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

A method and device for constructing a visual point cloud map

A construction method and map technology, applied in the field of navigation and positioning, to achieve good adaptability and stability, avoid jumping problems, and reduce the effect of relocation occurrence probability

Active Publication Date: 2022-06-03
HANGZHOU HIKROBOT TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In terms of input, before the robot runs, there is no special input. When it starts running, there are sensor raw data. In terms of output, the estimated pose and estimated map; that is, when building a new map model or improving a known map At the same time, positioning the robot on the map model is similar to the process of putting a person in an unfamiliar city and making the person familiar with the environment. It can be seen that the existing SLAM map construction usually couples the mapping problem and the positioning problem in the Together, the two influence each other

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
  • A method and device for constructing a visual point cloud map
  • A method and device for constructing a visual point cloud map
  • A method and device for constructing a visual point cloud map

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] Step 1011, according to the distortion coefficient of the camera, the source image is de-distorted to obtain the de-distorted image I(u,

[0045] For example, if the maximum pixel value is 255, the inversion operation is: 255-1(u, v).

[0055]

[0057] Image preprocessing is beneficial to improve the contrast of the image, and in some environments with weak texture information, it is beneficial to improve the contrast of the image.

[0061] In step 1022, the FAST feature points are screened to effectively control the scale of the feature points. In order to ensure the feature points

[0062]

[0063] Wherein, the symbol indicates rounded down.

[0073] The key frame condition can also be one of the following conditions:

[0074] The spatial distance with the previous key frame is greater than the set second threshold;

[0075] The space angle between the previous key frame is greater than the set third threshold;

[0082] The z coordinate is the camera installation height. ...

Embodiment 2

[0093] Step 301, according to the distortion coefficient of the camera, the source image is subjected to de-distortion processing to obtain the de-distorted image I(u,

[0104] The number of matching feature points is greater than the set first threshold;

[0105] The spatial distance with the previous key frame is greater than the set second threshold;

[0106] The space angle with the previous key frame is greater than the set third threshold;

[0110]

[0112] Substitute the normalized plane coordinates of eight pairs of matching feature points, and the essential matrix can be solved. Among them, the current keyframe matches

[0115]s

[0117] or,

[0119]s

[0124] The z coordinate is the camera focal length.

[0127] Y=s

[0128] Z=f

[0129] where f is the focal length of the camera to convert the normalized plane coordinates into the imaging plane.

Embodiment 3

[0137] The specific processing is the same as step 301 to step 304,

[0141] The specific matching method is the same as step 307.

[0144] The number of matching feature points is greater than the set first threshold;

[0145] The spatial distance with the previous key frame is greater than the set second threshold;

[0146] The space angle between the previous key frame is greater than the set third threshold;

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 present application discloses a method for constructing a visual point cloud map. The method includes: performing feature extraction on the source image frame collected in the space of the map to be built, obtaining feature points of the source image frame, and performing inter-frame tracking on the source image frame, Determine the key frame, match the feature points in the current key frame with the feature points in the previous key frame, get the matching feature points of the current key frame, calculate the spatial position information of the matching feature points in the current key frame, and match the feature points The spatial position information of is used as the map point information of the current key frame, wherein the point cloud formed by the set of map points of all key frames is the first visual point cloud map. The process of constructing the map in the present invention separates the mapping and positioning, effectively eliminates the mutual influence between the mapping and positioning, and has better adaptability and stability in complex and changeable environments.

Description

Method and device for constructing visual point cloud map technical field [0001] The present invention relates to the field of navigation and positioning, in particular, to a method for constructing a visual point cloud map. Background technique Building a map and positioning is a key technology in real-time positioning and mapping (SLAM) research, and building a map is a The prerequisite for positioning, the quality of the map directly affects the accuracy of positioning. The visual point cloud map is in the constructed map One, which describes the visual, pose and other information of the points in the environment through the three-dimensional point set in the space. Therefore, a visual point cloud is constructed. Maps require two types of data information: keyframes and map points, where keyframes describe the vision of points in the environment, and map points describe the vision of points in the environment. The pose of the point is described, and the set forme...

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): G01C21/32G06K9/62G06V10/74G06V10/24G06V20/40G06F16/29
CPCG01C21/32G06F16/29G06V20/46G06V20/62G06F18/22
Inventor 易雨亭李建禹龙学雄党志强
Owner HANGZHOU HIKROBOT TECH CO LTD