Indoor mobile robot-based object recognition method

A mobile robot and object recognition technology, which is applied in the field of indoor robot object recognition, can solve problems such as misjudgment, affect the accuracy and reliability of object recognition, and the matching algorithm is not very accurate, so as to improve computing efficiency and shorten recognition and judgment. time, the effect of reducing the calculation time

Active Publication Date: 2018-11-02
深圳市丰巨泰科电子有限公司
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, because this method only extracts feature vectors and matches the feature vectors, the matching algorithm is not very accurate, which often causes misjudgment and affects the accuracy and reliability of object recognition.

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
  • Indoor mobile robot-based object recognition method
  • Indoor mobile robot-based object recognition method
  • Indoor mobile robot-based object recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0028] figure 1 As shown, it is the specific process of the indoor mobile robot object recognition method realized by the present invention. First, it is necessary to detect the local features, that is, the key points, of the target image in the application scene, and the detected local feature neighborhood small blocks (key points feature) through a series of random transformations to generate training samples, and finally generate a random fern classifier; in the online recognition stage, the local features detected in the scene image are classified by the classifier obtained by offline training....

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 an indoor mobile robot-based object recognition method. The method comprises the following steps of: firstly detecting local features of a target image, carrying out a series of random transformation on detected local feature neighbor small blocks to generate training samples, and finally generating a random fern classifier; and in a linear recognition stage, classifying local features detected in a scene image through a classifier obtained via offline training, wherein the classification process is a process of matching local features in the target image; carrying outsecondary matching on matched points; calculating a transformation homographic matrix; and rejecting mistaken matching and finally recognizing a target object in the scene. The method is capable of correctly recognizing and judging objects, and is stable and reliable in recognition and judgement.

Description

technical field [0001] The invention belongs to the technical field of robots, in particular to an object recognition method for an indoor robot. Background technique [0002] A robot is a machine device that performs work automatically. It can accept human command, run pre-programmed programs, and act according to principles formulated with artificial intelligence technology. Its mission is to assist or replace human work in jobs such as manufacturing, construction, or hazardous jobs. With the improvement of the technical level at any time, the intelligence of the robot is getting higher and higher, and it has gradually entered the daily work and life of people. [0003] For robots, an important technical problem is to recognize and judge objects so as to execute control instructions. It is found through research that object recognition in real scenes can be directly completed through two-dimensional images guided by prior knowledge. The process of deriving a three-dime...

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): G06K9/00G06K9/46G06T3/00
CPCG06T3/0075G06V20/00G06V10/44G06V2201/07
Inventor 谢锋
Owner 深圳市丰巨泰科电子有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap