Binocular vision positioning method based on semantic target

A binocular vision positioning and target technology, applied in image analysis, instruments, computing and other directions, can solve the problems of high layout cost, inability to locate indoors, low positioning accuracy, etc., to achieve strong autonomy, fast and accurate positioning services, The effect of high positioning accuracy
CN112884841AActive Publication Date: 2021-06-01HARBIN INST OF TECH +1
6 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
HARBIN INST OF TECH
Publication Date
2021-06-01

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a binocular vision positioning method based on a semantic target, and relates to the binocular vision positioning method based on the semantic target. The invention aims to solve the problems that the existing indoor positioning methods need to know the scene layout before positioning, the layout cost is high, the positioning accuracy is low, and indoor positioning cannot be carried out in an unknown environment. The method comprises the steps of 1, acquiring a left image and a right image; 2, identifying semantic targets contained in the current left and right images and angular point coordinates corresponding to each semantic target; 3, selecting, by a user, a common semantic target contained in the left image and the right image in the semantic targets, and building a three-dimensional coordinate system of the target based on the angular point coordinates corresponding to the semantic target; 4, determining corresponding pixel coordinates of the angular point of the selected semantic target in the left image and the right image; 5, calibrating a binocular camera; and 6, solving the position coordinates and the steering angle of the current user relative to the target to realize the positioning of the user. The invention belongs to the field of image processing.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the field of image processing, and is a method for realizing binocular vision positioning based on semantic targets by using technologies such as digital image processing, deep learning, and visual imaging. Background technique

[0002] With the rapid development of the current society, more and more indoor places such as shopping malls, exhibition halls, and office buildings have sprung up, and people spend most of their time indoors every day. And when people enter a completely unfamiliar indoor place, they need to know their current specific location in the place, and hope to get a series of services based on it. Due to the complex and changeable indoor environment and being blocked by obstacles such as walls, traditional GPS technology is not applicable. At present, the positioning methods in the indoor environment are mainly divided into four categories, namely indoor positioning methods based on wireless signals, indoor ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More