Background modeling and subtraction by codebook construction

We present a new fast algorithm for background modeling and subtraction. Sample background values at each pixel are quantized into codebooks which represent a compressed form of background model for a long image sequence. This allows us to capture structural background variation due to periodic-like motion over a long period of time under limited memory. Our method can handle scenes containing moving backgrounds or illumination variations (shadows and highlights), and it achieves robust detection for compressed videos. We compared our method with other multimode modeling techniques.

• Type: Conference
• Year: 2004
• Where: ICIP
• Authors: Kyungnam Kim, Thanarat H. Chalidabhongse, David Harwood, Larry S. Davis
• Keywords: Background Modeling, ICIP 2004, Image Processing, Long Image Sequence, Multimode Modeling Techniques, Sample Background Values, Structural Background Variation