Browse > Article
http://dx.doi.org/10.5626/JOK.2015.42.1.138

Image Based Human Action Recognition System to Support the Blind  

Ko, ByoungChul (Keimyung Univ.)
Hwang, Mincheol (Keimyung Univ.)
Nam, Jae-Yeal (Keimyung Univ.)
Publication Information
Journal of KIISE / v.42, no.1, 2015 , pp. 138-143 More about this Journal
Abstract
In this paper we develop a novel human action recognition system based on communication between an ear-mounted Bluetooth camera and an action recognition server to aid scene recognition for the blind. First, if the blind capture an image of a specific location using the ear-mounted camera, the captured image is transmitted to the recognition server using a smartphone that is synchronized with the camera. The recognition server sequentially performs human detection, object detection and action recognition by analyzing human poses. The recognized action information is retransmitted to the smartphone and the user can hear the action information through the text-to-speech (TTS). Experimental results using the proposed system showed a 60.7% action recognition performance on the test data captured in indoor and outdoor environments.
Keywords
The blind; human detection; object recognition; action recognition;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 Statistics Korea (2014, June). Registered disabled persons of Korea [Online]. Available: http://www.index.go.kr/ (downloaded 2014, Aug.18)
2 R. Kim, S. Park, S. Lee, H. Cho, and S. Ha, "Improvement of An Electronic Aid for the Blind using Ultrasonic and Acceleration Sensors," Journal of KIISE : Software and Applications, Vol. 36, No. 4, pp. 291-297, Apr. 2009. (in Korean)   과학기술학회마을
3 C. Kang, H. Cho, and B. Kim, "A Machine-tomachine based Intelligent Walking Assistance System for Visually Impaired Person," The Journal of Korea Information and Communications Society, Vol. 36, No. 3, pp. 287-296, Mar. 2011. (in Korean).   과학기술학회마을   DOI
4 T-K. Kim, B-J. Choi, and B-S. Song, "A Machineto- machine based Intelligent Walking Assistance System for Visually Impaired person," The Korean Journal of Visual Impairment, Vol. 24. No. 2, pp. 43- 59, Feb. 2008.
5 H-S Yoon (2013, March), Adaptive visual information guiding system for the blind [Online]. Available: http://www.etri.re.kr/etri/res/res_01020303.etri (downloaded 2014, Aug. 18)
6 J. E. Son, J. H. Jung, B. C. Ko, and J. Y. Nam, "Part based human detection considering multi-view of human," Journal of KIISE :Computing Practices and Letters, Vol. 19, No. 11, pp. 596-600, Nov. 2013. (in Korean)   과학기술학회마을
7 J-H Jung, "Multi-View Object Detection with Sharing Local Features and Ensemble Learning of Random Forests," M.S thesis of Keimyung University, 2014.
8 B.C. Ko, J-Y Kwak, and J-Y Nam, "Human Tracking in Thermal Images Using Adaptive Particle Filters with Online Random Forest Learning," Optical Engineering, Vol. 52, No. 11, pp. 1-14, Nov. 2013.
9 J-H Hong, "Human action recognition in still images using action poselets and two-layer classification model," M.S thesis of Keimyung University, 2014.
10 N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection," Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 886-893, 2005.
11 J. R. R. Uijlings, K. E. A. Sande, T. Gevers, and A. W. M. Smeulders, "Selective Search for Object Recognition," International Journal of Computer Vision, Vol. 104, No. 2, pp. 154-171, Sep. 2013.   DOI
12 S. Maji, L. Bourdev, and J. Malik, "Action recognition from a distributed representation of pose and appearance," Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3177- 3184, 2011.