Parallel rigid body collision detection method and device based on sparse octree

Abstract

The invention discloses a sparse octree-based parallel rigid body collision detection method and device, and the method comprises the steps: constructing a bounding box tree according to a rigid body to be subjected to collision detection, dividing a generated collision region, and obtaining an index of each small unit space; according to the gravity center of the rigid body to be subjected to collision detection and the index of each small unit space, constructing leaf nodes of a compressed octree; sequencing the generated internal nodes, and generating post-order traversal of the compressed octree; generating the compressed octree in combination with the internal nodes and the post-order traversal of the compressed octree; obtaining intermediate nodes by calculating the depth difference between each node in the compressed octree and a father node thereof, and generating a complete octree; and searching the overlapping region from bottom to top from leaf nodes of the complete octree, and finding leaf node pairs which collide with each other. According to the method, the Z-space filling curve (Z-SFC) is used for effectively linearizing the collision area, so that the calculation overhead is greatly reduced, and real-time detection and calculation of large-scale rigid body collision can be realized.

Description

technical field

[0001] The invention belongs to the field of computer graphics and human-computer interaction, and in particular relates to a parallel rigid body collision detection method and device based on a sparse octree. Background technique

[0002] Octree is a very common data structure in the field of computer simulation and is widely used in collision detection, ray tracing, and simplification of 3D scenes. With the improvement of people's demand for simulation realism and frame rate, more and more simulation algorithms are not satisfied with the calculation of CPU, and start to use GPU to accelerate the solution in parallel. However, although the parallel computing speed of the GPU is relatively fast, the current GPU design architecture does not support recursive algorithms and dynamic memory allocation, resulting in a big difference in the implementation process of some GPU algorithms and CPU algorithms. Many complex data structures and algorithms are not suitabl...

Examples

Embodiment Construction

[0060] In order to make the above objects, features and advantages of the present invention more clearly understood, the present invention is described in detail below through specific implementations and accompanying drawings, but does not constitute a limitation of the present invention.

[0061] The hardware platform of the method of the invention adopts the CPU of the model Intel i7-8700, the main frequency is 3.2GHz, the NVIDIA GeForce GTX 1080Ti graphics card, and the video memory 8GB. The system program is written in C++, and the parallel computing part is accelerated by the CUDA language, and the program is compiled and executed with the help of Microsoft Visual Studio 2017. Open source libraries such as OpenGL and Freeglut are used in the development process.

[0062] The flow chart of the method of the present invention is as follows figure 1 As shown, the whole process is mainly divided into five parts. First, build a bounding box tree (including: AABB tree (axis-p...

technical field

[0001] The invention belongs to the field of computer graphics and human-computer interaction, and in particular relates to a parallel rigid body collision detection method and device based on a sparse octree. Background technique

[0002] Octree is a very common data structure in the field of computer simulation and is widely used in collision detection, ray tracing, and simplification of 3D scenes. With the improvement of people's demand for simulation realism and frame rate, more and more simulation algorithms are not satisfied with the calculation of CPU, and start to use GPU to accelerate the solution in parallel. However, although the parallel computing speed of the GPU is relatively fast, the current GPU design architecture does not support recursive algorithms and dynamic memory allocation, resulting in a big difference in the implementation process of some GPU algorithms and CPU algorithms. Many complex data structures and algorithms are not suitabl...

Examples

Embodiment Construction

[0060] In order to make the above objects, features and advantages of the present invention more clearly understood, the present invention is described in detail below through specific implementations and accompanying drawings, but does not constitute a limitation of the present invention.

[0061] The hardware platform of the method of the invention adopts the CPU of the model Intel i7-8700, the main frequency is 3.2GHz, the NVIDIA GeForce GTX 1080Ti graphics card, and the video memory 8GB. The system program is written in C++, and the parallel computing part is accelerated by the CUDA language, and the program is compiled and executed with the help of Microsoft Visual Studio 2017. Open source libraries such as OpenGL and Freeglut are used in the development process.

[0062] The flow chart of the method of the present invention is as follows figure 1 As shown, the whole process is mainly divided into five parts. First, build a bounding box tree (including: AABB tree (axis-p...

Images