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

A space environment recognition method and system for robot intelligent service

A technology of spatial environment and recognition method, applied in the field of robotics, can solve the problems of inaccurate definition, inaccurate spatial recognition, and failure to consider the attributes of image objects, and achieve the effect of improving recognition ability, efficient and accurate recognition

Active Publication Date: 2021-05-07
SHANDONG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The inventors of the present disclosure found that (1) most of the existing space recognition methods simply recognize the image without considering the attributes of the items in the image, which leads to inaccurate space recognition and cannot well define the properties of each item in the space (2) The existing recognition algorithm is mainly based on the neural network algorithm, which realizes the feature extraction of the image and then realizes the recognition of the object in the image, but there are few studies on the relative position relationship in the specific image, which cannot be effective The relative positional relationship between items in the expression space of

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 space environment recognition method and system for robot intelligent service
  • A space environment recognition method and system for robot intelligent service
  • A space environment recognition method and system for robot intelligent service

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] Such as Figure 1-3 As shown, Embodiment 1 of the present disclosure provides a space environment recognition method for robot intelligent service, including the following steps:

[0034] Acquiring at least one image of the space environment area to be identified;

[0035] According to the acquired image, the preset visual relationship acquisition model is used to obtain the feature of the item in the image and the relationship feature between the items, and the triplet feature of the item in the image is obtained, and then the triplet of the visual relationship of the item in the image is obtained;

[0036] According to the characteristics of the obtained items, use the preset attributes to obtain the model, and obtain the attributes of each item;

[0037] According to the obtained visual relationship triplets of each item and the attributes of each item, a multi-relationship diagram of items in the current image is obtained;

[0038] Process each image of the acquir...

Embodiment 2

[0081] Embodiment 2 of the present disclosure provides a space environment recognition system for robot intelligent service, including:

[0082] The data acquisition module is configured to: acquire at least one image of the space environment area to be identified;

[0083] The visual relationship triplet acquisition module is configured to: according to the acquired image, adopt the preset visual relationship acquisition model to acquire the feature of the item in the image and the relationship feature between the items, and obtain the triplet feature of the item in the image, and then Get the visual relationship triplet of the item in the image;

[0084] The item attribute acquisition module is configured to: obtain the attributes of each item by using the preset attribute acquisition model according to the acquired item features;

[0085] The item multi-relationship map acquisition module is configured to: obtain the item multi-relationship map in the current image accordi...

Embodiment 3

[0089] Embodiment 3 of the present disclosure provides a medium on which a program is stored, and when the program is executed by a processor, the steps in the method for recognizing a space environment for robot intelligent services described in Embodiment 1 of the present disclosure are implemented.

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 disclosure provides a space environment recognition method and system for robot intelligent service, which belongs to the field of robot technology, and obtains at least one image of the space environment area to be recognized; according to the obtained image, adopts a preset visual relationship to obtain a model , to get the visual relationship triplet of the items in the image; according to the obtained item characteristics, use the preset attribute to acquire the model, and get the attributes of each item; according to the obtained visual relationship triplet of each item and the attributes of each item, get the current The item multi-relationship map in the image; each image of the environment area to be recognized is processed to obtain the item multi-relationship map, and the semantic visual space of the robot is constructed according to the obtained item multi-relationship map of each image, so as to realize the recognition of the space environment; this disclosure By constructing relational triples, the relationship between items in the space and the relationship between items and attributes is obtained, which greatly improves the ability to recognize the environment of the space.

Description

technical field [0001] The present disclosure relates to the technical field of robots, in particular to a space environment recognition method and system for robot intelligent services. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art. [0003] When robots serve intelligently, they need to be able to understand the environment at the semantic level, especially to map the environment to the semantic space in terms of vision, strengthen the cognitive intelligence of the robot, and better analyze tasks. [0004] The inventors of the present disclosure found that (1) most of the existing space recognition methods simply recognize the image without considering the attributes of the items in the image, which leads to inaccurate space recognition and cannot well define the properties of each item in the space (2) The existing recognition algorithm is ma...

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): B25J9/16B25J11/00
CPCB25J9/1602B25J9/1697B25J11/008
Inventor 吴皓马庆焦梦林
Owner SHANDONG UNIV