An outdoor cognition system integrated on a regular smartphone device

In this paper we introduce an assistive device dedicated to visual impaired / blind people completely integrated on a regular smartphone. The framework is designed to detect and localize static and dynamic obstacle during user navigation. We start by selecting a reduced and relevant set of FAST interest points based on a regular grid and Harris-Laplacian operator. Then, we construct a global image representation using VLAD (Vector of Locally Aggregated Descriptor) that is further whitened using PCA (Principal Component Analysis). At the end the image patch is fed to a SVM (Support Vector Machine) system that uses a statistical procedure to distinguish between different types of obstacles.

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

[2]  Simon Meers,et al.  A substitute vision system for providing 3D perception and GPS navigation via electro-tactile stimulation , 2005 .

[3]  Sazali Yaacob,et al.  Fuzzy image processing scheme for autonomous navigation of human blind , 2007, Appl. Soft Comput..

[4]  Charles M. Higgins,et al.  A Navigation Aid for the Blind Using Tactile-Visual Sensory Substitution , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[5]  Zhigang Zhu,et al.  KinDectect: Kinect Detecting Objects , 2012, ICCHP.

[6]  Patrick Pérez,et al.  Revisiting the VLAD image representation , 2013, ACM Multimedia.

[7]  Hernsoo Hahn,et al.  Walking assistance system for sight impaired people based on a multimodal information transformation technique , 2009, 2009 ICCAS-SICE.

[8]  Cordelia Schmid,et al.  Product Quantization for Nearest Neighbor Search , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[10]  Edward Y. Chang,et al.  Support vector machine active learning for image retrieval , 2001, MULTIMEDIA '01.

[11]  Fatih Murat Porikli,et al.  Region Covariance: A Fast Descriptor for Detection and Classification , 2006, ECCV.

[12]  Luis Miguel Bergasa,et al.  Assisting the Visually Impaired: Obstacle Detection and Warning System by Acoustic Feedback , 2012, Sensors.

[13]  Guillaume Gravier,et al.  Oriented pooling for dense and non-dense rotation-invariant features , 2013, BMVC.

[14]  J. M. Hans du Buf,et al.  The SmartVision local navigation aid for blind and visually impaired persons , 2011 .

[15]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[16]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[17]  Roberto Manduchi,et al.  Mobile Vision as Assistive Technology for the Blind: An Experimental Study , 2012, ICCHP.

[18]  Nikolaos G. Bourbakis,et al.  Preserving visual information in low resolution images during navigation of visually impaired , 2008, PETRA '08.

[19]  Nikolaos G. Bourbakis,et al.  A 2D Vibration Array as an Assistive Device for Visually Impaired , 2007, 2007 IEEE 7th International Symposium on BioInformatics and BioEngineering.

[20]  Ruxandra Tapu,et al.  Real time static/dynamic obstacle detection for visually impaired persons , 2014, 2014 IEEE International Conference on Consumer Electronics (ICCE).

[21]  M. Bouzit,et al.  Evaluation of RU-Netra - Tactile Feedback Navigation System For The Visually Impaired , 2006, 2006 International Workshop on Virtual Rehabilitation.

[22]  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.