This paper deals with a new codec based on the JPEG 2000 standard that will use a market hardware codec in order to build a road surveillance device. The developed coder consists in 4 processing steps, namely construction of a reference image, foreground extraction (ROI mask), encoding with JPEG 2000 and transmission through a wireless device. A …rst order recursive …lter is used to build a reference image that corresponds to the background image and the updated reference image is computed according to a mixture of Gaussians model. The system builds a reference image and transmits it towards a decoder through the GSM network. After the initialization phase, the reference image is updated automatically according to a Gaussian mixture model, and when the ROI can be considered as null, a piece of the updated background image is sent. We perform motion detection in order to extract a binary mask. The motion mask gives the region of interest for the system. The current image and the motion mask are coded using the ROI option of JPEG 2000 codec with a very low bit rate and transmitted towards the decoder. The complete scheme is implemented and it reaches the expected performances. We also showed how the local background image is built and updated at each frame. We presented the strategy in order to update smoothly the remote background image. The implementation runs at 5-8 frames per second on a 1.8 GHz AMD processor for 320x240 color images.