Publication:
Depth estimation for visually impaired people using mobile devices

Thumbnail Image
Files

Files

Depth_estimation_for_visually_impaired_people_using_mobile_devices.pdf (569.3 KB)
View Statistics
Reference Managers
Mendeley
Indexers
Google Scholar CORE
QR Code
QR Code
Authors

Authors

Navarro, Felipe
Cancino, Sandra
Estupiñán, Enrique
Abstract (Spanish)
Este trabajo presenta el desarrollo de una aplicación para estimar la profundidad utilizando dispositivos móviles que podría ayudar a las personas con discapacidad visual a navegar en sitios cotidianos. El dispositivo móvil incorpora un sistema de cámaras estéreo y la aplicación aprovecha las capacidades del sistema operativo, como el cálculo paralelo, la configuración del hardware, junto con las librerías de procesamiento de imágenes para implementar algoritmos bien conocidos y de rápido rendimiento para la estimación de la profundidad. Cada cámara se calibra por separado y después se realiza una calibración estereoscópica. La estimación de la profundidad se calcula utilizando dos algoritmos diferentes y se presenta una evaluación de su rendimiento. Los dispositivos móviles manejan la carga computacional lo suficientemente rápido como para poder producir los resultados dentro del tiempo de paseo a ritmo normal. El error de estimación de la profundidad es lo suficientemente bajo como para permitir la detección de objetos como obstáculos, paredes de la habitación o personas en movimiento.
Abstract (English)
This paper presents the development of an application to estimate depth using mobile devices that could help visually impaired people to navigate in everyday sites. The mobile device incorporates a stereo camera system and the application takes advantage of the operating system capabilities, such as parallel computation, hardware configuration, in conjunction with the image processing libraries to implement well known and fast performing algorithms for depth estimation. Each camera is calibrated separately and afterwards a stereo calibration is performed. Depth estimation is calculated using two different algorithms and an evaluation of their performance is presented. The mobile devices handle the computational load fast enough to be able to produce the results within the walk time at normal pace. Depth estimation error is low enough to allow object detection like obstacles, room walls or moving persons.
Extent
4 páginas
URI: https://repositorio.escuelaing.edu.co/handle/001/1750
Collections

Collections

AB - Ecitrónica
References

Birchfield, S. &Tomasi,C., "C. A pixel dissimilarity measure that is insensitive to image sampling", IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998

Borenstein, J. &Ulrich,I., "The GuideCane A Computerized Travel Aid for the Active Guidance of Blind Pedestrians", Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 1997, pp. 1283-1288

Bradksi, G. &Kaehler, A., "Learning OpenCV", O'Reilly, 2008, pp. 415-453

Bradksi, G., "The OpenCV Library", Dr. Dobb's Journal of Software Tools, 2000

Diepstraten, J., "Design and Development of an Indoor Navigation and Object Identification System for the Blind. Hub A.", Ertl T. ASSETS'04, 2004, ACM 1-58113-911

Donghyun, K.; Dongbo, M. &Kwanghoon, S., "3D Scene Reconstruction System with Hand-Held Stereo Cameras", 3DTV Conference, 2007, ISBN 978-1-4244-0722-4

Dul, H.; Henry, P.; Ren, X.; Cheng, M.; Goldman, D.; Seitz, S. &Fox, D., "Interactive 3D Modeling of Indoor Environments with a Consumer Depth Camera", UbiComp11, 2011, ACM 978-1-4503-0630

Hirschmueller, H., "Stereo Processing by Semiglobal Matching and Mutual Information", IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008

Konolige, K., "Small Vision Systems: Hardware and Implementation", 8th International Symposium on Robotics Research (ISRR), Oct. 1997.

Konolige, K., "Technical Notes on Stereo Geometry", SRI International, Recovered http://pub1.willowgarage.com/~konolige/svs/disparity. htm

Loomis, J. M.; Klatzky, R. L; Golledge, R. G. &Philbeck, J. W., "Wayfinding: Cognitive mapping and other spatial processes", In R. G. Golledge (Ed.) "Human navigation by path integration", Johns Hopkins University Press, 1999, pp. 125-151

Shapiro, L. &Stockman, G., "Computer Vision", Ed. Prentice Hall, 2001, pp. 431

Sharstein,D. &Szeliski,R., "A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms", International Journal on Computer Vision (IJCV), 2002

World Health Organization WHO Media Center, FACT SHEET No 282, June 2012, Recovered http://www.who.int/mediacentre/factsheets/fs282/en