NAVI: Navigation aid for the visually impaired

This paper describes a voice navigational system for the visually impaired which runs on the user's smart-phone as an application and requires no additional expensive or heavy hardware. This system requires just the live video stream from the user's phone camera and an internet connection, and hence can be used on the most basic of smart-phones. The system proposed here identifies obstacles in front of the user and approaching obstacles, and is able to classify the obstacle into categories like car, human, dog, door or chair along with a direction of approach which would be either left, right or middle, in real time. It is also able to recognize faces of some predetermined people that the user desires. An audio feedback is given to the user. This system does not aim to eliminate the walking stick, but is meant to be used along with it essentially expanding the range of awareness of the user.

[1]  Per Ola Kristensson,et al.  Supporting blind navigation using depth sensing and sonification , 2013, UbiComp.

[2]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[3]  Miguel Á. Carreira-Perpiñán,et al.  On Contrastive Divergence Learning , 2005, AISTATS.

[4]  Kostas E. Bekris,et al.  Integrated online localization and navigation for people with visual impairments using smart phones , 2012, 2012 IEEE International Conference on Robotics and Automation.

[5]  B. D. Lucas.  Generalized image matching by the method of differences , 1985 .

[6]  Saurav Kumar.  Binocular Stereo Vision Based Obstacle Avoidance Algorithm for Autonomous Mobile Robots , 2009, 2009 IEEE International Advance Computing Conference.

[7]  Shruti Dambhare,et al.  Smart stick for Blind: Obstacle Detection, Artificial vision and Real-time assistance via GPS , 2011 .

[8]  Gunnar Farnebäck,et al.  Two-Frame Motion Estimation Based on Polynomial Expansion , 2003, SCIA.

[9]  John D. Austin,et al.  Adaptive histogram equalization and its variations , 1987 .

[10]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[11]  Francesco Bullo,et al.  Smooth Nearness-Diagram Navigation , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[12]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[13]  Ling Li,et al.  A Smartphone-Based Obstacle Sensor for the Visually Impaired , 2010, UIC.

[14]  Eelke Folmer,et al.  Headlock: a wearable navigation aid that helps blind cane users traverse large open spaces , 2014, ASSETS.

[15]  Andrei Bursuc,et al.  A Smartphone-Based Obstacle Detection and Classification System for Assisting Visually Impaired People , 2013, 2013 IEEE International Conference on Computer Vision Workshops.

[16]  Dan Roth,et al.  Learning to detect objects in images via a sparse, part-based representation , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Tomaso A. Poggio,et al.  A Trainable System for Object Detection , 2000, International Journal of Computer Vision.