In order to process huge volume of data efficiently
in video surveillance system, it is very necessary and
important to find out high efficient video retrieval
techniques and advanced video compression
techniques. This paper presents an improved video
compression algorithm for lane supervision, which
considers the implementation of video retrieval at the
stage of video compression. This improved video
compression algorithm combines the following three
parts: shot segmentation based on detection of moving
vehicle; key frame extraction based on vehicle-licenseplate
locating; video compression in which the I frame,
B frame and P frame is decided by the former two
steps.