Unlock instant, AI-driven research and patent intelligence for your innovation.

Semantic description method of ground information

A semantic and terrestrial technology, applied in the field of semantic description of terrestrial information, can solve the problems of increased communication and processing burden, calculation waste, etc., and achieve the effect of avoiding double calculation and reducing communication traffic

Active Publication Date: 2020-12-15
HANGZHOU JINGYI INTELLIGENT SCI & TECH
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, exchanging raw detection data will increase the burden of communication and processing, and perform multiple processing, resulting in waste of calculation

Method used

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
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Semantic description method of ground information
  • Semantic description method of ground information
  • Semantic description method of ground information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The present invention will be further described below in conjunction with accompanying drawing:

[0015] refer to figure 1 -3. A semantic description method for ground information, including a binocular stereo camera set at the front of the mobile robot, with a focal length of f, a baseline width of b, and a height of h. The optical axis of the binocular stereo camera is in line with the The chassis of the mobile robot is parallel, and the total height of the mobile robot is H.

[0016] It also includes a processor connected to the binocular stereo camera, and the processor sets a fast detection method for road conditions, including the following steps:

[0017] (1) The processor obtains the image pair f of the binocular stereo camera L and f R , forming depth information z=f 1 (X,Y), X, Y are pixel coordinates, z is the corresponding depth, X∈(-M / 2, M / 2), Y∈(-N / 2, N / 2), M is the direction in X The number of pixels, N is the number of pixels in the Y direction; th...

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

PUM

No PUM Login to View More

Abstract

The invention discloses a semantic description method of ground information. The method comprises a binocular stereo camera arranged on the front portion of the mobile robot, the focal length is f, the height is h, the optical axis of the binocular stereo camera is parallel to a chassis of the mobile robot, the method further comprises a processor connected with the binocular stereo camera, and the processor sets a pavement condition rapid detection method and comprises the following steps of acquiring the depth information z = f1 (X, Y), wherein the camera coordinate of the projection point is (x, y, z), and calculating x and y; calculating a ground information graph f2 (X, Y) = h-y, and performing binarization to obtain f3 (X, Y); optimizing the binary image f3 (X, Y), and optimizing f2(X, Y) by using the binary image f3 (X, Y); and scanning the ground information graph f2 (X, Y), obtaining the area, the maximum unevenness, the distance and the azimuth angle of an uneven area of theroad surface, and forming a semantic description operator. According to the method, original distance information is refined, and a semantic description operator is formed, so that a mobile robot andother cooperative work robots can use the semantic description operator conveniently..

Description

technical field [0001] The invention relates to a semantic description method of ground information and belongs to the image processing field of machine vision. Background technique [0002] When dealing with complex tasks, the efficiency of multi-robot collaborative work will be significantly improved, and tasks that cannot be completed by a single robot can be achieved. When multi-robots work together, in addition to the decomposition of tasks, the sharing of detection data is also required. For example, due to various reasons, robot A and robot B are equipped with different environmental perception sensors, robot A is equipped with a binocular stereo camera, and robot B The robot is equipped with infrared and ultrasonic sensors, so the detected data has different accuracy and range. The exchange of detection data between two robots can greatly make up for the lack of their own sensors. However, exchanging the original detection data will increase the burden of communicat...

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

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/593G06T7/60
CPCG06T7/60G06T2207/10012G06T2207/20036G06T7/593
Inventor 刘瑜
Owner HANGZHOU JINGYI INTELLIGENT SCI & TECH