Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 33030
Adaptive Block State Update Method for Separating Background
Authors: Youngsuck Ji, Youngjoon Han, Hernsoo Hahn
Abstract:
In this paper, we proposed the robust mobile object detection method for light effect in the night street image block based updating reference background model using block state analysis. Experiment image is acquired sequence color video from steady camera. When suddenly appeared artificial illumination, reference background model update this information such as street light, sign light. Generally natural illumination is change by temporal, but artificial illumination is suddenly appearance. So in this paper for exactly detect artificial illumination have 2 state process. First process is compare difference between current image and reference background by block based, it can know changed blocks. Second process is difference between current image-s edge map and reference background image-s edge map, it possible to estimate illumination at any block. This information is possible to exactly detect object, artificial illumination and it was generating reference background more clearly. Block is classified by block-state analysis. Block-state has a 4 state (i.e. transient, stationary, background, artificial illumination). Fig. 1 is show characteristic of block-state respectively [1]. Experimental results show that the presented approach works well in the presence of illumination variance.Keywords: Block-state, Edge component, Reference backgroundi, Artificial illumination.
Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1081593
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1315References:
[1] H. Fujiyoshi, "Layered Detection for Multiple Overlapping Objects," IEEE International Conference on Pattern Recognition, vol. 4, pp.156-161, 2002.
[2] Sigari, M., "Fuzzy running average and fuzzy background subtraction: Concepts and application," International Journal of Computer Science and Network Security 8, pp. 138-143, Feb. 2008.
[3] Nishi, T., "Object-based Video Coding Using Pixel State Analysis," ICPR 2004, Vol. 3, pp. 306- 309, Aug. 2004.
[4] X.Deng, "A block-based background model for video surveillance," ICASSP, pp. 1013-1016, 2008.
[5] V. Sanchez, "Prioritized region of interest coding in JPEG2000," IEEE Trans. on CSVT, vol. 14 (9), pp. 1149-1155, Sep. 2004.