Research on visual background extractor to identify the vehicles based on edge similarity

By combining visual background extractor with Canny operator, a new approach to identify vehicles in a complex traffic environment is proposed. Firstly, the foreground object is extracted by ViBe algorithm and background difference algorithm, then the 'ghost' is removed by means of edge similarity. Next, the complete moving objects can be obtained by using morphological processing for the foreground object, which can be used to detect vehicles by combining with motion analysis. Experiments showed that the whole region of the vehicle object in a complex traffic environment can be extracted exactly and effectively by using this method. In addition, problems due ghosts and the variation of background can be well handled with low computation complexity, which can fulfil the needs of real-time operation.