칼만 필터를 이용한 다양한 환경 변화에 적합한 효율적인 정보 압축 알고리즘에 관한 연구

다국어 초록 (Multilingual Abstract)

This paper describes a effective information compressor algorithm for the fourth industrial technology. One of the difficult problems for outdoor is to obtain effective updating process of background images. Because input images generally contain the shadows of buildings, trees, moving clouds and other objects, they are changed by lapse of time and variation of illumination. They provide the lowering of performance for surveillance system under outdoor.
In this paper, a effective information algorithm for variable environment variable under outdoor is proposed, which apply the Kalman Estimation Modeling and adaptive threshold on pixel level to separate foreground and background images from current input image. In results, the better SNR of about 3dB~5dB and about 10%~25% noise distribution rate in the proposed method. Furthermore, it was showed that the moving objects can be detected on various shadows under outdoor and better result Information.

참고문헌 (Reference)

1 M.Soga, "Visibility Improvem ent for a Blind Spot Monitor by Compressing the Brightness Range of Images" 2 : 17-21, 2002

2 L. Wang, "Using Steerable- Filters for Illumination-Invariant Recognition in Multispectral Images" 138-141, 1997

3 Ho-jung Lee, "The Efficient Color Feature Information Extraction Method for Color Histogram-based Image Retrieval" 25 (25): 2000

4 Kenji Irie, "Shadow Removal for Object Tracking in Complex Outdoor Scenes" 25-30, 2007

5 M. Jayakumar, "Risk-sensitive filters for recursive estimation of motion from images" Institute of Electrical and Electronics Engineers (IEEE) 20 (20): 659-666, 1998

6 G.D. Hager, "Efficient region tracking with parametric models of geometry and illumination" Institute of Electrical and Electronics Engineers (IEEE) 20 (20): 1025-1039, 1998

7 K. Irie, "A tech- nique for evaluation of CCD video- camera noise (Accepted forpublication)" 2007