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

Depth image partitioning and agent geometry based virtual and real collision interaction method and apparatus

A geometry and depth map technology, applied in the field of augmented reality, to achieve the effect of good application value

Inactive Publication Date: 2015-11-11
BEIJING FORESTRY UNIVERSITY
View PDF3 Cites 52 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method can achieve real-time efficiency, but it is limited to the collision interaction between very specific objects (such as palms) and virtual spheres; there are also real objects simplified to be expressed by planes, and virtual objects to be expressed by enclosing spheres to realize virtual reality Fast collision and interaction between objects, but the real objects require the user to provide prior knowledge in advance to assist in the construction of the virtual plane

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
  • Depth image partitioning and agent geometry based virtual and real collision interaction method and apparatus
  • Depth image partitioning and agent geometry based virtual and real collision interaction method and apparatus
  • Depth image partitioning and agent geometry based virtual and real collision interaction method and apparatus

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] Such as figure 1 As shown, the scene segmentation based on the depth image of the present application further includes the following steps:

[0035] Step 101: Obtain the depth image and color image of the current real scene, and adjust the calibration parameters of the depth camera and the color camera to align the depth image and the color image;

[0036] In this embodiment, Kinect is used to acquire color image information and depth image information of the current real scene. Kinect is a device developed by Microsoft for somatosensory interaction. It can obtain the depth information of the captured scene through an infrared camera, so as to complete the recognition and tracking of human body movements and realize somatosensory interaction. Kinect has pre-calibrated the depth camera and the color camera before leaving the factory, and provides the internal and external parameters of the two cameras, so that the calibration and alignment of the depth image and the col...

Embodiment 2

[0055] combine figure 2 As shown, in the embodiment of the present invention, the preprocessing of the depth image according to the color image further includes the following steps:

[0056] Step 201: According to the alignment relationship between the color image and the depth image, fill the hole pixels in the depth image, and search for the color pixels around the color pixels corresponding to the hole pixels For the pixel with the most matching color, the depth value of the most matching pixel is used as the depth value of the hole pixel.

[0057] In the processing process, the RGB image obtained by Kinect, that is, the color image, is used to fill the hole area. Although the hole position has no depth value, the RGB color information of the pixel corresponding to the hole position is known, so in the RGB image, according to the RGB color of the pixel point corresponding to the hole position, find the most matching color around the hole position pixel, and use the depth...

Embodiment 3

[0062] combine image 3 As shown, in the embodiment of the present application, the obtained depth image of the real scene is segmented by using the region growing method, which further includes the following steps:

[0063] Step 301: According to the current pixel point and its neighboring pixels, use the least squares method to fit a first plane, and use the normal vector of the first plane as the normal vector of the current pixel point.

[0064] In the embodiment of the present application, the local surface fitting method is used to obtain the normal direction: assuming that the surface of the sampled point cloud is smooth everywhere, a plane can be fitted by the least square method according to the neighborhood of the current pixel point, and the plane's The normal is used as the normal vector of the current pixel.

[0065] The least square method, also known as the least square method, is a mathematical optimization technique that finds the best function match for the ...

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

A depth image partitioning and agent geometry based virtual and real collision interaction method and apparatus are disclosed. The application discloses a method for realizing collision interaction of a virtual object and a real object by partitioning a scene in a depth image and constructing agent geometries based on a partitioning result. Firstly, color image information and depth image information of a current real scene are obtained; secondly, normal information in the depth image and connectivity are taken as criterions, the depth image is subjected to regional partitioning with a regional growth method, and on this basis, a main plane region in the scene is identified by utilizing a plane judgment technology of a Gaussian image; thirdly, other point cloud regions except the main plane region are subjected to fusion processing to obtain other main object regions in the scene; fourthly, constructing a virtual plane for an identified main plane and constructing a bounding box for a partitioned object; and finally, superposing the agent geometries onto the real object, endowing the real object with physical attributes, and realizing collision interaction of the virtual object and the real object by simulation. The depth image partitioning method disclosed by the application is quick, effective and more realistic in virtual and real interaction effect.

Description

technical field [0001] The application belongs to the field of augmented reality in computer application technology, and in particular relates to a system and method for segmenting a real scene based on a depth image and simulating the collision and interaction between a virtual object and a real object by constructing a proxy geometry. Background technique [0002] Augmented Reality (AR for short) refers to the superimposition of computer-generated scenes, virtual objects or system prompt information on real scenes, so as to realize the enhancement of reality. The augmented reality system organically combines real world information with virtual information. The two kinds of information are complementary and superimposed, which strengthens people's cognition and perception of the real world. In cognitive training, interactive scene simulation, games, entertainment, advertising, etc. It has important application value in many fields and has become a research and application h...

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
IPC IPC(8): G06T7/00G06T5/00
CPCG06T5/70
Inventor 杨刚黄心渊王祎
Owner BEIJING FORESTRY UNIVERSITY
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