

Feature extraction

Education and training

Video

RELATED CONTENT


Back to Top