Procedings of the British Machine Vision Conference 2006 2006
DOI: 10.5244/c.20.43
|View full text |Cite
|
Sign up to set email alerts
|

Detecting Half-Occlusion with a Fast Region-Based Fusion Procedure

Abstract: This paper presents a novel region-based approach for detecting occlusion between two consecutive frames. Based on a generalization of Marr and Poggio's uniqueness assumption, the explicit goal of our method is to reduce the number of false positives while optimizing the hit rate. To do so, our method relies on a fusion procedure that blends together two segmentation maps: one pre-estimated occlusion binary map and one color segmentation map. While the occlusion map is obtained after a simple thresholding proc… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
5
0

Year Published

2007
2007
2013
2013

Publication Types

Select...
6
3

Relationship

0
9

Authors

Journals

citations
Cited by 10 publications
(5 citation statements)
references
References 25 publications
0
5
0
Order By: Relevance
“…A pixel with no match is then considered as occluded. Jodoin et al [20] built on this principle to make it more robust to noise. Using a method similar to Ince and Konrad [18], they generated a coarse occlusion map where a pixel is marked occluded if fewer than two pixels' intensities in its neighborhood are within a certain Euclidean distance.…”
Section: Related Workmentioning
confidence: 99%
“…A pixel with no match is then considered as occluded. Jodoin et al [20] built on this principle to make it more robust to noise. Using a method similar to Ince and Konrad [18], they generated a coarse occlusion map where a pixel is marked occluded if fewer than two pixels' intensities in its neighborhood are within a certain Euclidean distance.…”
Section: Related Workmentioning
confidence: 99%
“…A region-based approach was presented by Jodoin et al [36], who first segment the images and classify segments as occluded or not according to the density of matched pixels in them. Ideally, occlusion detection should not be performed locally since occlusion is a result of long range interaction between remote surfaces.…”
Section: Related Workmentioning
confidence: 99%
“…where i (p) is close to zero when there is no occlusion and high when pixel p is occluded in image i. There have been several attempts to improve the robustness of this method [11,12]. However, the original LRC is still the most popular approach [2,5,13,14].…”
Section: Related Workmentioning
confidence: 99%