Vehicle color identification method based on defogging processing and weight blocking

Abstract

The invention discloses a vehicle color identification method based on defogging processing and weight blocking. The method includes the following steps that vehicle images to be identified are collected; preprocessing is conducted on the collected vehicle images; image weight blocking is conducted on the processed images; RGB-to-HSV color spatial switching is conducted on all blocks of images, the images are divided into three independent single channels according to the H component, the S component and the V component, statistics is conducted on column diagrams of different pixels of all the channels, the maximum value in each channel column diagram is found out, the maximum values of the three channels are merged, and the values of the H component, the S component and the V component of the main colors of the blocks of images are obtained respectively; the colors of all the blocking images are searched for, the most common colors in all the blocking images are found out to serve as the alternative colors of the vehicle color, color classification is conducted according to the H value and the V value, and the final vehicle color is determined. The vehicle color identification method has the advantages of being high in accuracy, good in robustness and high in practicability.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a vehicle color recognition method based on defogging processing and weight division, which is not affected by illumination or weather. Background technique [0002] With the rapid development of the economy and the development of road traffic, the number of cars has increased greatly. At the same time, the regulatory problems of cars have become increasingly heavy with the increase in the number of cars. Only relying on manpower can no longer meet the demand. In this case, intelligent transportation systems Came into being. At expressway toll gates, parking lot entrances and exits, and entrances and exits that require vehicle identification, cameras are used to collect vehicle images, and then the collected images are identified for information such as vehicle license plate number, body color, and vehicle logo. Color is an integral part. Some lawbreakers use vehicle...

AI Technical Summary

Problems solved by technology

However, there are still many defects in this method: the recognition efficiency is reduced due to the influence of light, the color of the car body cannot be correctly recognized due to the interference of the color of other items, and the positioning of the region of interest directly affects the result of color recognition. When the positioning is inaccurate, the color recognition will be greatly disturbed

Images