Pedestrian detection method based on improved YOLOv5

With the development of autonomous vehicles and intelligent transportation, more accurate detection of pedestrians. However, pedestrian detection suffers from occlusion and small target. First, the HorNet to improve the higher-order spatial interaction capability of the model, expand the effective s...

Full description

Saved in:
Bibliographic Details
Main Authors: Shangtao You, Zhenchao Gu, Kai Zhu
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:Systems Science & Control Engineering
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/21642583.2023.2300836
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846118837158674432
author Shangtao You
Zhenchao Gu
Kai Zhu
author_facet Shangtao You
Zhenchao Gu
Kai Zhu
author_sort Shangtao You
collection DOAJ
description With the development of autonomous vehicles and intelligent transportation, more accurate detection of pedestrians. However, pedestrian detection suffers from occlusion and small target. First, the HorNet to improve the higher-order spatial interaction capability of the model, expand the effective sensory field, and enhance the feature extraction of pedestrians. Then, ODConv to gain the variability of each dimension and capture rich information. Finally, a layer to increase the accuracy of detecting pedestrians at small scales. We optimize the regression prediction of the anchor using the Efficient IOU Loss (EIOU) function. Experimental data show that the mean average precision (mAP) of the HOD-YOLOv5 model achieves 83.5%, compared to YOLOv5, which is 4.4% higher than original YOLOv5, and the recognition speed of the HOD-YOLOV5 reaches 106.7 frames per second (FPS). This demonstrates that the proposed model could realize real-time pedestrian detection at a relatively small cost, which satisfies the requirements of uncrewed and intelligent transportation.
format Article
id doaj-art-bc015e3883884553b6f30e9be247c721
institution Kabale University
issn 2164-2583
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series Systems Science & Control Engineering
spelling doaj-art-bc015e3883884553b6f30e9be247c7212024-12-17T09:06:12ZengTaylor & Francis GroupSystems Science & Control Engineering2164-25832024-12-0112110.1080/21642583.2023.2300836Pedestrian detection method based on improved YOLOv5Shangtao You0Zhenchao Gu1Kai Zhu2School of Mechanical Engineering, Jiangsu University of Technology, Changzhou, People’s Republic of ChinaSchool of Mechanical Engineering, Jiangsu University of Technology, Changzhou, People’s Republic of ChinaSchool of Automobile and Traffic Engineering, Jiangsu University of Technology, Changzhou, People’s Republic of ChinaWith the development of autonomous vehicles and intelligent transportation, more accurate detection of pedestrians. However, pedestrian detection suffers from occlusion and small target. First, the HorNet to improve the higher-order spatial interaction capability of the model, expand the effective sensory field, and enhance the feature extraction of pedestrians. Then, ODConv to gain the variability of each dimension and capture rich information. Finally, a layer to increase the accuracy of detecting pedestrians at small scales. We optimize the regression prediction of the anchor using the Efficient IOU Loss (EIOU) function. Experimental data show that the mean average precision (mAP) of the HOD-YOLOv5 model achieves 83.5%, compared to YOLOv5, which is 4.4% higher than original YOLOv5, and the recognition speed of the HOD-YOLOV5 reaches 106.7 frames per second (FPS). This demonstrates that the proposed model could realize real-time pedestrian detection at a relatively small cost, which satisfies the requirements of uncrewed and intelligent transportation.https://www.tandfonline.com/doi/10.1080/21642583.2023.2300836YOLOv5HorNetODConvEIOUpedestrian detection
spellingShingle Shangtao You
Zhenchao Gu
Kai Zhu
Pedestrian detection method based on improved YOLOv5
Systems Science & Control Engineering
YOLOv5
HorNet
ODConv
EIOU
pedestrian detection
title Pedestrian detection method based on improved YOLOv5
title_full Pedestrian detection method based on improved YOLOv5
title_fullStr Pedestrian detection method based on improved YOLOv5
title_full_unstemmed Pedestrian detection method based on improved YOLOv5
title_short Pedestrian detection method based on improved YOLOv5
title_sort pedestrian detection method based on improved yolov5
topic YOLOv5
HorNet
ODConv
EIOU
pedestrian detection
url https://www.tandfonline.com/doi/10.1080/21642583.2023.2300836
work_keys_str_mv AT shangtaoyou pedestriandetectionmethodbasedonimprovedyolov5
AT zhenchaogu pedestriandetectionmethodbasedonimprovedyolov5
AT kaizhu pedestriandetectionmethodbasedonimprovedyolov5