Dense pedestrian detection based on improved YOLO-v5

JiaLe Wan; JunLi Li

doi:10.1117/12.2646833

7 September 2022 Dense pedestrian detection based on improved YOLO-v5

JiaLe Wan, JunLi Li

Proceedings Volume 12329, Third International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2022); 123291M (2022) https://doi.org/10.1117/12.2646833
Event: Third International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2022), 2022, Changsha, China

Abstract

Aiming at the problems of low model detection speed and low detection accuracy caused by pedestrian occlusion and changing pedestrian poses in dense pedestrian detection, a dense pedestrian detection algorithm with Hierarchical Vision Transformer Prediction Head (STPH)-YOLOv5 is proposed. Based on YOLOv5, the original YOLOv5 prediction head is replaced with a Hierarchical Vision Transformer Prediction Head (STPH) to explore the prediction potential with selfattention mechanism. In addition, a coordinate attention mechanism is integrated to accurately capture the location and orientation information of pedestrians in the image. In order to avoid the loss of feature information caused by the deepening of the network, the fused multi-scale feature network (BiFPN) is used in the neck part of the improved algorithm to replace the PANet in the original YOLOv5, which makes the prediction network more sensitive to targets of different sizes and improves the overall model. The detection ability reduces the missed detection rate and false detection rate of the model.

Citation Download Citation

JiaLe Wan and JunLi Li "Dense pedestrian detection based on improved YOLO-v5", Proc. SPIE 12329, Third International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2022), 123291M (7 September 2022); https://doi.org/10.1117/12.2646833

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Transformers

Computer programming

Data modeling

Detection and tracking algorithms

Feature extraction

Head

Visual process modeling

Show All Keywords

Keywords/Phrases

Search In:

Publication Years