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

Method for predicting collision detection based on neural network

A neural network and collision detection technology, applied in the field of virtual simulation collision detection, can solve the problem of low efficiency of neural network

Active Publication Date: 2021-02-26
ZHONGBEI UNIV
View PDF14 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a method for predicting collision detection based on neural network, aiming to solve the problem that the existing collision detection technology generally improves efficiency through the bounding box algorithm, but considers less in terms of using neural network to improve efficiency. Under the premise of ensuring the authenticity of cloth simulation, the neural network algorithm is used to optimize the efficiency of cloth collision detection, comprehensively considering authenticity and real-time performance, and improving the quality of cloth simulation

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
  • Method for predicting collision detection based on neural network
  • Method for predicting collision detection based on neural network
  • Method for predicting collision detection based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] 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.

[0056] Such as figure 1 As shown, a method for predicting collision detection based on neural network, with neural network as the main content, specifically includes the following steps:

[0057] Step 1, within a time step Δt, the position where the cloth particle motion starts is recorded as The position of the cloth particle after verlet integration is recorded as A data set is composed of the starting position of the cloth particle movement, the position of the cloth particle after verlet integration, and the position of the triangular patch of the model that collides with the cloth particle...

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 belongs to the field of virtual simulation collision detection, and particularly relates to a method for predicting collision detection based on a neural network. The method comprises the following steps: firstly, within a time step length, inputting the movement position of cloth particles and the position of a collided triangle into a neural network; secondly, utilizing a neural network to predict whether cloth particles collide with triangular patches or not; finally, carrying out collision response on the collided particles, and obtaining the final positions of the particles.Compared with a traditional physical collision detection method, the method has the advantages that on the premise that the cloth simulation authenticity is guaranteed, the detection speed of the algorithm is remarkably increased along with increase of the collision detection difficulty, meanwhile, higher stability is shown, and the requirement of a user for real-time performance is met.

Description

technical field [0001] The invention belongs to the field of virtual simulation collision detection, in particular to a method for predicting collision detection based on a neural network. Background technique [0002] The collision detection algorithm is to prevent the penetration of objects in the virtual environment, and it has a wide range of applications in the fields of computer graphics, film and television animation, and virtual reality. Authenticity and real-time performance have always been two key issues in researching collision detection. Authenticity requires that the algorithm can accurately represent the characteristics of objects, and real-time requires that the algorithm has fast computing power. In order to ensure the smoothness of the simulation effect, the cloth needs to complete the collision processing in a short time step. Every movement of the cloth will generate a large number of collision detections with other objects, and the calculation of colli...

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): G06F30/25G06F30/27G06F113/12
CPCG06F30/25G06F30/27G06F2113/12
Inventor 靳雁霞马博马巧梅贾瑶陈治旭芦烨史志儒刘亚变杨晶张建华
Owner ZHONGBEI UNIV
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