Fast depth edge detection and edge based RGB-D SLAM

L. Bose; A. Richards

doi:10.1109/ICRA.2016.7487265

Fast depth edge detection and edge based RGB-D SLAM

L. Bose, A. Richards

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

14 Citations (Scopus)

673 Downloads (Pure)

Abstract

This paper presents a method of occluding depth edge-detection targeted towards RGB-D video streams and explores the use of these and other edge features in RGB-D SLAM. The proposed depth edge-detection approach uses prior information obtained from the previous RGB-D video frame to determine which areas of the current depth image are likely to contain edges due to image similarity. By limiting the search for edges to these areas a significant amount of computation time is saved compared to searching the entire image. Pixels belonging to both the depth and colour edges of an RGB-D image can be back projected using the depth component to form 3D point clouds of edge points. Registration between such edge point clouds is achieved using ICP and we present a realtime RGB-D SLAM system utilizing such back projected edge features. Experimental results are presented demonstrating the performance of both the proposed depth edge-detection and SLAM system using publicly available datasets.

Original language	English
Title of host publication	2016 IEEE International Conference on Robotics and Automation (ICRA 2016)
Subtitle of host publication	Proceedings of a meeting held 16-21 May 2016, Stockholm, Sweden
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1323-1330
Number of pages	8
ISBN (Print)	9781467380270
DOIs	https://doi.org/10.1109/ICRA.2016.7487265
Publication status	Published - Aug 2016

Keywords

SLAM (robots)
edge detection
image colour analysis
iterative methods
mobile robots
robot vision
video streaming
3D point clouds
ICP
RGB-D video streams
back projected edge features
computation time
depth component
edge based RGB-D SLAM
edge features
fast depth edge detection
image similarity
publicly available datasets
Cameras
Image edge detection
Iterative closest point algorithm
Simultaneous localization and mapping
Streaming media
Three-dimensional displays

Access to Document

10.1109/ICRA.2016.7487265

Full-text PDF (accepted author manuscript)
This is the accepted author manuscript (AAM). The final published version (version of record) is available online via IEEE at https://doi.org/10.1109/ICRA.2016.7487265. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 3.2 MB

Fingerprint Dive into the research topics of 'Fast depth edge detection and edge based RGB-D SLAM'. Together they form a unique fingerprint.

Edge Based RGB-D SLAM and SLAM Based Navigation
Author: Bose, L. N., 7 Mar 2017
Supervisor: Richards, A. G. (Supervisor)
Student thesis: Doctoral Thesis › Doctor of Philosophy (PhD)

File

Cite this

@inproceedings{47255ce71a1145a489de14825ded00be,

title = "Fast depth edge detection and edge based RGB-D SLAM",

abstract = "This paper presents a method of occluding depth edge-detection targeted towards RGB-D video streams and explores the use of these and other edge features in RGB-D SLAM. The proposed depth edge-detection approach uses prior information obtained from the previous RGB-D video frame to determine which areas of the current depth image are likely to contain edges due to image similarity. By limiting the search for edges to these areas a significant amount of computation time is saved compared to searching the entire image. Pixels belonging to both the depth and colour edges of an RGB-D image can be back projected using the depth component to form 3D point clouds of edge points. Registration between such edge point clouds is achieved using ICP and we present a realtime RGB-D SLAM system utilizing such back projected edge features. Experimental results are presented demonstrating the performance of both the proposed depth edge-detection and SLAM system using publicly available datasets.",

keywords = "SLAM (robots), edge detection, image colour analysis, iterative methods, mobile robots, robot vision, video streaming, 3D point clouds, ICP, RGB-D video streams, back projected edge features, computation time, depth component, edge based RGB-D SLAM, edge features, fast depth edge detection, image similarity, publicly available datasets, Cameras, Image edge detection, Iterative closest point algorithm, Simultaneous localization and mapping, Streaming media, Three-dimensional displays",

author = "L. Bose and A. Richards",

year = "2016",

month = aug,

doi = "10.1109/ICRA.2016.7487265",

language = "English",

isbn = "9781467380270",

pages = "1323--1330",

booktitle = "2016 IEEE International Conference on Robotics and Automation (ICRA 2016)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

}

Fast depth edge detection and edge based RGB-D SLAM. / Bose, L.; Richards, A.

2016 IEEE International Conference on Robotics and Automation (ICRA 2016): Proceedings of a meeting held 16-21 May 2016, Stockholm, Sweden. Institute of Electrical and Electronics Engineers (IEEE), 2016. p. 1323-1330.

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Fast depth edge detection and edge based RGB-D SLAM

AU - Bose, L.

AU - Richards, A.

PY - 2016/8

Y1 - 2016/8

N2 - This paper presents a method of occluding depth edge-detection targeted towards RGB-D video streams and explores the use of these and other edge features in RGB-D SLAM. The proposed depth edge-detection approach uses prior information obtained from the previous RGB-D video frame to determine which areas of the current depth image are likely to contain edges due to image similarity. By limiting the search for edges to these areas a significant amount of computation time is saved compared to searching the entire image. Pixels belonging to both the depth and colour edges of an RGB-D image can be back projected using the depth component to form 3D point clouds of edge points. Registration between such edge point clouds is achieved using ICP and we present a realtime RGB-D SLAM system utilizing such back projected edge features. Experimental results are presented demonstrating the performance of both the proposed depth edge-detection and SLAM system using publicly available datasets.

AB - This paper presents a method of occluding depth edge-detection targeted towards RGB-D video streams and explores the use of these and other edge features in RGB-D SLAM. The proposed depth edge-detection approach uses prior information obtained from the previous RGB-D video frame to determine which areas of the current depth image are likely to contain edges due to image similarity. By limiting the search for edges to these areas a significant amount of computation time is saved compared to searching the entire image. Pixels belonging to both the depth and colour edges of an RGB-D image can be back projected using the depth component to form 3D point clouds of edge points. Registration between such edge point clouds is achieved using ICP and we present a realtime RGB-D SLAM system utilizing such back projected edge features. Experimental results are presented demonstrating the performance of both the proposed depth edge-detection and SLAM system using publicly available datasets.

KW - SLAM (robots)

KW - edge detection

KW - image colour analysis

KW - iterative methods

KW - mobile robots

KW - robot vision

KW - video streaming

KW - 3D point clouds

KW - ICP

KW - RGB-D video streams

KW - back projected edge features

KW - computation time

KW - depth component

KW - edge based RGB-D SLAM

KW - edge features

KW - fast depth edge detection

KW - image similarity

KW - publicly available datasets

KW - Cameras

KW - Image edge detection

KW - Iterative closest point algorithm

KW - Simultaneous localization and mapping

KW - Streaming media

KW - Three-dimensional displays

U2 - 10.1109/ICRA.2016.7487265

DO - 10.1109/ICRA.2016.7487265

M3 - Conference Contribution (Conference Proceeding)

SN - 9781467380270

SP - 1323

EP - 1330

BT - 2016 IEEE International Conference on Robotics and Automation (ICRA 2016)

PB - Institute of Electrical and Electronics Engineers (IEEE)

ER -

Fast depth edge detection and edge based RGB-D SLAM

Abstract

Keywords

Access to Document

Edge Based RGB-D SLAM and SLAM Based Navigation

Cite this