2014 22nd International Conference on Pattern Recognition 2014
DOI: 10.1109/icpr.2014.374
|View full text |Cite
|
Sign up to set email alerts
|

Accurate Camera Pose Estimation for KinectFusion Based on Line Segment Matching by LEHF

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
7
0

Year Published

2015
2015
2019
2019

Publication Types

Select...
3
3

Relationship

1
5

Authors

Journals

citations
Cited by 11 publications
(7 citation statements)
references
References 14 publications
0
7
0
Order By: Relevance
“…Therefore, the performance of point-feature-based algorithms in Kinect-based applications is not fully satisfactory. 23,24 Line-feature based or planar-feature based algorithms performed well in structured environments. However, they are not competent in unstructured natural scenes because it is extremely difficult to extract robust line or planar features in these scenes.…”
Section: Introductionmentioning
confidence: 96%
“…Therefore, the performance of point-feature-based algorithms in Kinect-based applications is not fully satisfactory. 23,24 Line-feature based or planar-feature based algorithms performed well in structured environments. However, they are not competent in unstructured natural scenes because it is extremely difficult to extract robust line or planar features in these scenes.…”
Section: Introductionmentioning
confidence: 96%
“…Raposo [8] proposed several modifications to the work of Herrera [4] that improved runtime using less images. Nakayama [9] propose an alignment method which is based on line segments to improve the camera pose accuracy. However, all these methods are either not robust, or produce a result which is not accurate enough for real applications, or require relatively complex processing procedure.…”
Section: Introductionmentioning
confidence: 99%
“…However, if the descriptor distances from the two directions are similar, mismatching is occurred. To improve the matching performance, we proposed Directed LEHF [9]. We adopt Directed LEHF as a line segment feature descriptor.…”
Section: Matching 2d Line Segments By Directed Lehfmentioning
confidence: 99%
“…However, there is a fear that LC i contains some mismatches. We use a method which solves the PnL problem with an algorithm like RANSAC explained in [9], and estimate the camera pose RT i cw . This method mainly use RPnL [13] for solving the PnL problem.…”
Section: Solution For the Pnl Problemmentioning
confidence: 99%
See 1 more Smart Citation