Along with the development of the digital video
processing technology and the depressed cost of the
storage device, more and more lane surveillance
systems that record mass visual information of
vehicular traffic lane appear, which play a great
important role in lane security and management.
However, it is not quite adaptable to the lane
supervision to use conventional techniques of video
compression in which MPEG4 or H.264 video-coding
standard is usually adopted. There have been many
problems in most of existing lane surveillance systems.
First, there is the conflict between the size of recorded
video data and the efficiency of video retrieval, in the
long run, the size of recorded video data becomes more
and more huge, as a result, it will take much more
effort to process the huge volume of video data, and
accordingly, the efficiency of video retrieval will be
depressed quickly. Second, how to balance the
compression ratio and the quality of image compressed
is another problem, on one hand, the new application
of video surveillance system calls for higher and higher
quality image, on the other hand, with the video
surveillance system enlarging quickly and the video
data exploding rapidly, it is very necessary to elevate
the compression ratio. Under the conditions of current
techniques for video processing, there are only two
choices: either to depress the compression ratio for
higher quality image, or to elevate the compression
ratio for reducing the size of video data recorded in the
memory device, accordingly, we can only get two
results too: we either keep much shot including
redundant information, or lost many key information of
the lane surveillance system. Third, the general video
compression technique adopts uniform compressing
method to the whole image; as a result, much
important information for the lane surveillance systems
will be not clear enough, such as the vehicle-licenseplate
and the portrait of passenger in the vehicle.