Locality Sensitive Hashing based deepmatching for optical flow estimation

Chen Wang; Zongqing Lu; Qingmin Liao; Danyi Li

ICASSP 2017accepted0 citations

Locality Sensitive Hashing based deepmatching for optical flow estimation

Chen Wang, Zongqing Lu, Qingmin Liao, Danyi Li

Abstract

DeepMatching (DM) is one of the state-of-art matching algorithms to compute quasi-dense correspondences between images. Recent optical flow methods use DeepMatching to find initial image correspondences and achieves outstanding performance. However, the key building block of DeepMatching, the correlation map computation, is time-consuming. In this paper, we propose a new algorithm, LSHDM, which addresses the problem by employing Locality Sensitive Hashing (LSH) to DeepMatching. The computational complexity is greatly reduced for the correlation map computation step. Experiments show that image matching can be accelerated by our approach in ten times or more compared to DeepMatching, while retaining comparable accuracy for optical flow estimation.

BibTeX

@inproceedings{icassp2017_localitysensitiv,
  title = {Locality Sensitive Hashing based deepmatching for optical flow estimation},
  author = {Chen Wang and Zongqing Lu and Qingmin Liao and Danyi Li},
  booktitle = {ICASSP 2017},
  year = {2017}
}