Road sign detection method and road sign detection device

Abstract

A road sign detection method, comprising: a scene modeling step, respectively determining the allowable range of each color according to sample images of a plurality of scene categories; a color filtering step, determining the scene category of the image to be processed, and using the allowable range of each color , to filter the image to be processed, to obtain the respective binarized images of the image to be processed about each color; the geometric feature filtering step is to perform connected domain analysis on each binarized image, and obtain the connected domains in the binarized image Geometric features, exclude the connected domains whose geometric features do not meet the specifications of road signs, and the remaining connected domains are candidate road signs; the shape detection step, according to a limited number of predetermined shapes, detect the shape of the candidate road signs; the recognition step, for the shape-determined candidate The road sign identifies the attribute of the candidate road sign according to the degree of similarity between the internal features and the standard internal features. A road sign detection device is also correspondingly provided.

Description

technical field [0001] The invention relates to a road sign detection method and a road sign detection device. Background technique [0002] With the development and wide application of Intelligent Transportation System (ITS) technology, the research on road sign detection technology has gradually attracted attention. Since the standards of road signs adopted by countries in the world are basically unified, the road sign detection technology developed for a country's road signs can be applied to other countries without or only with minor adjustments, thus having universal applicability. [0003] At present, some progress has been made in the field of road sign detection technology, for example, many patents or patent applications have been published. [0004] Patent document 1 (US20080002891A1, "Road sign determination approach, method and program") provides a road sign decision-making device. These include: an image recognition unit that performs recognition of image data...

AI Technical Summary

Problems solved by technology

However, the threshold used for color segmentation in this patent is also fixed, so that the accuracy of image segmentation results will inevitably be affected by external light; at the same time, the rough classification based on color-shape pairs is only for the outer contour features of road signs, The internal features of road signs such as internal color and other features are not involved, which will also lead to a relatively high probability of false detection

[0007] The color filtering image segmentation methods for the detection of road signs in the above-mentioned related patents are not adaptive. Even if the concept of rough classification is involved, it is based on a limited set of road signs. Clear, fixed Templates, or based on the concept of color-shape pairs, but do not use the internal features of road signs for further road sign recognition

Images