SFFNet: Shallow Feature Fusion Network Based on Detection Framework for Infrared Small Target Detection

Infrared small target detection (IRSTD) is the process of recognizing and distinguishing small targets from infrared images that are obstructed by crowded backgrounds. This technique is used in various areas, including ground monitoring, flight navigation, and so on. However, due to complex backgrou...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhihui Yu, Nian Pan, Jin Zhou
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/22/4160
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850226268544434176
author Zhihui Yu
Nian Pan
Jin Zhou
author_facet Zhihui Yu
Nian Pan
Jin Zhou
author_sort Zhihui Yu
collection DOAJ
description Infrared small target detection (IRSTD) is the process of recognizing and distinguishing small targets from infrared images that are obstructed by crowded backgrounds. This technique is used in various areas, including ground monitoring, flight navigation, and so on. However, due to complex backgrounds and the loss of information in deep networks, infrared small target detection remains a difficult undertaking. To solve the above problems, we present a shallow feature fusion network (SFFNet) based on detection framework. Specifically, we design the shallow-layer-guided feature enhancement (SLGFE) module, which guides multi-scale feature fusion with shallow layer information, effectively mitigating the loss of information in deep networks. Then, we design the visual-Mamba-based global information extension (VMamba-GIE) module, which leverages a multi-branch structure combining the capability of convolutional layers to extract features in local space with the advantages of state space models in the exploration of long-distance information. The design significantly extends the network’s capacity to acquire global contextual information, enhancing its capability to handle complex backgrounds. And through the effective fusion of the SLGFE and VMamba-GIE modules, the exorbitant computation brought by the SLGFE module is substantially reduced. The experimental results on two publicly available infrared small target datasets demonstrate that the SFFNet surpasses other state-of-the-art algorithms.
format Article
id doaj-art-2d32158d14a44c1baa8a22e76ed2801d
institution OA Journals
issn 2072-4292
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-2d32158d14a44c1baa8a22e76ed2801d2025-08-20T02:05:07ZengMDPI AGRemote Sensing2072-42922024-11-011622416010.3390/rs16224160SFFNet: Shallow Feature Fusion Network Based on Detection Framework for Infrared Small Target DetectionZhihui Yu0Nian Pan1Jin Zhou2National Laboratory on Adaptive Optics, Chengdu 610209, ChinaNational Laboratory on Adaptive Optics, Chengdu 610209, ChinaNational Laboratory on Adaptive Optics, Chengdu 610209, ChinaInfrared small target detection (IRSTD) is the process of recognizing and distinguishing small targets from infrared images that are obstructed by crowded backgrounds. This technique is used in various areas, including ground monitoring, flight navigation, and so on. However, due to complex backgrounds and the loss of information in deep networks, infrared small target detection remains a difficult undertaking. To solve the above problems, we present a shallow feature fusion network (SFFNet) based on detection framework. Specifically, we design the shallow-layer-guided feature enhancement (SLGFE) module, which guides multi-scale feature fusion with shallow layer information, effectively mitigating the loss of information in deep networks. Then, we design the visual-Mamba-based global information extension (VMamba-GIE) module, which leverages a multi-branch structure combining the capability of convolutional layers to extract features in local space with the advantages of state space models in the exploration of long-distance information. The design significantly extends the network’s capacity to acquire global contextual information, enhancing its capability to handle complex backgrounds. And through the effective fusion of the SLGFE and VMamba-GIE modules, the exorbitant computation brought by the SLGFE module is substantially reduced. The experimental results on two publicly available infrared small target datasets demonstrate that the SFFNet surpasses other state-of-the-art algorithms.https://www.mdpi.com/2072-4292/16/22/4160infrared small target detectionmultiscale features fusionstate space modelsmambadetection framework
spellingShingle Zhihui Yu
Nian Pan
Jin Zhou
SFFNet: Shallow Feature Fusion Network Based on Detection Framework for Infrared Small Target Detection
Remote Sensing
infrared small target detection
multiscale features fusion
state space models
mamba
detection framework
title SFFNet: Shallow Feature Fusion Network Based on Detection Framework for Infrared Small Target Detection
title_full SFFNet: Shallow Feature Fusion Network Based on Detection Framework for Infrared Small Target Detection
title_fullStr SFFNet: Shallow Feature Fusion Network Based on Detection Framework for Infrared Small Target Detection
title_full_unstemmed SFFNet: Shallow Feature Fusion Network Based on Detection Framework for Infrared Small Target Detection
title_short SFFNet: Shallow Feature Fusion Network Based on Detection Framework for Infrared Small Target Detection
title_sort sffnet shallow feature fusion network based on detection framework for infrared small target detection
topic infrared small target detection
multiscale features fusion
state space models
mamba
detection framework
url https://www.mdpi.com/2072-4292/16/22/4160
work_keys_str_mv AT zhihuiyu sffnetshallowfeaturefusionnetworkbasedondetectionframeworkforinfraredsmalltargetdetection
AT nianpan sffnetshallowfeaturefusionnetworkbasedondetectionframeworkforinfraredsmalltargetdetection
AT jinzhou sffnetshallowfeaturefusionnetworkbasedondetectionframeworkforinfraredsmalltargetdetection