English

Learning Knowledge-Rich Sequential Model for Planar Homography Estimation in Aerial Video

Computer Vision and Pattern Recognition 2023-04-07 v1

Abstract

This paper presents an unsupervised approach that leverages raw aerial videos to learn to estimate planar homographic transformation between consecutive video frames. Previous learning-based estimators work on pairs of images to estimate their planar homographic transformations but suffer from severe over-fitting issues, especially when applying over aerial videos. To address this concern, we develop a sequential estimator that directly processes a sequence of video frames and estimates their pairwise planar homographic transformations in batches. We also incorporate a set of spatial-temporal knowledge to regularize the learning of such a sequence-to-sequence model. We collect a set of challenging aerial videos and compare the proposed method to the alternative algorithms. Empirical studies suggest that our sequential model achieves significant improvement over alternative image-based methods and the knowledge-rich regularization further boosts our system performance. Our codes and dataset could be found at https://github.com/Paul-LiPu/DeepVideoHomography

Keywords

Cite

@article{arxiv.2304.02715,
  title  = {Learning Knowledge-Rich Sequential Model for Planar Homography Estimation in Aerial Video},
  author = {Pu Li and Xiaobai Liu},
  journal= {arXiv preprint arXiv:2304.02715},
  year   = {2023}
}

Comments

Accepted by 2020 25th International Conference on Pattern Recognition (ICPR) 2021

R2 v1 2026-06-28T09:51:45.642Z