MSIA-Net: A Lightweight Infrared Target Detection Network with Efficient Information Fusion
In order to solve the problems of infrared target detection (i.e., the large models and numerous parameters), a lightweight detection network, MSIA-Net, is proposed. Firstly, a feature extraction module named MSIA, which is based on asymmetric convolution, is proposed, and it can greatly reduce the...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-05-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/25/5/808 |
_version_ | 1797600163711156224 |
---|---|
author | Jimin Yu Shun Li Shangbo Zhou Hui Wang |
author_facet | Jimin Yu Shun Li Shangbo Zhou Hui Wang |
author_sort | Jimin Yu |
collection | DOAJ |
description | In order to solve the problems of infrared target detection (i.e., the large models and numerous parameters), a lightweight detection network, MSIA-Net, is proposed. Firstly, a feature extraction module named MSIA, which is based on asymmetric convolution, is proposed, and it can greatly reduce the number of parameters and improve the detection performance by reusing information. In addition, we propose a down-sampling module named DPP to reduce the information loss caused by pooling down-sampling. Finally, we propose a feature fusion structure named LIR-FPN that can shorten the information transmission path and effectively reduce the noise in the process of feature fusion. In order to improve the ability of the network to focus on the target, we introduce coordinate attention (CA) into the LIR-FPN; this integrates the location information of the target into the channel so as to obtain more expressive feature information. Finally, a comparative experiment with other SOTA methods was completed on the FLIR on-board infrared image dataset, which proved the powerful detection performance of MSIA-Net. |
first_indexed | 2024-03-11T03:45:45Z |
format | Article |
id | doaj.art-71e9648e0bcc4798abebc5dd68b08814 |
institution | Directory Open Access Journal |
issn | 1099-4300 |
language | English |
last_indexed | 2024-03-11T03:45:45Z |
publishDate | 2023-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Entropy |
spelling | doaj.art-71e9648e0bcc4798abebc5dd68b088142023-11-18T01:16:41ZengMDPI AGEntropy1099-43002023-05-0125580810.3390/e25050808MSIA-Net: A Lightweight Infrared Target Detection Network with Efficient Information FusionJimin Yu0Shun Li1Shangbo Zhou2Hui Wang3College of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaCollege of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaCollege of Computer Science, Chongqing University, Chongqing 400044, ChinaCollege of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaIn order to solve the problems of infrared target detection (i.e., the large models and numerous parameters), a lightweight detection network, MSIA-Net, is proposed. Firstly, a feature extraction module named MSIA, which is based on asymmetric convolution, is proposed, and it can greatly reduce the number of parameters and improve the detection performance by reusing information. In addition, we propose a down-sampling module named DPP to reduce the information loss caused by pooling down-sampling. Finally, we propose a feature fusion structure named LIR-FPN that can shorten the information transmission path and effectively reduce the noise in the process of feature fusion. In order to improve the ability of the network to focus on the target, we introduce coordinate attention (CA) into the LIR-FPN; this integrates the location information of the target into the channel so as to obtain more expressive feature information. Finally, a comparative experiment with other SOTA methods was completed on the FLIR on-board infrared image dataset, which proved the powerful detection performance of MSIA-Net.https://www.mdpi.com/1099-4300/25/5/808lightweight neural networksinfrared target detectionMSIA moduleDPP modulecoordinate attentionLIR-FPN |
spellingShingle | Jimin Yu Shun Li Shangbo Zhou Hui Wang MSIA-Net: A Lightweight Infrared Target Detection Network with Efficient Information Fusion Entropy lightweight neural networks infrared target detection MSIA module DPP module coordinate attention LIR-FPN |
title | MSIA-Net: A Lightweight Infrared Target Detection Network with Efficient Information Fusion |
title_full | MSIA-Net: A Lightweight Infrared Target Detection Network with Efficient Information Fusion |
title_fullStr | MSIA-Net: A Lightweight Infrared Target Detection Network with Efficient Information Fusion |
title_full_unstemmed | MSIA-Net: A Lightweight Infrared Target Detection Network with Efficient Information Fusion |
title_short | MSIA-Net: A Lightweight Infrared Target Detection Network with Efficient Information Fusion |
title_sort | msia net a lightweight infrared target detection network with efficient information fusion |
topic | lightweight neural networks infrared target detection MSIA module DPP module coordinate attention LIR-FPN |
url | https://www.mdpi.com/1099-4300/25/5/808 |
work_keys_str_mv | AT jiminyu msianetalightweightinfraredtargetdetectionnetworkwithefficientinformationfusion AT shunli msianetalightweightinfraredtargetdetectionnetworkwithefficientinformationfusion AT shangbozhou msianetalightweightinfraredtargetdetectionnetworkwithefficientinformationfusion AT huiwang msianetalightweightinfraredtargetdetectionnetworkwithefficientinformationfusion |