Abstract:
In this paper, a Major Color Spectrum Histogram
Representation (MCSHR) is introduced to represent a
moving object by using a normalized geometric distance
between two points in the RGB space. Then, an
Incremental Major Color Representation Algorithm is
proposed to cope with small pose changes occurring
along the track. Finally, a two directional similarity
measurement based on the major colors is used to
measure the similarity of any two given moving objects in
multiple integrated frames. Experimental results show
that with a few (4 or 5) frames MCSHR integration, the
proposed Incremental MCSHR algorithm can make
matching more robust and reliable than single frame
matching, especially for small pose changes. The major
color representation algorithm based on the introduced
color distance can represent moving objects accurately
with a limited number of colors and the frequency of each
major color. The similarity of a same moving object in
two different tracks has improved from 85% to 97% with
the number of integrated frames increasing from 1 to 5,
while the similarity of two different moving objects has
been kept as low as 9% to 19%.
