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

Object characteristic identifying method, visual identifying device and robot

A recognition method and object technology, applied in the field of visual recognition, can solve problems such as the difficulty of recognizing objects by machines, and achieve the effect of accurate recognition

Active Publication Date: 2019-04-16
SHENZHEN DORABOT ROBOTICS CO LTD
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] This application relates to a method for recognizing object features, a visual recognition device and a robot to solve the problem that machines in the prior art are difficult to recognize objects

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
  • Object characteristic identifying method, visual identifying device and robot
  • Object characteristic identifying method, visual identifying device and robot
  • Object characteristic identifying method, visual identifying device and robot

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific embodiments described here are only used to explain the present application, but not to limit the present application. In addition, it should be noted that, for the convenience of description, only some structures related to the present application are shown in the drawings but not all structures. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of this application.

[0018] see figure 1 , figure 1 It is a flow chart of an embodiment of the object feature recognition method of the present application. The method disclosed in this embodiment may specifically include the following steps:

[0019] S11: Obtain fi...

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

Object characteristic identifying method comprises following steps: obtaining first description information of an object and second description information of environment where the object stays; according to the first description information, obtaining reference information; according to the second description information and reference information, obtaining characteristic data, which meets a first condition, of the first description information; wherein the first condition comprises first incidence relation composed of all characteristic data and the second description information, and according to obtained characteristic data, determining the characteristic surface so as to identify the object accurately. The invention also relates to a luggage handle recognition method, a visual identifying device, and a robot.

Description

technical field [0001] The present application relates to the technical field of visual recognition, in particular to a method for recognizing object features, a visual recognition device and a robot. Background technique [0002] The existing mainstream vision technology adopts the method of machine learning, and uses a large amount of data to train a specific model. First, a large amount of data is collected for manual labeling, and then the labeled data is handed over to the machine learning program for training. [0003] However, there are some disadvantages in existing machines learning by using supervised learning methods: machine learning requires a large amount of training data to support, data collection and labeling require a lot of labor costs, and collection requires the cooperation of volunteers. A large amount of manual data classification is required; machine learning is prone to overfitting, that is, the performance of the trained situation is very accurate, ...

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 Applications(China)
IPC IPC(8): B25J9/16B25J19/04
CPCB25J9/1697B25J19/04
Inventor 吴启帆
Owner SHENZHEN DORABOT ROBOTICS CO LTD