Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Feasible region training data set expansion method for mobile robot

A technology for training data sets and mobile robots, applied in the field of data set expansion, can solve problems such as narrow coverage, shorten the cycle, improve the recognition rate, and improve the training effect.

Active Publication Date: 2019-04-05
杭州珈斐猫网络科技有限公司
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Aiming at the problem that the general image database expansion method can only transform images under normal conditions, and the coverage is narrow during expansion, the present invention provides a mobile robot feasible area training data set expansion method, which covers the images that may be photographed under normal and special conditions. images, increasing the richness of the dataset

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0033] Embodiment: a method for expanding a mobile robot feasible region training data set, comprising the following steps:

[0034] Step 1: Use a binocular camera to obtain a rated original image containing topography, and calculate the relative position height between several points on the image, and mark the image with a relative position height difference greater than the rated value; In step 1, the original image includes a variety of different lighting conditions, and includes 10 different topography, and 100 images are collected for each type of topography, and the extraction process of the relative position and height information is: extracting from the image N pixel points subject to uniform distribution, randomly select 9 points from the pixel points, use the depth information of the points in the binocular to calculate their relative positional relationship, and establish a reference plane according to the height average of the above points, Calculate the distance f...

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 a feasible region training data set expansion method for mobile robot, which comprises the following steps of: acquiring a rated original image containing topography and geomorphology by using a binocular camera, and then performing standardization processing on the image, so as to facilitate subsequent data set expansion and transformation, and then performing image transformation expansion. On the basis, expanding image samples obtained under different weather and shooting conditions through image synthesis, increasing rain and snow marks and simulation of infrared rays, and acquiring image samples which can only be collected under many special conditions through conversion. According to the method, the coverage range of the data set is effectively expanded, moretraining samples are added for subsequent machine learning, the period of constructing the data set is remarkably shortened, the cost of constructing the data set is reduced, the training effect of the mobile robot is improved in an auxiliary mode, and the recognition rate of the robot on feasible regions under various special conditions is increased.

Description

technical field [0001] The invention relates to a data set expansion method, in particular to a mobile robot feasible area training data set expansion method. Background technique [0002] The feasible area refers to the area where the mobile robot can walk, and the identification of the feasible area is the prerequisite for the navigation and planning of the mobile robot. The current feasible area identification technology mainly divides the space covered by sensors (such as lidar, vision, etc.) into feasible areas and unfeasible areas. With the development of robot technology, the application field of robots is also expanding, and its working environment is gradually expanding from indoor to outdoor. The difference between the outdoor feasible areas is very large, such as: asphalt road, dirt road, tile road, grass, sand road, etc. Although different feasible areas can walk, they have a great impact on the robot's speed, safety, energy consumption and other indicators. C...

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): G06K9/00G06K9/54G06K9/62
CPCG06V20/10G06V10/20G06F18/22G06F18/214
Inventor 蒋彦敏张波涛仲朝亮王万里吕强吴秋轩
Owner 杭州珈斐猫网络科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com