This paper presents a novel vision-based approach for indoor environment monitoring by a mobile robot. The proposed system is based on computer vision methods to match the current scene with a stored one, looking for new or removed objects. The matching process uses both keypoint features and colour information. A PCA-SIFT algorithm is employed for feature extraction and matching. Colour-based segmentation is performed separately, using HSV coding. A fuzzy logic inference system is applied to fuse information from both steps and decide whether a significant variation of the scene has occurred. Results from experimental tests demonstrate the feasibility of the proposed method in robot surveillance applications.
Robust Vision-Based Monitoring of Indoor Environments by an Autonomous Mobile Robot
- Views Icon Views
- Share Icon Share
- Search Site
Di Paola, D, Milella, A, Cicirelli, G, & Distante, A. "Robust Vision-Based Monitoring of Indoor Environments by an Autonomous Mobile Robot." Proceedings of the ASME 2007 International Mechanical Engineering Congress and Exposition. Volume 9: Mechanical Systems and Control, Parts A, B, and C. Seattle, Washington, USA. November 11–15, 2007. pp. 567-574. ASME. https://doi.org/10.1115/IMECE2007-41181
Download citation file: