An embedded stereo vision module for 6D pose estimation and mapping

Author

Spampinato, G. ; Lidholm, J. ; Ahlberg, C. ; Ekstrand, F. ; Ekström, M. ; Asplund, L.

Author_Institution

Sch. of Innovation, Design & Eng., Malardalen Univ., Vasteras, Sweden

fYear

2011

fDate

25-30 Sept. 2011

Firstpage

1626

Lastpage

1631

Abstract

This paper presents an embedded vision system based on reconfigurable hardware (FPGA) and two CMOS cameras to perform stereo image processing and 3D mapping for autonomous navigation. We propose an EKF based visual SLAM and sparse feature detectors to achieve 6D localization of the vehicle in non flat scenarios. The system can operate regardless of the odometry information from the vehicle since visual odometry is used. As a result, the final system is compact and easy to install and configure.

Keywords

CMOS image sensors; Kalman filters; SLAM (robots); automatic guided vehicles; distance measurement; feature extraction; field programmable gate arrays; mobile robots; pose estimation; robot vision; stereo image processing; 3D mapping; 6D localization; 6D pose estimation; CMOS camera; EKF based visual SLAM; FPGA; autonomous navigation; embedded stereo vision module; odometry information; reconflgurable hardware; sparse feature detector; stereo image processing; visual odometry; Accuracy; Cameras; Estimation; Three dimensional displays; Uncertainty; Vehicles; Visualization;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Robots and Systems (IROS), 2011 IEEE/RSJ International Conference on

Conference_Location

San Francisco, CA

ISSN

2153-0858

Print_ISBN

978-1-61284-454-1

Type

conf

DOI

10.1109/IROS.2011.6094788

Filename

6094788