Vehicle logo automatic recognition method and system

Abstract

The invention discloses an automatic identification method and system for a vehicle logo. The automatic identification system for the vehicle logo comprises an offline training subsystem and an online identification subsystem. Features of the vehicle logo are extracted by adopting dense scale invariant feature transform (dense-SIFT), and abundant and stable features which are identifiable and discriminative can be extracted from a low-resolution vehicle logo picture; clustering analysis is performed on the dense-SIFT features, and a visual word bank and a K-dimension (KD) tree index are established so as to accelerate computation speed; according to the relevance between the dense-SIFT and visual words, the dense-SIFT is mapped into all visual words for representation to enhance feature descriptiveness; when a visual word histogram is established, a rectangular-ambulatory-plane spatial pyramid is proposed to increase the spatial position information of the features ,and thus, discriminating effect is promoted; and by adopting a support vector machine (SVM) training vehicle logo classifier, vehicle logo identification is realized. The automatic identification system for the vehicle logo disclosed by the invention still has high identification rate on the low-resolution picture, has high robustness on blocking, illumination, weather and shooting angle changes and the like, is short in computation time and has real-time performance.

Description

technical field [0001] The present invention relates to the technical field of automatic vehicle identification, in particular to a method and system for automatic identification of vehicle logos. Background technique [0002] With the rapid development of social economy and road traffic, automobiles have been popularized in a large area, and the number of motor vehicles has increased sharply. On the one hand, the rapid increase of vehicles such as highways and parking lots makes it difficult to count, which increases the difficulty of road traffic management; Traditional road traffic management and public security management usually only rely on human eyes to observe vehicle information, and the efficiency and detection rate are very low. Therefore, the safety automation management of vehicles has become an important problem to be solved urgently. [0003] The automatic identification of vehicles can conveniently and quickly realize a large number of tasks such as easy pa...

AI Technical Summary

Problems solved by technology

However, the four existing methods for vehicle logo recognition have significant limitations.

The template matching method is only suitable for the scene shot by the front of the camera. When the camera is tilted or the image of the vehicle logo is shifted, the accuracy of this recognition method is low and it is not suitable for practical application; the algorithm of the edge histogram method is simple, but different car logos have Similar to the edge histogram, this method has a higher false recognition rate; the feature matching method has a large amount of calculation, is easily affected by light, weather, occlusion, noise, etc., and the system is not robust, and this method increases with the number of vehicle logos The accuracy rate will be reduced; the algorithm of feature training classifier is complicated, the calculation amount is large, the calculation time is long, it is difficult to realize real-time recognition, and it is not suitable for the application of real-time system

Due to the complex urban traffic environment (such as light and weather changes, occlusion, etc.), the vehicle logo recognition system still faces great challenges

Vehicle logo recognition technology has only been developed in recent years, and the current algorithm is still immature. In summary, there are mainly the following difficulties: 1) The accuracy rate is low, and the misrecognition rate of similar car logos is high. The more types of car logos, the higher the recognition accuracy rate. Low; 2) The amount of calculation is large and the calculation time is long, so it is not suitable for real-time system application; 3) The robustness is low, and it is easily affected by environmental factors such as lighting, weather, camera angle, and occlusion

4) Under the condition of low image resolution, the recognition ability is poor

Images