2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020
DOI: 10.1109/cvpr42600.2020.00498
|View full text |Cite
|
Sign up to set email alerts
|

Information-Driven Direct RGB-D Odometry

Abstract: This paper presents an information-theoretic approach to point selection for direct RGB-D odometry. The aim is to select only the most informative measurements, in order to reduce the optimization problem with a minimal impact in the accuracy. It is usual practice in visual odometry/SLAM to track several hundreds of points, achieving real-time performance in high-end desktop PCs. Reducing their computational footprint will facilitate the implementation of odometry and SLAM in low-end platforms such as small ro… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
30
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 29 publications
(30 citation statements)
references
References 27 publications
0
30
0
Order By: Relevance
“…So that we choose these representative systems, according to the methods and attributes of them, and enumerate their attribute in Table 1. We have also introduced 3 relatively advanced RGB-D SLAM systems, include two direct-based tracking methods: RGBDTAM [13], ID-RGBDO [14] and one indirect-based methods Plane-Edge-SLAM [18], and we have also introduced their tracking method in the survey part. Due to the lack of open source code or implementation difficulties, we did not conduct experiments and only refer to the experimental data provided in their articles.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…So that we choose these representative systems, according to the methods and attributes of them, and enumerate their attribute in Table 1. We have also introduced 3 relatively advanced RGB-D SLAM systems, include two direct-based tracking methods: RGBDTAM [13], ID-RGBDO [14] and one indirect-based methods Plane-Edge-SLAM [18], and we have also introduced their tracking method in the survey part. Due to the lack of open source code or implementation difficulties, we did not conduct experiments and only refer to the experimental data provided in their articles.…”
Section: Discussionmentioning
confidence: 99%
“…While most direct methods take as many pixels as possible to ensure the accuracy, Alejandro Fontán et al proposed ID-RGBDO in 2020 [14], which takes only 24 points for tracking and can achieve an accuracy similar to the state of the art (some times out perform it). Based on an information matrix, ID-RGBDO selects only the most informative points in the local Bundle Adjustment and pose tracking optimizations.…”
Section: ) Id-rgbdomentioning
confidence: 99%
“…Motion-based feature selection methods have been widely applied in visual SLAM [16], [25]- [27], and many of them are based on the covariance or information matrices that capture uncertainties of poses [28]. These methods formulate the feature selection as a submatrix selection problem and aim to find a subset of features with the objective to preserve the information matrix's spectral attributes.…”
Section: B Feature Selectionmentioning
confidence: 99%
“…The uncertainty so obtained has been extensively studied in photometric computer vision [11]. It has also found applicability in a wide variety of tasks, such as RGB-D SLAM [10], radial distortion model selection [42] in SFM, skeletal images selection for efficient SFM [51], height map fusion [79], 3D reconstruction [17], and camera calibration [39]. Polic et al recently make efforts [41,40] towards efficient uncertainty computation in large-scale 3D reconstruction.…”
Section: Related Workmentioning
confidence: 99%