Detecting stairs and pedestrian crosswalks for the blind by RGBD camera

A computer vision-based wayfinding and navigation aid can improve the mobility of blind and visually impaired people to travel independently. In this paper, we develop a new framework to detect and recognize stairs and pedestrian crosswalks using a RGBD camera. Since both stairs and pedestrian crosswalks are featured by a group of parallel lines, we first apply Hough transform to extract the concurrent parallel lines based on the RGB channels. Then, the Depth channel is employed to further recognize pedestrian crosswalks, upstairs, and downstairs using support vector machine (SVM) classifiers. Furthermore, we estimate the distance between the camera and stairs for the blind users. The detection and recognition results on our collected dataset demonstrate that the effectiveness and efficiency of our proposed framework.

[1]  Luqiang Xu,et al.  Electronic travel aids for the blind based on sensory substitution , 2010, 2010 5th International Conference on Computer Science & Education.

[2]  M. Bousbia-Salah,et al.  An Ultrasonic Navigation System for Blind People , 2007, 2007 IEEE International Conference on Signal Processing and Communications.

[3]  Lakhmi C. Jain,et al.  Intelligent systems and technologies in rehabilitation engineering , 2001 .

[4]  L. Kay,et al.  A sonar aid to enhance spatial perception of the blind: engineering design and evaluation , 1974 .

[5]  K. Karacs,et al.  Advanced crosswalk detection for the Bionic Eyeglass , 2010, 2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010).

[6]  Shi,et al.  A Fast Algorithm for Finding Crosswalks using Figure-Ground Segmentation , 2006 .

[7]  Shraga Shoval,et al.  Computerized obstacle avoidance systems for the blind and visually impaired , 2001 .

[8]  James M. Coughlan,et al.  Detecting and locating crosswalks using a camera phone , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[9]  Roman Kuc,et al.  Binaural sonar electronic travel aid provides vibrotactile cues for landmark, reflector motion and surface texture classification , 2002, IEEE Transactions on Biomedical Engineering.

[10]  Michael Brady,et al.  Vision-based Detection of Stair-cases , 2003 .

[11]  Mohammad Shorif Uddin,et al.  Bipolarity and Projective Invariant-Based Zebra-Crossing Detection for the Visually Impaired , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops.

[12]  Stephen Se.  Zebra-crossing detection for the partially sighted , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[13]  David C. Mountain,et al.  DESIGN OF A SONAR SYSTEM FOR VISUALLY IMPAIRED HUMANS , 2008 .

[14]  Bitjoka Laurent,et al.  A sonar system modeled after spatial hearing and echolocating bats for blind mobility aid , 2007 .

[15]  Barry T. Thomas,et al.  Wearable Mobility Aid for Low Vision Using Scene Classification in a Markov Random Field Model Framework , 2003, Int. J. Hum. Comput. Interact..

[16]  Günther Palm,et al.  Detecting zebra crossings utilizing AdaBoost , 2008, ESANN.

[17]  Xiaodong Yang,et al.  Toward a computer vision-based wayfinding aid for blind persons to access unfamiliar indoor environments , 2012, Machine Vision and Applications.