JOURNAL BROWSE
Search
Advanced SearchSearch Tips
Hardware Implementation of Depth Image Stabilization Method for Efficient Computer Vision System
facebook(new window)  Pirnt(new window) E-mail(new window) Excel Download
 Title & Authors
Hardware Implementation of Depth Image Stabilization Method for Efficient Computer Vision System
Kim, Geun-Jun; Kang, Bongsoon;
  PDF(new window)
 Abstract
Increasing of depth data accessibility, depth data is used in many researches. Motion recognition of computer vision also widely use depth image. More accuracy motion recognition system needs more stable depth data. But depth sensor has a noise. This noise affect accuracy of the motion recognition system, we should noise suppression. In this paper, we propose using spatial domain and temporal domain stabilization for depth image and makes it hardware IP. We adapted our hardware to floor removing algorithm and verification its effect. we did realtime verification using FPGA and APU. Designed hardware has maximum frequency 202.184MHz.
 Keywords
Depth data stabilization;Depth sensor;Computer vision;Motion recognition;FPGA;
 Language
Korean
 Cited by
 References
1.
Jungong Han, Ling Shao, Dong Xu and Shotton., “Enhanced computer vision with microsoft kinect sensor: A Review,” IEEE Transactions on Cybernetics, Vol. 43, no. 5, pp. 1318-1334, Oct. 2013. crossref(new window)

2.
Jichan Lee, S. Lim, J. Kim and B. Kim, "Moving object detection using background subtraction and motion depth detectionin depth image sequences," in proceeding of the IEEE International Symposium on Consumer Electronics, Jeju, pp.1-2, June. 2014.

3.
Chenyang Zhang, YingLi Tian, "Edge Enhanced Depth Motion map for Dynamic Hand Gesture Recognition," in proceeding of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Portland, pp.500-505, June. 2013.

4.
Mallick, T, Das, P.P and Majumdar, A.K,, “Characterizations of noise in Kinect depth images: A Review,” IEEE Sensors journal, Vol 14, no. 6, pp. 1731-1740, Nov. 2014. crossref(new window)

5.
Tatong Xu, Xin Jin and Qionghai Dai, "Spatial-temporal depth de-noising for Kinect based on texture edge-assisted depth classification," in proceeding of the 19th International Conference on Digital Signal Processing, Hong Kong, pp. 327-332, Aug. 2014.

6.
Matyunin, S, Vatolin, D, Berdnikov, Y and Smirnov, M, "Temporal filtering for depth maps generated by Kinect depth camera," in proceeding of the 3DTV Conference, Antalya, pp. 1-4, May. 2011.

7.
Geun-Jun Kim, Gippeum Jo, Hosang Cho, Bongsoon Kang, "Depth data smoothing method for the motion recognition pre-processing system," in proceeding of the Information and Control Symposium, Seoul, pp. 22-23, April. 2014.

8.
Kyounghoon Jang, Hosang Cho, Geun-Jun Kim and Bongsoon Kang, "A Floor Plane Removal System Using Depth Information for Motion Recognition System," in proceeding of the International Conference on Information Technology Convergence and Services, Taiwan, pp. 33-38, Oct. 2014.