Three-dimensional data acquisition method, device and electronic equipment

A technology of three-dimensional data and acquisition method, applied in the field of image processing, can solve the problem of slow image processing speed affecting image processing efficiency, etc., and achieve the effect of realizing image processing efficiency and speed improvement.

Active Publication Date: 2018-09-28
JIANGSU HAGONG INTELLIGENT ROBOT CO LTD
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the object of the present invention is to provide a three-dimensional data acquisition method, device and electronic equipment to solve the technical problem in the prior art that the image processing speed is slow and affects the image processing efficiency

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
  • Three-dimensional data acquisition method, device and electronic equipment
  • Three-dimensional data acquisition method, device and electronic equipment
  • Three-dimensional data acquisition method, device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] A method for obtaining three-dimensional data provided by an embodiment of the present invention can be used for contour modeling of objects in the environment, such as figure 1 shown, including:

[0063] S11: Extracting a region image of the target object through a region threshold method according to the image.

[0064] Specifically, the target object image is extracted through the improved area threshold method applicable to various environments, that is, the object requiring contour modeling in the real-time image is extracted using the improved area threshold method.

[0065] As a preferred solution, read the left real-time image of the binocular camera, threshold the depth map obtained by stereo vision, obtain the ROI area of ​​the target, and extract the target by using the area threshold method of the HSV model.

[0066] S12: Perform superpixel segmentation on the region image through the linear iterative clustering SLIC method to obtain a superpixel image of t...

Embodiment 2

[0073] A method for acquiring three-dimensional data provided by an embodiment of the present invention may also be an adaptive object contour modeling method for contour modeling of objects in the environment, such as figure 2 shown, including:

[0074] S21: Obtain a color image through acquisition.

[0075] S22: Segment the color image by dynamically adjusting the segmentation threshold based on the region according to the color model and the depth model, and extract the region image of the target object.

[0076] In practical applications, step S22 specifically includes:

[0077] S221: Perform threshold data screening on the depth map of the color image according to the depth model to obtain a target contour.

[0078] To obtain a depth map for real-time graphics, the disparity map of the real-time image can be obtained through calibration, correction, and matching methods in stereo vision, and the depth map can also be obtained according to the principle of three-dimensi...

Embodiment 3

[0165] A device for obtaining three-dimensional data provided by an embodiment of the present invention, such as Figure 7 As shown, the three-dimensional data acquisition device 3 includes: an extraction module 31 , a segmentation module 32 , and an acquisition module 33 .

[0166] It should be noted that the extraction module 31 is used for extracting the area image of the target object through the area threshold method according to the image. The segmentation module 32 is used to perform superpixel segmentation on the region image through the linear iterative clustering SLIC method to obtain a superpixel image of the target object. The acquisition module 33 is used to obtain the three-dimensional data of the target object through the stereo vision method according to the superpixel image.

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 provides a three-dimensional data acquisition method, device and electronic equipment, and relates to the technical field of the image processing. The three-dimensional data acquisitionmethod comprises the following steps: extracting a regional image of a target object according to an image through a region threshold method; performing super-pixel segmentation on the regional imagethrough a linear iteration clustering SLIC method to obtain a super-pixel image of the target object; and obtaining the three-dimensional data of the target object according to the super-pixel image through a stereoscopic vision method. The technical problem that the image processing efficiency is influenced by slow image processing speed in the prior art is solved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method, device and electronic equipment for acquiring three-dimensional data. Background technique [0002] Image segmentation technology has been widely used in various images such as gray and color natural images, medical images, mineral maps and traffic images. Traditional image segmentation methods mainly include threshold method, boundary detection method, region method and so on. [0003] The image segmentation method based on superpixels refers to the process of integrating the similar parts of the image according to a certain similarity criterion, so as to subdivide the digital image into multiple coherent and easy-to-analyze image regions. Effective information for image segmentation, and generally will not destroy the original image information such as object boundaries in the original image. [0004] At present, for obtaining the relevant data of t...

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): G06T7/11G06T7/90G06K9/62
CPCG06T7/11G06T7/90G06F18/23
Inventor 乔徽张兆东李军王博
Owner JIANGSU HAGONG INTELLIGENT ROBOT CO LTD
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