Contour Flow: Middle-Level Motion Estimation by Combining Motion Segmentation and Contour Alignment

Huijun Di, Qingxuan Shi, Feng Lv, Ming Qin, Yao Lu; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2015, pp. 4355-4363

Abstract


Our goal is to estimate contour flow (the contour pairs with consistent point correspondence) from inconsistent contours extracted independently in two video frames. We formulate the contour flow estimation locally as a motion segmentation problem where motion patterns grouped from optical flow field are exploited for local correspondence measurement. To solve local ambiguities, contour flow estimation is further formulated globally as a contour alignment problem. We propose a novel two-staged strategy to obtain global consistent point correspondence under various contour transitions such as splitting, merging and branching. The goal of the first stage is to obtain possible accurate contour-to-contour alignments, and the second stage aims to make a consistent fusion of many partial alignments. Such a strategy can properly balance the accuracy and the consistency, which enables a middle-level motion representation to be constructed by just concatenating frame-by-frame contour flow estimation. Experiments prove the effectiveness of our method.

Related Material


[pdf]
[bibtex]
@InProceedings{Di_2015_ICCV,
author = {Di, Huijun and Shi, Qingxuan and Lv, Feng and Qin, Ming and Lu, Yao},
title = {Contour Flow: Middle-Level Motion Estimation by Combining Motion Segmentation and Contour Alignment},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2015}
}