제 목 | [11/22(목) 16:00] Multi-Scale Generalized PlaneMatch based occlusion detection and correspondence for optical flow (이민호 교수 초청) | ||||
---|---|---|---|---|---|
작성자 | 김근수 | 작성일 | 2018-11-19 | 조회수 | 1194 |
첨부파일 | |||||
1. 제 목 : Multi-Scale Generalized PlaneMatch based occlusion detection and correspondence for optical flow
2. 발 표 자 : Inchul Choi
3. 일 시 : 2018년 11월 22일(목) 16:00 ~ 17:30
4. 장 소 : 경북대학교 IT대학 1호관 318호
5. 초청교수 : 이민호 교수
6. 강사약력 : · Ph.D in Computer Science 2018 Concentrations : Machine Learning , Computer Vision,
7. 내용요약 : Despite recent advances, estimating optical flow remains a challenging problem in the presence of illumination change, large occlusions or fast movement. In this paper, we propose a novel optical flow estimation framework which can provide accurate dense correspondence and occlusion localization through a multi-scale generalized plane matching approach. In our method, we regard the scene as a collection of planes at multiple scales, and for each such plane, compensate motion in consensus to improve match quality. We estimate the square patch plane distortion using a robust plane model detection method and iteratively apply a plane matching scheme within a multi-scale framework. During the flow estimation process, our enhanced plane matching method also clearly localizes the occluded regions. In experiments on MPI-Sintel datasets, our method robustly estimated optical flow from given noisy correspondences, and also revealed the occluded regions accurately. Compared to other state-of-the-art optical ow methods, our method shows accurate occlusion localization, comparable optical ow quality, and better thin object detection.
◀ 문의처 : IT대학 전자공학부 인공두뇌연구실 이혜경 ☎ 940-8616
|
|||||
[좋아요 0 ] |