Research Of Recognition Techniques For Moving Vehicles

The main purpose of recognition system for moving vehicles is to get variant features of vehicle in real-time, such as vehicle-shape, vehicle-logo, vehicle-license-plate and color of vehicle-body. By utilization of optimized recognition algorithms and information fusion techniques, the vehicle's type, and its color and license plate can be automatically recognized.This paper mainly studied three problems, one was the vehicle-plate location method based on rectangle peak value detected, the other one was to provide a timely and robust vehicle-logo location method combining all the advantanges of many of the vehicle-plate location arithmetic, and the last one was to put up with an video detection method based visual-loop to detect traffic parameters such as vehicle-flow, vehicle-speed, vehicle-type and so on.At present, people have provided numerous plate location arithmetic. After comprehensive analysis to various of methods, people have discovered plate recognition was mainly based on plate location, binary image of the plate and character division. The author used the common attributes of plate images to offer a plate location method based on rectangle peak value and further utilized micro-location technology to locate the plate again. Combining template match and characteristics match, we could improve theaccuracy of vehicle-plate recognition efficiency.Compared with vehicle-plate, the vehicle-logo has its own speciality. It is small, similar each other, and is influenced by its size and the light, it lies in different backgrounds and when it belongs to different automobile companies, it is different in size and shape too. So its accurate location is difficult. For the sake of such solutions, a fast and robust method of vehicle-logo location is presented in this paper. By full utilize of the location of vehicle- plate, and its correlation of vehicle-logo and vehicle-head, and by utilize of axis symmetry of vehicle-head, an experimental rough searching rectangle of vehicle-logo can be located. Further on, the vehicle-logo can be accurately located.For a long time, road surface traffic control system has been detected by induction loops imbedded under ground. This traditional detection method is often easy to be influenced by weather conditions or road surface conditions. Moreover, the costs of installation and maintenance of the loops are considerably enormous.This detection method, which based on video, carries through the on/off video frequency by cameras that are installed at high places. The method decreases the influence caused by weather conditions or road surface conditions. Installing and maintaining the cameras will not influence the roads, as well as it improves the reliability of the traffic control system. Compared with the traditional loop detection method, this one saves the cost.This article provided an vedio detection method based on visual loops, and constructed a practical traffic parameter detection system from this. This method is utilized to detected traffic parameters such as vehicle-flow, vehicle-speed and vehicle-type. It improves the accuracy of the system greatly by the technology of overtake-detection. The results indicate this new method has a good effect on video detection and the cost of installation andmaintenance is lower than the traditional one.