Disjoint track matching based on a major color spectrum histogram representation

A disjoint track matching algorithm is proposed based on major color spectrum histogram representation (MCSHR) matching and post-matching integration algorithms; this algorithm is useful for reconnecting broken tracks due to occlusions and potentially useful for tracking a single object across multiple, disjoint cameras. An incremental MCSHR (IMCSHR) matching algorithm is also proposed to cope with small pose changes occurring along the track. First, an MCSHR is introduced to represent a moving object by its most frequent colors. Then a two-directional (2-D) similarity measurement algorithm based on the most similar major color searching algorithm is proposed to measure the similarity of the two given moving objects by using IMCSHR in a few frames. Last, our track matching algorithm extends the multiframe matching along the object's tracks by a post-matching integration algorithm. Experimental results have shown that the similarity of two tracks from the same moving objects has proven as high as 89 to 97%, while the similarity of two tracks from different moving objects has been kept as low as 14 to 54%. The post-matching integration algorithm has been proven to be able to make track matching more robust and reliable. (C) 2007 Society of Photo-Optical Instrumentation Engineers.