Loading [a11y]/accessibility-menu.js
Multibranch Mutual-Guiding Learning for Infrared Small Target Detection | IEEE Journals & Magazine | IEEE Xplore

Multibranch Mutual-Guiding Learning for Infrared Small Target Detection


Abstract:

At present, many infrared target detection approaches focus on designing modules that address the two key characteristics of targets: their weak signals and small size. H...Show More

Abstract:

At present, many infrared target detection approaches focus on designing modules that address the two key characteristics of targets: their weak signals and small size. However, these approaches often fail to fully leverage guided learning for weak and small target content, resulting in suboptimal detection performance, particularly in terms of shape preservation and target positioning. To tackle this challenge, this article proposes a multibranch mutual-guiding learning network (MMLNet) that enhances the accuracy of infrared target detection, even in the absence of clear morphological and textural features in images. The method consists of three branches: edge, positioning, and detection, each of which is designed with a specialized module from a unique perspective. In the detection branch, we introduce a multidimensional lossless encoder optimized through a downsampling strategy and multilevel feature fusion to mitigate feature loss in small targets. In the positioning branch, a target positioning strategy is proposed to explicitly identify candidate targets from the image by means of a learnable multikernel pattern. In the edge branch, a simple architecture is adopted to enhance the ability of the model to preserve the target shape. To effectively utilize the knowledge of different branches, a mutual-guiding fusion module is developed to adjust information within and between branches. The manner adaptively utilizes the specific knowledge from each input branch. The experimental results demonstrate that the proposed method achieves comparable performance, and the visualization results show the advantages of our method in shape preservation and positioning of the targets. Our code is publicly available at https://github.com/qianngli/MMLNet.
Article Sequence Number: 5605710
Date of Publication: 07 January 2025

ISSN Information:

Funding Agency:


I. Introduction

Infrared target detection is a crucial task in image processing and plays an essential role in various fields, including military, security, and autonomous driving. Unlike visible imaging, infrared imaging technology effectively captures target information in challenging environmental conditions, such as low light. This capability makes infrared target detection particularly valuable for night reconnaissance and concealed scenarios. Consequently, research in infrared target detection holds significant value for applications.

Contact IEEE to Subscribe

References

References is not available for this document.