Automobile classification based on GVF-Snake Model & Inertia Ellipse principle

With the increase of vehicles, the work load and the difficulties of the traffic management and road tolling become harder and harder, and day by day, so the automatic recognition of automobile type has very important real value in the traffic management system and road auto-tolling system. An approach is presented to detect and classify the moving vehicle in static scenes, which is based on GVF-Snake model and inertia ellipse. The difference of two successive traffic-frames was computed, and a Gaussian mixture model (GMM) of the gray-level distribution of the difference image was constructed, whose parameters were estimated by expectation maximization (EM) algorithm. Based on the model, a motion detection operator was introduced to generate a moving vehicle border image. Then, a static vehicle image based on algorithm GVF-Snake, was improved. The energy entry was modified by using the motion border image so that it could be used in video sequences. The image area of the moving vehicle is determined. Finally, the eccentricity of ellipse is calculated and the equivalent of ellipse is formed based on the principal of inertia ellipse of rigid body. All vehicles can be classified into five kinds by fuzzy threshold. As the method is based on statistics, and simple, it can be easily programmed to be applied into the embed system. Experiment results show that it can process 4 road (6~8 roadway) video signals, and has fast process speed and rate of identifying.