Procedings of the British Machine Vision Conference 2003 2003
DOI: 10.5244/c.17.15
|View full text |Cite
|
Sign up to set email alerts
|

Dense matching using correlation: new measures that are robust near occlusions

Abstract: In the context of computer vision, matching can be done using correlation measures. This paper presents the classification of fifty measures into five families. In addition, eighteen new measures based on robust statistics are presented to deal with the problem of occlusions. An evaluation protocol is proposed and the results show that robust measures (one of the five families), including the new measures, give the best results near occlusions.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
24
0
4

Year Published

2007
2007
2017
2017

Publication Types

Select...
3
2
2

Relationship

0
7

Authors

Journals

citations
Cited by 25 publications
(28 citation statements)
references
References 15 publications
0
24
0
4
Order By: Relevance
“…A plethora of such distance measures has been suggested, often with specific applications and specific types of invariance in mind. An extensive review and classification (including a performance comparison) is presented in [61,62]; partial reviews and performance comparisons are provided in [60,[63][64][65][66][67]. Chambon and Crouzil [62] provide a helpful classification of distance measures: cross correlation-based methods ("cross"), classical statistics-based measures ("classical", including distance metrics), derivative-based measures ("derivative", often based on intensity gradients), non-parametric measures ("non-parametric", including rank-based measures), and robust measures ("robust", including median-based measures).…”
Section: Illumination Invariance and Distance Measuresmentioning
confidence: 99%
See 1 more Smart Citation
“…A plethora of such distance measures has been suggested, often with specific applications and specific types of invariance in mind. An extensive review and classification (including a performance comparison) is presented in [61,62]; partial reviews and performance comparisons are provided in [60,[63][64][65][66][67]. Chambon and Crouzil [62] provide a helpful classification of distance measures: cross correlation-based methods ("cross"), classical statistics-based measures ("classical", including distance metrics), derivative-based measures ("derivative", often based on intensity gradients), non-parametric measures ("non-parametric", including rank-based measures), and robust measures ("robust", including median-based measures).…”
Section: Illumination Invariance and Distance Measuresmentioning
confidence: 99%
“…image distance functions or matching costs) are directly computed on intensities or their derivatives (reviews: [60][61][62][63]). Different types of invariance (or at least tolerance), among them invariance against illumination changes, have to be achieved by the distance measure itself.…”
Section: Illumination Invariance and Distance Measuresmentioning
confidence: 99%
“…또한 정합기법에 따라서는 명암의 세기와 특징을 고려한 기법, 변형모델을 고려한 기법, 영상의 활용 영역을 고려한 기법, 방법의 개수를 고려한 기법 등이 있다 [3,4]. 먼저 명암의 세기와 특징을 고려한 기 법에는 다시 특징기반 접근(feature-based approach)법 과 영상기반 접근(intensity(area)-based approach)법으 로 나눌 수 있다 [4][5][6][7][8][9][10][11]. 전자는 정합에 명암을 고려하 지 않는 방법으로 영상에서 명암도의 특성이 다르기 때 문에 공통적 특성을 제공하는 특징을 찾아 정합에 이용 하는 방법이다.…”
unclassified
“…특징으로는 영상의 특징점, 외곽선 특 징, 에지(edge), 그리고 기울기 등의 정보가 이용되며, 특징에 따라 정합성능이 달라진다. 여기에는 국부적 특 징들을 이용하는 Hough 변환 일반화(generalizing Hough transform : GHT)법과 기하학적 특징들을 이용 하는 색인접근(indexing approach)법 등이 있다 [3][4][5][6]. 또한 후자는 영상의 전체 명암을 기반으로 한 방법으로 대상 영상 상호간의 명암 관계가 매우 복잡하거나 상관 관계를 잘 알 수가 없으면 정합의 정확성을 보장하지 못하는 제약이 있다.…”
unclassified
See 1 more Smart Citation