Research and Implementation of Moving Object Contour Extraction Algorithm Based on GPU

Abstract:

In this paper, frame differential method will be used to detect moving targets in a static background video file, and pre-contour can be obtained by binarizing the detected targets . However,, the result are not what was expected, so the expansion and corrosion of mathematical morphology are used to extract the final contour of moving targets. in the progress of dealing with massive data , mathematical morphology is not good enough to achieve the need of the real-time in video surveillance. Considering the dilation and erosion is a kind of parallel processing operations, in order to improve the speed of mathematical morphology operations, this paper offers detailed implementation process of the dilation algorithm for parallel computing on GPU. Experimental results showed that GPU parallel processing on mathematical morphology algorithm faster than the CPU serial processing.

• Periodical: Applied Mechanics and Materials (Volume 643)
• Pages: 253-257
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.643.253
• Online since: September 2014
• Authors: Kai Min Zhao*, Yu Ting Chen, Jun Li, Hao Yang, Li Ying Chen
• Keywords: Contour Extraction, GPU, Mathematical Morphology, Moving Object Detection, Real-Time

References

[1] Pavel Korshunov, Wei Tsang Ooi. Critical video quality for distributed automated video surveillance[C] . Proceedings of the 13th annual ACM international conference on Multimedia, 2005: 151—160.

DOI: 10.1145/1101149.1101172

[2] Ismail A. Taha,  Joydeep Ghosh. Symbolic Interpretation of Artificial Neural Networks. May. 1999 . IEEE Transactions on Knowledge and Data Engineering.

DOI: 10.1109/69.774103

[3] Punam Kumar Saha. Tensor scale: a local morphometric parameter with applications to computer vision and image processing[J]. Computer Vision and Image Understanding, 2005, 99(3): 384—413.

DOI: 10.1016/j.cviu.2005.03.003

[4] Zhang Keqi, Chen Shu-Ching, Whitman D et al. A progressive morphological filter for removing nonground measurements from airborne LIDAR data[J]. IEEE Tran. On Geoscience and Remote Sensing, 2003, 41(4)：872-882.

DOI: 10.1109/tgrs.2003.810682

[5] Marie-Pierre Dubuisson, Anil K. Jain. Contour extraction of moving objects in complex outdoor scenes. International Journal of Computer Vision.

DOI: 10.1007/bf01421490

[6] L Wang, Y Huang, X Chen. Task scheduling of parallel processing in cpu-gpu collaborative environment. Computer Science, (2008).

DOI: 10.1109/iccsit.2008.27

[7] Hu Wei, Qin Kaihuai. A New Rendering Technology of GPU-Accelerated Radiosity[J]. Journal of Computer Research And Development, 2005, 42（6）: 81-83.

DOI: 10.1360/crad20050607