Real-Time Indoor Floor Detection for Mobile Robots using Iterative Approach
Main Article Content
Abstract
This paper introduces an iterative technique to segmentation of indoor floor from a single 2-D camera connected to a mobile robot. The segmentation of the floor is an essential function for efficient mobile robot navigation, unlike previous approaches which rely on geometric indications, edges etc. Mobile robot mounted with the 2-D camera can capture floors images over long indoor sequences. Both floor and non-floor regions are all of a similar color when the conditions of illumination vary over a single image. The texture of the floor varies over a single image, and features may be lost as lighting changes. As mobile robot rotates, lot of information may be lost in the presence of small obstacles. Some floor areas are very shining under the artificial light condition. The radiant floor gives the wrong segmentation output. In the proposed approach does not require multiple images. The floor patterns are dynamically selected in the proposed research, and segmentation is performed based on the chosen designs. Camera calibration is not required in the proposed approach for floor segmentation. Also, edge cues and geometric cues are not necessary. The extensive experiment is conducted on a broad set of real indoor corridor floor image set.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
IJCERT Policy:
The published work presented in this paper is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This means that the content of this paper can be shared, copied, and redistributed in any medium or format, as long as the original author is properly attributed. Additionally, any derivative works based on this paper must also be licensed under the same terms. This licensing agreement allows for broad dissemination and use of the work while maintaining the author's rights and recognition.
By submitting this paper to IJCERT, the author(s) agree to these licensing terms and confirm that the work is original and does not infringe on any third-party copyright or intellectual property rights.
References
J Adorno et al. “Smartphone-based Floor Detection in Unstructured and Structured Environments”, 978-1- 5090-1941-0/16/$31.00 ©2016 IEEE
R. Deepu, B. Honnaraju, and S. Murali, "Path Generation for Robot Navigation using a SingleCamera", Procedia Computer Science, vol. 46, pp. 1425–1432, 2015, DOI: 10.1016/j.procs.2015.02.061.
Soumabha Bhowmick and Abhishek Pant, “A novel floor segmentation algorithm for mobile robot navigation ” 978-1-4673-8564-0/15/$31.00 c 2015 IEEE
Suryansh Kumar and K Madhava Krishna, “Fusing Appearance and Geometric Cues for Adaptive Floor Segmentation over Images”, Centre for Robotics International Institute of Information Technology 2013.
X.-N. Cui, Y.-G. Kim, and H. Kim, “Floor segmentation by computing plane normal from image motion fields for visual navigation”. International Journal of Control, Automation, and Systems, 7(5):788–798, 2009.
Y.-G. Kim and H. Kim, “Layered ground floor detection for vision-based mobile robot navigation”. In Proceedings of the IEEE International Conference on Robotics and Automation, 2004.
J. Zhou and B. Li. “Robust ground plane detection with normalized homography in monocular sequences from a robot platform”. In Proceedings of the International Conference on Image Processing, 2006.