IMD-Net: Interpretable multi-scale detection network for infrared dim and small objects
This study proposed an interpretable multi-scale infrared small object detection network (IMD-Net) design method to improve the precision of infrared small object detection and contour segmentation in complex backgrounds. To this end, a multi-scale object enhancement module was constructed, which co...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
AIMS Press
2024-01-01
|
Series: | Mathematical Biosciences and Engineering |
Subjects: | |
Online Access: | https://www.aimspress.com/article/doi/10.3934/mbe.2024074?viewType=HTML |
_version_ | 1797321004370886656 |
---|---|
author | Dawei Li Suzhen Lin Xiaofei Lu Xingwang Zhang Chenhui Cui Boran Yang |
author_facet | Dawei Li Suzhen Lin Xiaofei Lu Xingwang Zhang Chenhui Cui Boran Yang |
author_sort | Dawei Li |
collection | DOAJ |
description | This study proposed an interpretable multi-scale infrared small object detection network (IMD-Net) design method to improve the precision of infrared small object detection and contour segmentation in complex backgrounds. To this end, a multi-scale object enhancement module was constructed, which converted artificially designed features into network structures. The network structure was used to enhance actual objects and extract shallow detail and deep semantic features of images. Next, a global object response, channel attention, and multilayer feature fusion modules were introduced, combining context and channel information and aggregated information, selected data, and decoded objects. Finally, the multiple loss constraint module was constructed, which effectively constrained the network output using multiple losses and solved the problems of high false alarms and high missed detections. Experimental results showed that the proposed network model outperformed local energy factor (LEF), self-regularized weighted sparse model (SRWS), asymmetric contextual modulation (ACM), and other state of the art methods in the intersection-over-union (IoU) and Fmeasure values by 10.8% and 11.3%, respectively. The proposed method performed best on the currently available datasets, achieving accurate detection and effective segmentation of dim and small objects in various infrared complex background images. |
first_indexed | 2024-03-08T04:52:15Z |
format | Article |
id | doaj.art-0a5177c39d324442a7d8e2e053dda1dd |
institution | Directory Open Access Journal |
issn | 1551-0018 |
language | English |
last_indexed | 2024-03-08T04:52:15Z |
publishDate | 2024-01-01 |
publisher | AIMS Press |
record_format | Article |
series | Mathematical Biosciences and Engineering |
spelling | doaj.art-0a5177c39d324442a7d8e2e053dda1dd2024-02-08T00:53:06ZengAIMS PressMathematical Biosciences and Engineering1551-00182024-01-012111712173710.3934/mbe.2024074IMD-Net: Interpretable multi-scale detection network for infrared dim and small objectsDawei Li 0Suzhen Lin1Xiaofei Lu 2Xingwang Zhang 3Chenhui Cui 4Boran Yang51. College of Electricity and Control Engineering, North University of China, Taiyuan 030051, China2. College of Data Science and Technology, North University of China, Taiyuan 030051, China3. Jiuquan Satellite Launch Center, Dongfeng Frame, Jiuquan 735000, China1. College of Electricity and Control Engineering, North University of China, Taiyuan 030051, China2. College of Data Science and Technology, North University of China, Taiyuan 030051, China2. College of Data Science and Technology, North University of China, Taiyuan 030051, ChinaThis study proposed an interpretable multi-scale infrared small object detection network (IMD-Net) design method to improve the precision of infrared small object detection and contour segmentation in complex backgrounds. To this end, a multi-scale object enhancement module was constructed, which converted artificially designed features into network structures. The network structure was used to enhance actual objects and extract shallow detail and deep semantic features of images. Next, a global object response, channel attention, and multilayer feature fusion modules were introduced, combining context and channel information and aggregated information, selected data, and decoded objects. Finally, the multiple loss constraint module was constructed, which effectively constrained the network output using multiple losses and solved the problems of high false alarms and high missed detections. Experimental results showed that the proposed network model outperformed local energy factor (LEF), self-regularized weighted sparse model (SRWS), asymmetric contextual modulation (ACM), and other state of the art methods in the intersection-over-union (IoU) and Fmeasure values by 10.8% and 11.3%, respectively. The proposed method performed best on the currently available datasets, achieving accurate detection and effective segmentation of dim and small objects in various infrared complex background images.https://www.aimspress.com/article/doi/10.3934/mbe.2024074?viewType=HTMLmulti-scale object enhancement moduleglobal object response modulemultilayer feature fusion modulemultiple loss constraint moduledim and small object detection |
spellingShingle | Dawei Li Suzhen Lin Xiaofei Lu Xingwang Zhang Chenhui Cui Boran Yang IMD-Net: Interpretable multi-scale detection network for infrared dim and small objects Mathematical Biosciences and Engineering multi-scale object enhancement module global object response module multilayer feature fusion module multiple loss constraint module dim and small object detection |
title | IMD-Net: Interpretable multi-scale detection network for infrared dim and small objects |
title_full | IMD-Net: Interpretable multi-scale detection network for infrared dim and small objects |
title_fullStr | IMD-Net: Interpretable multi-scale detection network for infrared dim and small objects |
title_full_unstemmed | IMD-Net: Interpretable multi-scale detection network for infrared dim and small objects |
title_short | IMD-Net: Interpretable multi-scale detection network for infrared dim and small objects |
title_sort | imd net interpretable multi scale detection network for infrared dim and small objects |
topic | multi-scale object enhancement module global object response module multilayer feature fusion module multiple loss constraint module dim and small object detection |
url | https://www.aimspress.com/article/doi/10.3934/mbe.2024074?viewType=HTML |
work_keys_str_mv | AT daweili imdnetinterpretablemultiscaledetectionnetworkforinfrareddimandsmallobjects AT suzhenlin imdnetinterpretablemultiscaledetectionnetworkforinfrareddimandsmallobjects AT xiaofeilu imdnetinterpretablemultiscaledetectionnetworkforinfrareddimandsmallobjects AT xingwangzhang imdnetinterpretablemultiscaledetectionnetworkforinfrareddimandsmallobjects AT chenhuicui imdnetinterpretablemultiscaledetectionnetworkforinfrareddimandsmallobjects AT boranyang imdnetinterpretablemultiscaledetectionnetworkforinfrareddimandsmallobjects |