Abstract:

To overcome the shortcoming of the manual detection of illegal parking cars, a surveillance algorithm was developed to detect the illegal parking cars based on the image processing technology. A visual sensor was set at the forbidden parking region of the road to record the video sequence. An adaptive mixed Gaussian model was used to extract the background in the complicated environment. The still objects were detected by the temporal sequence feature of the pixel level. The still vehicles were recognized by the regional feature of the object level to get the illegal car parking information. The autoalarm was realized according to the requirements from the regulation of different forbidden parking regions. The suggested algorithm was validated by the video sequence of the real traffic scenes to be effective.

Key words: engineering of communications and transportation system, intelligent transportation, video surveillance, illegal parking, background model