Learn Temporal Consistency For Robust Satellite Video Detector

2026-06-13

AI Summary

Existing satellite video object detection methods struggle to robustly achieve accurate and consistent detection of oriented and fine-grained moving objects. To address this challenge, this work proposes a detection framework based on Temporal Consistency Learning (TCL), which effectively integrates multi-frame temporal context through three key components: Temporal and Fine-grained feature Aggregation (TFA), Structural Encoding (SE), and Temporal Consistency Constraint (TCC). This approach enables, for the first time, high-precision fine-grained oriented object detection in satellite videos and can be seamlessly integrated with mainstream image detectors. Evaluated on the SAT-MTB dataset, the method achieves a 47.7% mAP, surpassing the baseline by 4.8% and setting a new state-of-the-art performance for this task.

Abstract

Satellite video object detection (SVOD) for oriented and fine-grained objects plays an important role in satellite applications. Most existing SVOD methods only focus on one or a few coarse-grained categories of moving objects and represent objects with horizontal bounding boxes. They have difficulty extracting complete, accurate, and consistent information about objects in whole satellite videos. In this paper, we propose a satellite video object detection framework based on Temporal Consistency Learning (TCL). TCL adeptly detects oriented and fine-grained objects by leveraging the rich temporal contexts within satellite videos. The framework integrates three key modules: temporal and fine-grained feature aggregation (TFA), structure encoding (SE), and temporal consistency constraint (TCC). TFA and TCC modules facilitate consistent representation learning across frames, while the SE module encodes both appearance and structural information for precise fine-grained recognition. Experimental results on the SAT-MTB benchmark dataset demonstrate TCL's superior performance, achieving a new state-of-the-art oriented and fine-grained detection accuracy of 47.7% mAP--a 4.8% improvement over the baseline. Furthermore, our TCL framework readily accommodates existing image-based detectors, leading to enhanced detection accuracies.

Problem

• satellite video object detection
• temporal consistency
• oriented objects
• fine-grained recognition

Innovation

• Temporal Consistency Learning
• Satellite Video Object Detection
• Fine-grained Recognition
• Oriented Object Detection
• Temporal Feature Aggregation