In the lane surveillance system, the camera is placed
at a certain place, focusing on one or two lanes. So the
background in the video sequence is almost fixed too,
the foreground object is the moving vehicle which
arrives or leaves in vertical direction in each frame.
Nowadays, the application of the lane surveillance
system increases quickly, for example, it is widely
settled at entrance of the high way, the park and the
community to strengthen the traffic management and
survey the public security. Accordingly, the size of the
captured video data increases over time. So, it is quite
important to study how to manage this video data and
how to extract useful information from this large
amount of video data. To a great degree, the
performance of video retrieval depends on the quality
of the shot segmentation; for another thing, it is very
crucial for full description content of shot to accurately
extract the key frame [1]