COMPUTER VISION FOR ASSISTIVE INDOOR LOCALIZATION

The number of elderly people in the world is increasing in proportion to the total number of people. As people get older, their cognitive and perceptual faculties decline in functionality and sometimes fail entirely; for example, manifesting themselves in disease or illness such as blindness or Alzheimer’s disease. Approximately 14 million people in North America are affected by blindness and 6 million people suffer from Alzheimer’s. Technology can help alleviate issues of confinement, security and safety as well as empowering people who feel constrained by their condition. One such way is to ensure that they are still able to conduct their daily activities by providing them with technological navigational tools. A GPS can tell people where they are and how to get somewhere but the interface can be complicated for the elderly. What if the interface was intuitively conveyed by touch like a sixth sense? This is what we have done by creating a tactile belt that we are now commercializing [TAC 11]. However, GPS does not work indoors but computer vision can be used to localize and create maps and augment as well as override GPS so navigational capabilities are never compromised (e.g., in indoor environments & urban canyons where GPS does not work).

[1]  Peter Cheeseman,et al.  On the Representation and Estimation of Spatial Uncertainty , 1986 .

[2]  Hugh F. Durrant-Whyte,et al.  An Autonomous Guided Vehicle for Cargo Handling Applications , 1995, ISER.

[3]  Andrew W. Fitzgibbon,et al.  Bundle Adjustment - A Modern Synthesis , 1999, Workshop on Vision Algorithms.

[4]  Wolfram Burgard,et al.  Experiences with an Interactive Museum Tour-Guide Robot , 1999, Artif. Intell..

[5]  Antonio Torralba,et al.  Sharing features: efficient boosting procedures for multiclass object detection , 2004, CVPR 2004.

[6]  Alexei A. Efros,et al.  Discovering object categories in image collections , 2005 .

[7]  Silvio Savarese,et al.  Discriminative Object Class Models of Appearance and Shape by Correlatons , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[8]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[9]  Hugh Durrant-Whyte,et al.  Simultaneous localization and mapping (SLAM): part II , 2006 .

[10]  Antonio Torralba,et al.  Describing Visual Scenes Using Transformed Objects and Parts , 2008, International Journal of Computer Vision.

[11]  Tom Drummond,et al.  Monocular SLAM as a Graph of Coalesced Observations , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[12]  Kurt Konolige,et al.  Large-Scale Visual Odometry for Rough Terrain , 2007, ISRR.

[13]  John S. Zelek,et al.  Local Graph Matching for Object Category Recognition , 2007, Fourth Canadian Conference on Computer and Robot Vision (CRV '07).

[14]  David W. Murray,et al.  Improving the Agility of Keyframe-Based SLAM , 2008, ECCV.

[15]  Andrew J. Davison,et al.  Guest Editorial Special Issue on Visual SLAM , 2008 .

[16]  Daniel C. Asmar,et al.  Vision SLAM Maps: Towards Richer Content , 2009 .

[17]  Silvio Savarese,et al.  A multi-view probabilistic model for 3D object classes , 2009, CVPR.

[18]  Sanja Fidler,et al.  Object Categorization: Learning Hierarchical Compositional Representations of Object Structure , 2009 .

[19]  Antonio Torralba,et al.  Exploiting hierarchical context on a large database of object categories , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.