Method and system for dynamic identification and location of charging pile based on Kinect

A technology of dynamic identification and positioning method, which is applied in the field of mobile robots, can solve the problems of serious impact of light conditions and lack of universality, and achieve the effects of not being easily disturbed by light, stable dynamic tracking, and accurate recognition

Active Publication Date: 2018-01-16
斯坦德机器人昆山有限公司
View PDF6 Cites 32 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In terms of algorithms, in many cases, the recognition of objects in the scene is based on the color information of the object

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
  • Method and system for dynamic identification and location of charging pile based on Kinect
  • Method and system for dynamic identification and location of charging pile based on Kinect
  • Method and system for dynamic identification and location of charging pile based on Kinect

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] like figure 1 As shown, the present invention discloses a Kinect-based charging pile dynamic identification and positioning method, comprising the following steps:

[0060] Step 1: according to the three-dimensional point cloud data that Kinect sensor obtains, calculate camera coordinate system to the conversion matrix of setting world coordinate system;

[0061] Step 2: obtain color and depth images by Kinect, and align the pixels in color maps and depth maps one by one;

[0062] Step 3: Remove invalid pixels from the image obtained in step 2, convert the remaining pixels into a three-dimensional point cloud and remove points higher than 50cm or lower than 3cm;

[0063] Step 4: the down-sampling of the point cloud obtained in step 3 to reduce the amount of calculation for subsequent processing, and carry out radius filtering to the point cloud to remove outliers;

[0064] Step 5: the point cloud that step 4 obtains is carried out Euclidean clustering, obtains one or ...

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 invention provides a method and system for dynamic identification and location of a charging pile based on Kinect. The method comprises: the step 1: calculating a conversion matrix from acamera coordinate system to a setting world coordinate system according to three-dimensional point cloud data obtained by a Kinect sensor; the step 2: performing one-to-one alignment of pixels in a color map and a depth map; the step 3: removing invalid pixel points in an image obtained in the step 2, converting residual pixel points to three-dimensional spatial points and eliminating points higher than 50cm or lower than 3cm; the step 4: performing downsampling of point cloud obtained in the step 3 to reduce computing amount of follow-up processing, and performing radius filtering to remove outliers; the step 5: performing Euclidean cluster of the point cloud obtained in the step 4 to obtain one or more than one cluster objects; the step 6: processing the one or more than one cluster objects obtained in the step 5, and screening cluster objects having two feature planes; the step 7: processing a cluster body screened in the step 6, and calculating whether a geometrical relationship between two feature planes accords with a three-dimensional shape of a charging pile or not; and the step 8: performing calculation in geometry according to relative position of the two feature planes determined in the step 7, determining a position and an angle of deflection of the charging relative to an original point of the world coordinate system, and realizing location of the charging pile. The method and system for dynamic identification and location of charging pile based on the Kinect have the advantages of accurate recognition, strong robustness, stable dynamic tracking, less susceptible to light interference and the like, and the positioning of the target is small in calculation amount and accurate in calculation result, etc.

Description

technical field [0001] The invention relates to the technical field of mobile robots, in particular to a Kinect-based charging pile dynamic identification and positioning method and system. Background technique [0002] With the rapid development of mobile robot technology, heavy and single physical labor in society, such as handling, inspection, etc., is gradually undertaken by various mobile robots. In order to further liberate the labor force and increase the degree of industrial automation, these mobile robots need to have the ability to automatically recharge. However, the existing autonomous positioning methods for robots are limited by sensors and environmental factors, and it is difficult to achieve the accuracy of autonomous charging, which puts forward requirements for accurate identification and positioning of charging piles by robots. [0003] In terms of sensors, industrial cameras and lidar are commonly used in robot vision systems for identification and posit...

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
IPC IPC(8): G06T7/73G06K9/00G06K9/62
Inventor 仲星光王永锟钟上焜
Owner 斯坦德机器人昆山有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products