Ground-plane classification for robot navigation: combining multiple cues toward a visual-based learning system
Paper
Paper/Presentation Title | Ground-plane classification for robot navigation: combining multiple cues toward a visual-based learning system |
---|---|
Presentation Type | Paper |
Authors | Low, Tobias (Author) and Manzanera, Antoine (Author) |
Journal or Proceedings Title | Proceedings of the 11th International Conference on Control, Automation, Robotics and Vision (ICARCV 2010) |
Number of Pages | 6 |
Year | 2010 |
Place of Publication | United States |
ISBN | 9781424478149 |
9781424478156 | |
Digital Object Identifier (DOI) | https://doi.org/10.1109/ICARCV.2010.5707289 |
Web Address (URL) of Paper | https://ieeexplore.ieee.org/document/5707289 |
Web Address (URL) of Conference Proceedings | https://ieeexplore.ieee.org/xpl/conhome/5702939/proceeding |
Conference/Event | 11th International Conference on Control, Automation, Robotics and Vision (ICARCV 2010) |
Event Details | Rank A A A |
Event Details | 11th International Conference on Control, Automation, Robotics and Vision (ICARCV 2010) Event Date 07 to end of 10 Dec 2010 Event Location Singapore |
Abstract | This paper describes a vision-based ground-plane classification system for autonomous indoor mobile-robot that takes advantage of the synergy in combining together multiple visual-cues. A priori knowledge of the environment is important in many biological systems, in parallel with their reactive systems. As such, a learning model approach is taken here for the classification of the ground/object space, initialised through a new Distributed-Fusion (D-Fusion) method that captures colour and textural data using Superpixels. A Markov Random Field (MRF) network is then used to classify, regularise, employ a priori constraints, and merge additional ground/object information provided by other visual cues (such as motion) to improve classification images. The developed system can classify indoor test-set ground-plane surfaces with an average true-positive to false-positive rate of 90.92% to 7.78% respectively on test-set data. The system has been designed in mind to fuse a variety of different visual-cues. Consequently it can be customised to fit different situations and/or sensory architectures accordingly. |
Keywords | image classification; image disparity; ground plane; obstacle avoidance; visual navigation; mobile robots |
Contains Sensitive Content | Does not contain sensitive content |
ANZSRC Field of Research 2020 | 400703. Autonomous vehicle systems |
400799. Control engineering, mechatronics and robotics not elsewhere classified | |
469999. Other information and computing sciences not elsewhere classified | |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | Department of Mechanical and Mechatronic Engineering |
Superior National School of Advanced Techniques, France | |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q0951/ground-plane-classification-for-robot-navigation-combining-multiple-cues-toward-a-visual-based-learning-system
1977
total views2489
total downloads1
views this month0
downloads this month