MM-IRSTD: Conv Self-Attention-Based Multi-Modal Small and Dim Target Detection in Infrared Dual-Band Images

MM-IRSTD: Conv Self-Attention-Based Multi-Modal Small and Dim Target Detection in Infrared Dual-Band Images

Infrared multi-band small and dim target detection is an important research direction in the fields of modern remote sensing and military surveillance. However, achieving high-precision detection remains challenging due to the small scale, low contrast of small and dim targets, and their susceptibil...

Full description

Saved in:
Bibliographic Details
Published in:Remote sensing (Basel, Switzerland) Vol. 16; no. 21; p. 3937
Main Authors: Yang, Junyan, Ye, Zhihui, Lin, Jian, Chen, Dongfang, Du, Lingbian, Li, Shaoyi
Format: Journal Article
Language:English
Published: Basel MDPI AG 01-11-2024
Subjects:
Ablation
Accuracy
attention mechanism
Complexity
Deep learning
Distillation
dual-band infrared
Feature extraction
feature fusion
Image contrast
Image enhancement
Infrared imagery
Learning strategies
Light
lightweight network
Methods
Modules
Multilayer perceptrons
Neural networks
Performance enhancement
Remote sensing
Signal to noise ratio
Similarity
Sobel
Spatial discrimination
Target detection
Target recognition
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Infrared multi-band small and dim target detection is an important research direction in the fields of modern remote sensing and military surveillance. However, achieving high-precision detection remains challenging due to the small scale, low contrast of small and dim targets, and their susceptibility to complex background interference. This paper innovatively proposes a dual-band infrared small and dim target detection method (MM-IRSTD). In this framework, we integrate a convolutional self-attention mechanism module and a self-distillation mechanism to achieve end-to-end dual-band infrared small and dim target detection. The Conv-Based Self-Attention module consists of a convolutional self-attention mechanism and a multilayer perceptron, effectively extracting and integrating input features, thereby enhancing the performance and expressive capability of the model. Additionally, this module incorporates a dynamic weight mechanism to achieve adaptive feature fusion, significantly reducing computational complexity and enhancing the model’s global perception capability. During model training, we use a spatial and channel similarity self-distillation mechanism to drive model updates, addressing the similarity discrepancy between long-wave and mid-wave image features extracted through deep learning, thus improving the model’s performance and generalization capability. Furthermore, to better learn and detect edge features in images, this paper designs an edge extraction method based on Sobel. Finally, comparative experiments and ablation studies validate the advancement and effectiveness of our proposed method.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs16213937