Intelligent vehicular visual global positioning method based on ground texture

Abstract

The present invention provides an intelligent vehicular visual global positioning method based on ground texture and is belongs to the technical field of mobile robot. The method of the invention comprises the following steps: 1. establishing a ground texture map of the whole environment and storing in a system; 2. transmitting an image signal shot by a camera to an upper processing unit through adata wire and an image collecting program; 3. executing image processing by the upper processing unit, and extracting the texture information in the image for forming a partial ground texture map; 4.using the mileage information of the intelligent vehicle for reducing the searching matching range of the partial map in the global map; and 5. executing searching matching between the present partial ground texture map and the global ground texture map in the range defined by the step 4. The intelligent vehicular visual global positioning method based on the ground texture according to the invention has the advantages of simple structure, low cost and convenient maintenance.

Description

[0001] The present invention is based on the patent application number: 200710036550.9, the name of the patent application is: Ground texture-based smart car vision device and its global positioning method, the patent applicant is: Shanghai Jiaotong University, the patent application date: January 18, 2007 Patent division application. Technical field [0002] The invention relates to a device and method in the technical field of mobile robots, in particular to a visual global positioning method of a smart car based on ground texture. Background technique [0003] The self-positioning problem of smart cars means that smart cars use sensor information to estimate their own pose (position and posture) in the operating environment. The first thing encountered in practical applications is the positioning problem, which is a prerequisite for the realization of smart car navigation. At present, the main positioning methods include positioning based on magnetic signals and positioning ba...

AI Technical Summary

Problems solved by technology

Therefore, if it is in a relatively complex outdoor environment, feature extraction is more difficult, the method described in the article is not applicable

and the text does not mention the robustness of the method to environmental changes

[0006] Another major problem with vision-based methods is that when environmental conditions such as lighting, shadows change, or when the front of the camera is blocked, the system is likely to fail to operate normally, that is, it cannot show strong robustness to environmental changes.

Images