Multispectral pedestrian detection based on feature complementation and enhancement

Abstract Multispectral pedestrian detection with visible light and infrared images is robust to changes in lighting conditions and therefore is of great importance to numerous applications that require all‐day environmental perception. This paper proposes a novel method named FCE‐RCNN, which integra...

Full description

Saved in:
Bibliographic Details
Main Authors: Linzhen Nie, Meihe Lu, Zhiwei He, Jiachen Hu, Zhishuai Yin
Format: Article
Language:English
Published: Wiley 2024-11-01
Series:IET Intelligent Transport Systems
Subjects:
Online Access:https://doi.org/10.1049/itr2.12562
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850197610769416192
author Linzhen Nie
Meihe Lu
Zhiwei He
Jiachen Hu
Zhishuai Yin
author_facet Linzhen Nie
Meihe Lu
Zhiwei He
Jiachen Hu
Zhishuai Yin
author_sort Linzhen Nie
collection DOAJ
description Abstract Multispectral pedestrian detection with visible light and infrared images is robust to changes in lighting conditions and therefore is of great importance to numerous applications that require all‐day environmental perception. This paper proposes a novel method named FCE‐RCNN, which integrates saliency detection as a sub‐task and utilizes global information for enhanced feature representation. The approach enhances thermal inputs by incorporating gradients at the raw‐data level before feature extraction. Utilizing a dual‐stream backbone, a global semantic information extraction module is introduced that combines pooling with horizontal–vertical attention mechanisms, capturing high‐quality global semantic information for lower‐level feature enrichment and guidance. Additionally, the pedestrian locality enhancement module is designed to enhance spatial locality information of pedestrians through saliency detection. Furthermore, to alleviate the challenges posed by positional shifts between cross‐spectral features, deformable convolution is innovatively employed. Experimental results on the KAIST dataset demonstrate that FCE‐RCNN significantly improves nighttime detection, achieving a log‐average miss rate of 6.92%, outperforming the new method ICAFusion by 0.93%. These results underscore the effectiveness of FCE‐RCNN, and the method also maintains competitive inference speed, making it suitable for real‐time applications.
format Article
id doaj-art-e7875880a4c5433d9245327eda3c2784
institution OA Journals
issn 1751-956X
1751-9578
language English
publishDate 2024-11-01
publisher Wiley
record_format Article
series IET Intelligent Transport Systems
spelling doaj-art-e7875880a4c5433d9245327eda3c27842025-08-20T02:13:06ZengWileyIET Intelligent Transport Systems1751-956X1751-95782024-11-0118112166217710.1049/itr2.12562Multispectral pedestrian detection based on feature complementation and enhancementLinzhen Nie0Meihe Lu1Zhiwei He2Jiachen Hu3Zhishuai Yin4School of Automotive Engineering Wuhan University of Technology Wuhan ChinaSchool of Automotive Engineering Wuhan University of Technology Wuhan ChinaSchool of Automotive Engineering Wuhan University of Technology Wuhan ChinaSchool of Automotive Engineering Wuhan University of Technology Wuhan ChinaSchool of Automotive Engineering Wuhan University of Technology Wuhan ChinaAbstract Multispectral pedestrian detection with visible light and infrared images is robust to changes in lighting conditions and therefore is of great importance to numerous applications that require all‐day environmental perception. This paper proposes a novel method named FCE‐RCNN, which integrates saliency detection as a sub‐task and utilizes global information for enhanced feature representation. The approach enhances thermal inputs by incorporating gradients at the raw‐data level before feature extraction. Utilizing a dual‐stream backbone, a global semantic information extraction module is introduced that combines pooling with horizontal–vertical attention mechanisms, capturing high‐quality global semantic information for lower‐level feature enrichment and guidance. Additionally, the pedestrian locality enhancement module is designed to enhance spatial locality information of pedestrians through saliency detection. Furthermore, to alleviate the challenges posed by positional shifts between cross‐spectral features, deformable convolution is innovatively employed. Experimental results on the KAIST dataset demonstrate that FCE‐RCNN significantly improves nighttime detection, achieving a log‐average miss rate of 6.92%, outperforming the new method ICAFusion by 0.93%. These results underscore the effectiveness of FCE‐RCNN, and the method also maintains competitive inference speed, making it suitable for real‐time applications.https://doi.org/10.1049/itr2.12562automated drivingintelligent vehiclescomputer visionimage fusioninfrared imaging
spellingShingle Linzhen Nie
Meihe Lu
Zhiwei He
Jiachen Hu
Zhishuai Yin
Multispectral pedestrian detection based on feature complementation and enhancement
IET Intelligent Transport Systems
automated driving
intelligent vehicles
computer vision
image fusion
infrared imaging
title Multispectral pedestrian detection based on feature complementation and enhancement
title_full Multispectral pedestrian detection based on feature complementation and enhancement
title_fullStr Multispectral pedestrian detection based on feature complementation and enhancement
title_full_unstemmed Multispectral pedestrian detection based on feature complementation and enhancement
title_short Multispectral pedestrian detection based on feature complementation and enhancement
title_sort multispectral pedestrian detection based on feature complementation and enhancement
topic automated driving
intelligent vehicles
computer vision
image fusion
infrared imaging
url https://doi.org/10.1049/itr2.12562
work_keys_str_mv AT linzhennie multispectralpedestriandetectionbasedonfeaturecomplementationandenhancement
AT meihelu multispectralpedestriandetectionbasedonfeaturecomplementationandenhancement
AT zhiweihe multispectralpedestriandetectionbasedonfeaturecomplementationandenhancement
AT jiachenhu multispectralpedestriandetectionbasedonfeaturecomplementationandenhancement
AT zhishuaiyin multispectralpedestriandetectionbasedonfeaturecomplementationandenhancement