A computer vision-based navigation method, device and system for the blind

Abstract

The invention relates to the technical field of computer vision, and specifically discloses a computer vision-based navigation method for the blind, which includes: obtaining image data of the surrounding environment in real time through a camera; processing the image data through an algorithm to obtain the camera pose, object category, and object The position in the image data and the depth information of each pixel; the position of the object in the three-dimensional coordinate system is obtained by integrating the camera pose, the object category, the position of the object in the image data, and the depth information of each pixel, and After the camera pose is processed, the user's walking trajectory is obtained; it is judged whether the user deviates from the walking route, and a prompt message is sent to the user whether there is an obstacle according to the position of the object in the three-dimensional coordinate system. The invention also discloses a blind navigation device and system based on computer vision. The computer vision-based navigation method for the blind provided by the invention can be used conveniently by the blind and has low cost.

Description

technical field [0001] The present invention relates to the technical field of computer vision, in particular to a computer vision-based blind navigation method, a computer vision-based blind navigation device and a computer vision-based blind navigation system including the computer vision-based blind navigation device. Background technique [0002] In recent years, with the improvement of hardware computing speed, deep learning algorithms have developed rapidly and have been widely used in the field of computer vision, such as face recognition, object detection, object tracking and other tasks. In these tasks, both accuracy and speed have surpassed traditional machine learning methods, and scientific and technological personnel are constantly looking for application scenarios, trying to apply these algorithms to actual products. Simultaneous Localization and Mapping (SLAM) technology can simultaneously solve the problem of precise positioning and map reconstruction. Posit...

AI Technical Summary

Problems solved by technology

Such a multi-sensor design increases the manufacturing cost, and the integration of multiple devices is inconvenient for users to carry, which causes difficulties for users and is not conducive to the popularization of this navigation technology.

Images