ALSS-YOLO: An Adaptive Lightweight Channel Split and Shuffling Network for TIR Wildlife Detection in UAV Imagery

Unmanned aerial vehicles (UAVs) equipped with thermal infrared (TIR) cameras play a crucial role in combating nocturnal wildlife poaching. However, TIR images often face challenges such as jitter and wildlife overlap, necessitating UAVs to possess the capability to identify blurred and overlapping s...

Full description

Saved in:
Bibliographic Details
Main Authors: Ang He, Xiaobo Li, Ximei Wu, Chengyue Su, Jing Chen, Sheng Xu, Xiaobin Guo
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10680397/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846166273629618176
author Ang He
Xiaobo Li
Ximei Wu
Chengyue Su
Jing Chen
Sheng Xu
Xiaobin Guo
author_facet Ang He
Xiaobo Li
Ximei Wu
Chengyue Su
Jing Chen
Sheng Xu
Xiaobin Guo
author_sort Ang He
collection DOAJ
description Unmanned aerial vehicles (UAVs) equipped with thermal infrared (TIR) cameras play a crucial role in combating nocturnal wildlife poaching. However, TIR images often face challenges such as jitter and wildlife overlap, necessitating UAVs to possess the capability to identify blurred and overlapping small targets. Current traditional lightweight networks deployed on UAVs struggle to extract features from blurry small targets. To address this issue, we developed ALSS-YOLO, an efficient and lightweight detector optimized for TIR aerial images. First, we propose a novel adaptive lightweight channel split and shuffling (ALSS) module. This module employs an adaptive channel split strategy to optimize feature extraction and integrates a channel shuffling mechanism to enhance information exchange between channels. This improves the extraction of blurry features, crucial for handling jitter-induced blur and overlapping targets. Second, we developed a lightweight coordinate attention (LCA) module that employs adaptive pooling and grouped convolution to integrate feature information across dimensions. This module ensures lightweight operation while maintaining high detection precision and robustness against jitter and target overlap. Additionally, we developed a single-channel focus module to aggregate the width and height information of each channel into 4-D channel fusion, which improves the feature representation efficiency of infrared images. Finally, we modify the localization loss function to emphasize the loss value associated with small objects to improve localization accuracy. Extensive experiments on the BIRDSAI and ISOD TIR UAV wildlife datasets show that ALSS-YOLO achieves state-of-the-art performance.
format Article
id doaj-art-78792cd46a8e4d27b378a23d6c1f7fe0
institution Kabale University
issn 1939-1404
2151-1535
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-78792cd46a8e4d27b378a23d6c1f7fe02024-11-16T00:00:10ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352024-01-0117173081732610.1109/JSTARS.2024.346117210680397ALSS-YOLO: An Adaptive Lightweight Channel Split and Shuffling Network for TIR Wildlife Detection in UAV ImageryAng He0https://orcid.org/0009-0003-7204-7983Xiaobo Li1Ximei Wu2Chengyue Su3Jing Chen4https://orcid.org/0000-0001-5206-1110Sheng Xu5https://orcid.org/0000-0002-6314-8104Xiaobin Guo6https://orcid.org/0000-0003-0262-4063Guangdong Provincial Key Laboratory of Sensing Physics and System Integration Applications, Guangdong University of Technology, Guangzhou Higher Education Mega Centre, Guangzhou, PR ChinaGuangdong Provincial Key Laboratory of Sensing Physics and System Integration Applications, Guangdong University of Technology, Guangzhou Higher Education Mega Centre, Guangzhou, PR ChinaGuangdong Provincial Key Laboratory of Sensing Physics and System Integration Applications, Guangdong University of Technology, Guangzhou Higher Education Mega Centre, Guangzhou, PR ChinaGuangdong Provincial Key Laboratory of Sensing Physics and System Integration Applications, Guangdong University of Technology, Guangzhou Higher Education Mega Centre, Guangzhou, PR ChinaGuangdong Provincial Key Laboratory of Sensing Physics and System Integration Applications, Guangdong University of Technology, Guangzhou Higher Education Mega Centre, Guangzhou, PR ChinaGuangdong Provincial Key Laboratory of