Infrared Small Target Detection in Satellite Videos: A New Dataset and A Novel Recurrent Feature Refinement Framework

TL;DR

This paper introduces a large-scale satellite video dataset for infrared small target detection and proposes a recurrent feature refinement framework that enhances detection accuracy by exploiting temporal dependencies and motion compensation.

Contribution

The paper provides a new semi-simulated dataset for satellite video analysis and develops a novel RFR framework with modules for feature alignment and refinement, improving detection performance.

Findings

RFR outperforms existing methods in experiments.

The dataset facilitates algorithm development for satellite videos.

Modules like PDA and TSFM improve feature alignment and detection accuracy.

Abstract

Multi-frame infrared small target (MIRST) detection in satellite videos is a long-standing, fundamental yet challenging task for decades, and the challenges can be summarized as: First, extremely small target size, highly complex clutters & noises, various satellite motions result in limited feature representation, high false alarms, and difficult motion analyses. Second, the lack of large-scale public available MIRST dataset in satellite videos greatly hinders the algorithm development. To address the aforementioned challenges, in this paper, we first build a large-scale dataset for MIRST detection in satellite videos (namely IRSatVideo-LEO), and then develop a recurrent feature refinement (RFR) framework as the baseline method. Specifically, IRSatVideo-LEO is a semi-simulated dataset with synthesized satellite motion, target appearance, trajectory and intensity, which can provide a standard toolbox for satellite video generation and a reliable evaluation platform to facilitate the algorithm development. For baseline method, RFR is proposed to be equipped with existing powerful CNN-based methods for long-term temporal dependency exploitation and integrated motion compensation & MIRST detection. Specifically, a pyramid deformable alignment (PDA) module and a temporal-spatial-frequency modulation (TSFM) module are proposed to achieve effective and efficient feature alignment, propagation, aggregation and refinement. Extensive experiments have been conducted to demonstrate the effectiveness and superiority of our scheme. The comparative results show that ResUNet equipped with RFR outperforms the state-of-the-art MIRST detection methods. Dataset and code are released at https://github.com/XinyiYing/RFR.