2006
DOI: 10.1109/lgrs.2005.861735
|View full text |Cite
|
Sign up to set email alerts
|

Seed Point Selection Method for Triangle Constrained Image Matching Propagation

Abstract: In order to select proper seed points for triangle constrained image-matching propagation, this letter analyzes the affects of different numbers and different distributions of seed points on the image-matching results. The concept of distribution quality is introduced to quantify the distribution of seed points. An intensive experimental analysis is illustrated using two different stereo aerial images and, based on the experimental results, a seed point selection strategy for triangle constrained image-matchin… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
32
0

Year Published

2007
2007
2019
2019

Publication Types

Select...
8
1

Relationship

0
9

Authors

Journals

citations
Cited by 54 publications
(32 citation statements)
references
References 4 publications
0
32
0
Order By: Relevance
“…In order to select the n_cell i corner points among the N i available corner points in each cell, the multiplication of the Harris measure by the information entropy of corners is used as the ranking criteria. Information entropy, which has a strong relationship with the correct matching probability (Zhu et al, 2006), is calculated in the surrounding circular region of each corner point with a radius of r = 7 pixels. In cases where it is not possible to select the required n_cell i corners in a grid cell, the lack of corners is compensated by a proportional increase in the number of features assigned to other cells.…”
Section: Methodology Of the Proposed Approachmentioning
confidence: 99%
“…In order to select the n_cell i corner points among the N i available corner points in each cell, the multiplication of the Harris measure by the information entropy of corners is used as the ranking criteria. Information entropy, which has a strong relationship with the correct matching probability (Zhu et al, 2006), is calculated in the surrounding circular region of each corner point with a radius of r = 7 pixels. In cases where it is not possible to select the required n_cell i corners in a grid cell, the lack of corners is compensated by a proportional increase in the number of features assigned to other cells.…”
Section: Methodology Of the Proposed Approachmentioning
confidence: 99%
“…However, it can be performed before pairwise matching begins in practical applications such as the landmark-based navigation [23,24]. In these applications, a detailed understanding of the environments is usually required for selecting a small number of features.…”
Section: Computational Complexitymentioning
confidence: 99%
“…Zhu [22] indicated that the probability of correct matching and information content enjoy strong correlation. This means that the probability of correct matching increases with increasing information entropy.…”
Section: Piecewise Correction With Optimized Cps Based On Distribumentioning
confidence: 99%