Qing Lin1, Youngjoon Han1, Namki Lee1, Hwanik Chung2
Department of Electronic Engineering, Soongsil University, Seoul 156-743, Korea
Abstract： This paper presents an obstacle detection approach for blind pedestri ans by fusing data from camera and laser sensor. For purely vision-based blind g uidance system, it is difficult to discriminate low-level obstacles with clutter ed road surface, while for purely laser-based system, it usually requires to sca n the forward environment, which turns out to be very inconvenient. To overcome these inherent problems when using camera and laser sensor independently, a sens or-fusion model is proposed to associate range data from laser domain with edges from image domain. Based on this fusion model, obstacle's position, size and sh ape can be estimated. The proposed method is tested in several indoor scenes, an d its efficiency is confirmed.
Key words： obstacle detection; sensor fusion; electronic travel-aids
References
[1] Dakopoulos D, Bourbakis N G. Wearable obstacle avoidance electronic travel a ids for sight-impaired: a survey. IEEE Transactions on Systems, Man, and Cyberne tics, 2010, 40(1): 25-35.
[2] Rodriguez A, Bergasa L M, Alcantarilla P F, et al. Obstacle avoidance system for assisting visually impaired people. In: Proceedings of IEEE Intelligent Veh icles Symposium, Alcala de Henares, Spain, 2012: 34-39.
[3] Mora J L G, Hernandez R, Ramos L F R, et al. Research and development team i n space perception using sounds with specific aplication for blind people. [2013 -02-21]. http://www.iac.es/proyect/eavi.
[4] Dakopoulos D, Boddhu S K, Bourbakis N. A 2D vibration array as an assistive device for visually impaired. In: Proceedings of the 7th IEEE International Con ference on Bioinformatics and Bioengineering, Chania, Greece, 2007: 930-937.
[5] Bourbakis N. Sensing 3D dynamic space for sight-impaired. IEEE Engineering i n Medicine and Biology Magazine, 2008, 27(1): 49-55.
[6] Yuan D, Manduchi R. A tool for range sensing and environment discovery for t he blind. In: Proceedings of Computer Vision and Pattern Recognition Workshop(CV PRW’04), Washington, USA, 2004: 39-41.
[7] ZHANG Qi-long, Pless R. Extrinsic calibration of a camera and laser range fi nder. In: Proceedings of IEEE/RSJ International Conference on Intelligence Robot s and Systems(IROS), 2004: 2031-2036.
[8] ZHANG Zheng-you. A flexible new technique for camera calibration. IEEE Trans actions on Pattern Analysis and Machine Intelligence, 2000, 22(11): 1330-1334.
[9] Dietmayer K C J, Sparbert J, Streller D. Model based object classification a nd object tracking in traffic scenes from range images. In: Proceedings of IEEE Intelligent Vehicles Symposium, 2001: 25-30.
[10] Lin Q, Han Y J, Hahn H S. Real-time lane departure detection based on exten ded edge-linking algorithm. In: Proceedings of the 2nd International Conference on Computer Research and Development, 2010: 725-730.
[full text view]
