Object Search and Localization for an Indoor Mobile Robot
Kristoffer Sjö
; Centre for Autonomous Systems, Royal Institute of Technology, Stockholm, Sweden
Dorian Gálvez López
; Centre for Autonomous Systems, Royal Institute of Technology, Stockholm, Sweden
Chandana Paul
; Centre for Autonomous Systems, Royal Institute of Technology, Stockholm, Sweden
Patric Jensfelt
; Centre for Autonomous Systems, Royal Institute of Technology, Stockholm, Sweden
Danica Kragic
; Centre for Autonomous Systems, Royal Institute of Technology, Stockholm, Sweden
APA 6th Edition Sjö, K., López, D.G., Paul, C., Jensfelt, P. i Kragic, D. (2009). Object Search and Localization for an Indoor Mobile Robot. Journal of computing and information technology, 17 (1), 67-80. https://doi.org/10.2498/cit.1001182
MLA 8th Edition Sjö, Kristoffer, et al. "Object Search and Localization for an Indoor Mobile Robot." Journal of computing and information technology, vol. 17, br. 1, 2009, str. 67-80. https://doi.org/10.2498/cit.1001182. Citirano 27.02.2021.
Chicago 17th Edition Sjö, Kristoffer, Dorian Gálvez López, Chandana Paul, Patric Jensfelt i Danica Kragic. "Object Search and Localization for an Indoor Mobile Robot." Journal of computing and information technology 17, br. 1 (2009): 67-80. https://doi.org/10.2498/cit.1001182
Harvard Sjö, K., et al. (2009). 'Object Search and Localization for an Indoor Mobile Robot', Journal of computing and information technology, 17(1), str. 67-80. https://doi.org/10.2498/cit.1001182
Vancouver Sjö K, López DG, Paul C, Jensfelt P, Kragic D. Object Search and Localization for an Indoor Mobile Robot. Journal of computing and information technology [Internet]. 2009 [pristupljeno 27.02.2021.];17(1):67-80. https://doi.org/10.2498/cit.1001182
IEEE K. Sjö, D.G. López, C. Paul, P. Jensfelt i D. Kragic, "Object Search and Localization for an Indoor Mobile Robot", Journal of computing and information technology, vol.17, br. 1, str. 67-80, 2009. [Online]. https://doi.org/10.2498/cit.1001182
Sažetak In this paper we present a method for search and localization of objects with a mobile robot using a monocular camera with zoom capabilities. We show how to overcome the limitations of low resolution images in object recognition by utilizing a combination of an attention mechanism and zooming as the first steps in the recognition process. The attention mechanism is based on receptive field cooccurrence histograms and the object recognition on SIFT feature matching. We present two methods for estimating the distance to the objects which serves both as the input to the control of the zoom and the final object localization. Through extensive experiments in a realistic environment, we highlight the strengths and weaknesses of both methods. To evaluate the usefulness of the method we also present results from experiments with an integrated system where a global sensing plan is generated based on view planning to let the camera cover the space on a per room basis.