What to Select: Pursuing Consistent Motion Segmentation from Multiple Geometric Models

Authors

  • Yangbangyan Jiang Institute of Information Engineering, Chinese Academy of Sciences University of Chinese Academy of Sciences
  • Qianqian Xu Institute of Computing Technology, Chinese Academy of Sciences
  • Ke Ma University of Chinese Academy of Sciences
  • Zhiyong Yang Institute of Information Engineering, Chinese Academy of Sciences University of Chinese Academy of Sciences
  • Xiaochun Cao Institute of Information Engineering, Chinese Academy of Sciences University of Chinese Academy of Sciences Peng Cheng Laboratory
  • Qingming Huang University of Chinese Academy of Sciences Institute of Computing Technology, Chinese Academy of Sciences Peng Cheng Laboratory

Keywords:

Applications

Abstract

Motion segmentation aims at separating motions of different moving objects in a video sequence. Facing the complicated real-world scenes, recent studies reveal that combining multiple geometric models would be a more effective way than just employing a single one. This motivates a new wave of model-fusion based motion segmentation methods. However, the vast majority of models of this kind merely seek consensus in spectral embeddings. We argue that a simple consensus might be insufficient to filter out the harmful information which is either unreliable or semantically unrelated to the segmentation task. Therefore, how to automatically select valuable patterns across multiple models should be regarded as a key challenge here. In this paper, we present a novel geometric-model-fusion framework for motion segmentation, which targets at constructing a consistent affinity matrix across all the geometric models. Specifically, it incorporates the structural information shared by affinity matrices to select those semantically consistent entries. Meanwhile, a multiplicative decomposition scheme is adopted to ensure structural consistency among multiple affinities. To solve this problem, an alternative optimization scheme is proposed, together with a proof of its global convergence. Experiments on four real-world benchmarks show the superiority of the proposed method.

Downloads

Published

2021-05-18

How to Cite

Jiang, Y., Xu, Q., Ma, K., Yang, Z., Cao, X., & Huang, Q. (2021). What to Select: Pursuing Consistent Motion Segmentation from Multiple Geometric Models. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 1708-1716. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16264

Issue

Section

AAAI Technical Track on Computer Vision I