Stair case detection and recognition using ultrasonic signal

The process of staircase negotiation is complex for blinds. Therefore, an intelligent system is required to help them. In this paper, we investigate using only one ultrasonic sensor to detect and recognize floor and stair cases in electronic white cane. The performance of an object recognition system depends on both object representation and classification algorithms. In our system, we have used more than one representation of ultrasonic signal in frequencial domain. First, spectrogram representation explains how the spectral density of ultrasonic signal varies with time. Second, spectrum representation shows the amplitudes as a function of the frequency. Finally, periodogram representation estimates the spectral density of ultrasonic signal. Then, several features are extracted from each representation. Our system was evaluated on a set of ultrasonic signal where floor and stair cases occur with different shape. Using a multiclass SVM approach, accuracy rates of 72.41% has been achieved.

[1]  A.-C. Scherlen,et al.  "RecognizeCane" : The new concept of a cane which recognizes the most common objects and safety clues , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[2]  Sooyong Lee,et al.  Design and analysis of an infrared range sensor system for floor-state estimation , 2011 .

[3]  F. Dunn,et al.  Ultrasonic Scattering in Biological Tissues , 1992 .

[4]  Jaime B. Santos,et al.  Automatic defects classification — a contribution , 2001 .

[5]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[6]  Martin David Adams,et al.  On-line gradient based surface discontinuity detection for outdoor scanning range sensors , 2001, Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180).

[7]  C. Barat,et al.  Classification of indoor environment using only one ultrasonic sensor , 2001, IMTC 2001. Proceedings of the 18th IEEE Instrumentation and Measurement Technology Conference. Rediscovering Measurement in the Age of Informatics (Cat. No.01CH 37188).

[8]  George H. John.  Enhancements to the data mining process , 1997 .

[9]  Hamid D. Taghirad,et al.  Autonomous staircase detection and stair climbing for a tracked mobile robot using fuzzy controller , 2009, 2008 IEEE International Conference on Robotics and Biomimetics.

[10]  Satish S. Udpa,et al.  Classification of Ultrasonic Weld Inspection Data Using Principal Component Analysis , 1997 .

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

[12]  J.M. Perez Oria,et al.  Object recognition using ultrasonic sensors in robotic applications , 1993, Proceedings of IECON '93 - 19th Annual Conference of IEEE Industrial Electronics.

[13]  Roberto Manduchi,et al.  Dynamic environment exploration using a virtual white cane , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[14]  Roman Kuc,et al.  Introduction to Digital Signal Processing , 1988 .

[16]  Aung Aung Phyo Wai,et al.  Application of ultrasonic sensors in a smart environment , 2007, Pervasive Mob. Comput..

[17]  Herbert Peremans,et al.  A high-resolution sensor based on tri-aural perception , 1993, IEEE Trans. Robotics Autom..

[18]  Sung-Jin Song,et al.  Development of an intelligent system for ultrasonic flaw classification in weldments , 2002 .

[19]  David J. DeFatta,et al.  Digital Signal Processing: A System Design Approach , 1988 .

[20]  S. Udpa,et al.  Classification of ultrasonic signals via neural networks : Review of Progress in Quantitative Nondestructive Evaluation, La Jolla, California (United States), 15–20 Jul. 1990. Vol. 10A, pp. 659–666. Edited by D.O. Thompson, and D.E. Chimenti. Plenum Press (1991). ISBN 0-306-43903-4 , 1992 .

[21]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[22]  K. Ramamohan Rao.  Discrete transforms and their applications , 1985 .

[23]  Roman Kuc,et al.  Building a Sonar Map in a Specular Environment Using a Single Mobile Sensor , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  Itiel E. Dror,et al.  Three-Dimensional target recognition via sonar: A neural network model , 1995, Neural Networks.