Temporal Point-Supervised Signal Reconstruction: A Human-Annotation-Free Framework for Weak Moving Target Detection

TL;DR

This paper introduces a novel weak moving target detection framework that leverages temporal signal modeling and a deep network to detect targets without manual annotations, achieving high accuracy and real-time speed.

Contribution

The proposed TPS framework reformulates detection as a temporal signal reconstruction problem and introduces TSRNet with DMSAttention for robust, annotation-free weak target detection.

Findings

Outperforms state-of-the-art methods on low-SNR datasets

Operates at over 1000 FPS for real-time applications

Requires no manual annotations for training

Abstract

In low-altitude surveillance and early warning systems, detecting weak moving targets remains a significant challenge due to low signal energy, small spatial extent, and complex background clutter. Existing methods struggle with extracting robust features and suffer from the lack of reliable annotations. To address these limitations, we propose a novel Temporal Point-Supervised (TPS) framework that enables high-performance detection of weak targets without any manual annotations.Instead of conventional frame-based detection, our framework reformulates the task as a pixel-wise temporal signal modeling problem, where weak targets manifest as short-duration pulse-like responses. A Temporal Signal Reconstruction Network (TSRNet) is developed under the TPS paradigm to reconstruct these transient signals.TSRNet adopts an encoder-decoder architecture and integrates a Dynamic Multi-Scale Attention (DMSAttention) module to enhance its sensitivity to diverse temporal patterns. Additionally, a graph-based trajectory mining strategy is employed to suppress false alarms and ensure temporal consistency.Extensive experiments on a purpose-built low-SNR dataset demonstrate that our framework outperforms state-of-the-art methods while requiring no human annotations. It achieves strong detection performance and operates at over 1000 FPS, underscoring its potential for real-time deployment in practical scenarios.