Sensing Physics and System Integration Applications, Guangdong University of Technology, Guangzhou Higher Education Mega Centre, Guangzhou, PR ChinaGuangdong Provincial Key Laboratory of Sensing Physics and System Integration Applications, Guangdong University of Technology, Guangzhou Higher Education Mega Centre, Guangzhou, PR ChinaUnmanned aerial vehicles (UAVs) equipped with thermal infrared (TIR) cameras play a crucial role in combating nocturnal wildlife poaching. However, TIR images often face challenges such as jitter and wildlife overlap, necessitating UAVs to possess the capability to identify blurred and overlapping small targets. Current traditional lightweight networks deployed on UAVs struggle to extract features from blurry small targets. To address this issue, we developed ALSS-YOLO, an efficient and lightweight detector optimized for TIR aerial images. First, we propose a novel adaptive lightweight channel split and shuffling (ALSS) module. This module employs an adaptive channel split strategy to optimize feature extraction and integrates a channel shuffling mechanism to enhance information exchange between channels. This improves the extraction of blurry features, crucial for handling jitter-induced blur and overlapping targets. Second, we developed a lightweight coordinate attention (LCA) module that employs adaptive pooling and grouped convolution to integrate feature information across dimensions. This module ensures lightweight operation while maintaining high detection precision and robustness against jitter and target overlap. Additionally, we developed a single-channel focus module to aggregate the width and height information of each channel into 4-D channel fusion, which improves the feature representation efficiency of infrared images. Finally, we modify the localization loss function to emphasize the loss value associated with small objects to improve localization accuracy. Extensive experiments on the BIRDSAI and ISOD TIR UAV wildlife datasets show that ALSS-YOLO achieves state-of-the-art performance.https://ieeexplore.ieee.org/document/10680397/Lightweight detectorsmall targetsthermal infrared (TIR)unmanned aerial vehicles (UAVs)wildlife detection
spellingShingle Ang He
Xiaobo Li
Ximei Wu
Chengyue Su
Jing Chen
Sheng Xu
Xiaobin Guo
ALSS-YOLO: An Adaptive Lightweight Channel Split and Shuffling Network for TIR Wildlife Detection in UAV Imagery
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Lightweight detector
small targets
thermal infrared (TIR)
unmanned aerial vehicles (UAVs)
wildlife detection
title ALSS-YOLO: An Adaptive Lightweight Channel Split and Shuffling Network for TIR Wildlife Detection in UAV Imagery
title_full ALSS-YOLO: An Adaptive Lightweight Channel Split and Shuffling Network for TIR Wildlife Detection in UAV Imagery
title_fullStr ALSS-YOLO: An Adaptive Lightweight Channel Split and Shuffling Network for TIR Wildlife Detection in UAV Imagery
title_full_unstemmed ALSS-YOLO: An Adaptive Lightweight Channel Split and Shuffling Network for TIR Wildlife Detection in UAV Imagery
title_short ALSS-YOLO: An Adaptive Lightweight Channel Split and Shuffling Network for TIR Wildlife Detection in UAV Imagery
title_sort alss yolo an adaptive lightweight channel split and shuffling network for tir wildlife detection in uav imagery
topic Lightweight detector
small targets
thermal infrared (TIR)
unmanned aerial vehicles (UAVs)
wildlife detection
url https://ieeexplore.ieee.org/document/10680397/
work_keys_str_mv AT anghe alssyoloanadaptivelightweightchannelsplitandshufflingnetworkfortirwildlifedetectioninuavimagery
AT xiaoboli alssyoloanadaptivelightweightchannelsplitandshufflingnetworkfortirwildlifedetectioninuavimagery
AT ximeiwu alssyoloanadaptivelightweightchannelsplitandshufflingnetworkfortirwildlifedetectioninuavimagery
AT chengyuesu alssyoloanadaptivelightweightchannelsplitandshufflingnetworkfortirwildlifedetectioninuavimagery
AT jingchen alssyoloanadaptivelightweightchannelsplitandshufflingnetworkfortirwildlifedetectioninuavimagery
AT shengxu alssyoloanadaptivelightweightchannelsplitandshufflingnetworkfortirwildlifedetectioninuavimagery
AT xiaobinguo alssyoloanadaptivelightweightchannelsplitandshufflingnetworkfortirwildlifedetectioninuavimagery