Vehicle color recognition method based on area discrimination

Abstract

The invention relates to a vehicle color recognition method based on area discrimination. The detected complete vehicle image is used as input, a deep learning algorithm framework is adopted, and the color type of a vehicle under recognition is outputted through processing of various steps of vehicle color area discrimination, vehicle color feature extraction and vehicle color judgment, wherein vehicle color area discrimination refers that a main clue area, an auxiliary recognition area and an unrelated area of color recognition in the complete vehicle image are discriminated according to the color information quantity, and the vehicle color features are respectively extracted through accurate detection of the areas so as to realize accurate recognition of the vehicle color. The complete vehicle image is divided into the main clue area, the auxiliary recognition area and the unrelated area of color recognition, the unrelated area is eliminated in the recognition process, and the vehicle color is recognized through combination of the features of the main clue area and the auxiliary recognition area so that the accuracy of vehicle color recognition under a complex monitoring scene can be enhanced.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a vehicle color recognition method in an intelligent traffic system. Background technique [0002] In recent years, computer vision technology (Computer Vision) and its applications have achieved great development, which has greatly stimulated the application requirements of visual image processing in intelligent transportation systems. Realizing vehicle color recognition based on vision technology is exactly the presented against this background. [0003] At present, the existing vehicle color recognition methods are mainly divided into the following two categories. The first type is the color recognition method based on the location of the license plate. First, the license plate is detected on the vehicle, and then the color features of the area near the license plate are extracted, and the color classifier is used for judgment. The second method is to randomly sample the vehic...

AI Technical Summary

Problems solved by technology

[0004] Although these existing methods have taken into account the complexity of vehicle color distribution, there are also obvious disadvantages: in the first method, due to the huge difference in the color distribution near the license plate of different models, the color near the license plate is directly used as the body color. There is a problem of generalization, and this method is not effective for vehicles without license plates; in the second method, when the color of the vehicle to be recognized is not single, the semantic characteristics of the feature will be affected, thereby reducing the color recognition. accuracy rate

[0005] Due to the complexity of the color distribution of motor vehicles, and the color of the body is easily affected by the environment, the existing vehicle color recognition methods are difficult to achieve the ideal vehicle recognition accuracy, and are easily limited by objective factors such as vehicle type.

Images