Plane and barrier detection method based on RGB-D camera and attitude sensor

Abstract

The invention discloses a plane and barrier detection method based on an RGB-D camera and an attitude sensor, and the method achieves the environmental three-dimensional information recognition with higher resolution, higher refresh rate and higher precision based on the RGB-D camera and the attitude sensor. The method can achieve the recognition of a ground passage, the judgment and early-warning of a ground cavity and various types of barriers and the recognition of scenes of going upstairs and downstairs, and is close to the visual sensing of an environment. Through the cooperation of the attitude sensor, a whole system is more flexible and portable, and the camera does not need to keep a fixed relative position with a user or any other ground reference object. When a visually-impaired person goes out, the camera can be placed at any body part which can photograph a three-dimensional environment. A portable computer or pad compatible with the RGB-D camera can be selected by himself or herself to achieve the same function.

Description

technical field [0001] The invention belongs to the technical fields of three-dimensional environment recognition and assistance for the blind, and relates to a plane and obstacle detection method based on an RGB-D camera and an attitude sensor. Background technique [0002] Visual information is the most important source of information for humans to recognize the surrounding environment, and about 80% of the information obtained by humans is input from the visual system. For blind people who lack visual perception, traditional tools such as canes and guide dogs cannot provide them with sufficient assistance. Since the middle of the last century, many researchers have devoted themselves to the development of electronic assistive technology for the blind. The main function of electronic assistive technology for the blind is to provide access prompts and danger warnings for the visually impaired. [0003] According to the different means of detecting the three-dimensional en...

AI Technical Summary

Problems solved by technology

First of all, the feature point extraction and matching algorithms for obtaining 3D depth information are relatively complex, and the effective points obtained in the field of view are less and the accuracy is limited; secondly, it has high requirements for computing performance and storage of the processing module, and it is difficult to integrate

Images