Highly Efficient and Unsupervised Framework for Moving Object Detection in Satellite Videos

TL;DR

This paper introduces a highly efficient unsupervised framework for moving object detection in satellite videos, leveraging pseudo labels and a sparse convolutional network to improve speed and accuracy without manual annotations.

Contribution

The authors propose a novel unsupervised detection framework that evolves pseudo labels and employs a sparse, anchor-free network for efficient satellite video analysis.

Findings

Processes 98.8 frames per second on 1024x1024 images.

Achieves state-of-the-art detection performance.

Reduces annotation and computational costs.

Abstract

Moving object detection in satellite videos (SVMOD) is a challenging task due to the extremely dim and small target characteristics. Current learning-based methods extract spatio-temporal information from multi-frame dense representation with labor-intensive manual labels to tackle SVMOD, which needs high annotation costs and contains tremendous computational redundancy due to the severe imbalance between foreground and background regions. In this paper, we propose a highly efficient unsupervised framework for SVMOD. Specifically, we propose a generic unsupervised framework for SVMOD, in which pseudo labels generated by a traditional method can evolve with the training process to promote detection performance. Furthermore, we propose a highly efficient and effective sparse convolutional anchor-free detection network by sampling the dense multi-frame image form into a sparse spatio-temporal point cloud representation and skipping the redundant computation on background regions. Coping these two designs, we can achieve both high efficiency (label and computation efficiency) and effectiveness. Extensive experiments demonstrate that our method can not only process 98.8 frames per second on 1024x1024 images but also achieve state-of-the-art performance. The relabeled dataset and code are available at https://github.com/ChaoXiao12/Moving-object-detection-in-satellite-videos-HiEUM.