Triple-domain Feature Learning with Frequency-aware Memory Enhancement for Moving Infrared Small Target Detection

TL;DR

This paper introduces a novel triple-domain feature learning strategy with frequency-aware memory enhancement for infrared small target detection, leveraging spatio-temporal and frequency domains to improve detection accuracy.

Contribution

It is the first to explore comprehensive infrared target feature learning across spatio-temporal-frequency domains, integrating frequency-aware modules and memory enhancement.

Findings

Outperforms state-of-the-art methods on three datasets.

Effectively enhances frequency features using Fourier transform.

Captures spatial and temporal relations of targets in infrared videos.

Abstract

As a sub-field of object detection, moving infrared small target detection presents significant challenges due to tiny target sizes and low contrast against backgrounds. Currently-existing methods primarily rely on the features extracted only from spatio-temporal domain. Frequency domain has hardly been concerned yet, although it has been widely applied in image processing. To extend feature source domains and enhance feature representation, we propose a new Triple-domain Strategy (Tridos) with the frequency-aware memory enhancement on spatio-temporal domain for infrared small target detection. In this scheme, it effectively detaches and enhances frequency features by a local-global frequency-aware module with Fourier transform. Inspired by human visual system, our memory enhancement is designed to capture the spatial relations of infrared targets among video frames. Furthermore, it encodes temporal dynamics motion features via differential learning and residual enhancing. Additionally, we further design a residual compensation to reconcile possible cross-domain feature mismatches. To our best knowledge, proposed Tridos is the first work to explore infrared target feature learning comprehensively in spatio-temporal-frequency domains. The extensive experiments on three datasets (i.e., DAUB, ITSDT-15K and IRDST) validate that our triple-domain infrared feature learning scheme could often be obviously superior to state-of-the-art ones. Source codes are available at https://github.com/UESTC-nnLab/Tridos.