Spatio-Temporal Context Learning with Temporal Difference Convolution for Moving Infrared Small Target Detection

2025-11-11

AI Summary

In infrared small target detection (IRSTD), low signal-to-noise ratio and strong clutter background impede effective spatiotemporal feature modeling. To address this, we propose TDCNet—a novel network integrating temporal differencing and 3D convolution. Its key contributions are: (1) a temporally differenced convolution (TDC) reparameterization module that explicitly captures multi-scale motion cues across frames; and (2) a TDC-guided spatiotemporal attention mechanism that jointly suppresses background interference and enhances motion-sensitive feature responses. TDCNet adopts a parallel architecture combining TDC and 3D convolution, further enhanced by reparameterization and cross-modal attention for joint and dynamic spatiotemporal feature learning. Extensive experiments on IRSTD-UAV and multiple public infrared datasets demonstrate that our method achieves state-of-the-art detection accuracy and robustness, surpassing existing approaches and attaining internationally leading performance.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs

Abstract

Moving infrared small target detection (IRSTD) plays a critical role in practical applications, such as surveillance of unmanned aerial vehicles (UAVs) and UAV-based search system. Moving IRSTD still remains highly challenging due to weak target features and complex background interference. Accurate spatio-temporal feature modeling is crucial for moving target detection, typically achieved through either temporal differences or spatio-temporal (3D) convolutions. Temporal difference can explicitly leverage motion cues but exhibits limited capability in extracting spatial features, whereas 3D convolution effectively represents spatio-temporal features yet lacks explicit awareness of motion dynamics along the temporal dimension. In this paper, we propose a novel moving IRSTD network (TDCNet), which effectively extracts and enhances spatio-temporal features for accurate target detection. Specifically, we introduce a novel temporal difference convolution (TDC) re-parameterization module that comprises three parallel TDC blocks designed to capture contextual dependencies across different temporal ranges. Each TDC block fuses temporal difference and 3D convolution into a unified spatio-temporal convolution representation. This re-parameterized module can effectively capture multi-scale motion contextual features while suppressing pseudo-motion clutter in complex backgrounds, significantly improving detection performance. Moreover, we propose a TDC-guided spatio-temporal attention mechanism that performs cross-attention between the spatio-temporal features from the TDC-based backbone and a parallel 3D backbone. This mechanism models their global semantic dependencies to refine the current frame's features. Extensive experiments on IRSTD-UAV and public infrared datasets demonstrate that our TDCNet achieves state-of-the-art detection performance in moving target detection.

Problem

• Detecting moving infrared small targets with weak features
• Overcoming complex background interference in IRSTD
• Integrating motion cues and spatio-temporal feature representation

Innovation

• Temporal difference convolution re-parameterization module
• Multi-scale motion contextual feature capture
• TDC-guided spatio-temporal attention mechanism