A data-driven water surface reconstruction method and system

A data-driven, water surface technology, applied in the field of image processing and computer vision, can solve the problems of sensitive parameter setting, time-consuming, difficult implementation, etc., achieve good water surface reconstruction effect, high efficiency, and save computing time

Active Publication Date: 2019-03-15
INST OF COMPUTING TECH CHINESE ACAD OF SCI
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] Among the above common methods, the traditional physics-based method requires a large amount of calculation, takes a long time, and is more sensitive to parameter settings. There are certain technical difficulties in the detailed simulation of complex features.
Most of the existing data-driven water surface reconstruction methods require complex data acquisition device design, and have certain requirements for water bodies or require pretreatment, using structured light and predetermined patterns as marks, etc. These requirements can be achieved under indoor conditions. Satisfied, but difficult to implement outdoors

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
  • A data-driven water surface reconstruction method and system
  • A data-driven water surface reconstruction method and system
  • A data-driven water surface reconstruction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] Aiming at the problems existing in the prior art, the present invention proposes a data-driven water surface reconstruction method, including:

[0060] Step 1, acquiring the water surface video, and analyzing the water surface video into a single-frame picture according to the frame rate of the water surface video;

[0061] Step 2, divide the picture into blocks, calculate the reflectance of the water surface in each of the blocks, calculate the information entropy of each of the blocks based on their respective reflectances according to each of the reflectances, and set a threshold , when the information entropy is less than the threshold, subdivide the block corresponding to the information entropy less than the threshold, generate a new block, calculate the information entropy of the new block, until the new block The information entropy is greater than the threshold, and the height field of each block is obtained;

[0062] Step 3, stitching the height field of each...

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 data-driven water surface reconstruction method and system, and relates to the field of image processing and computer vision. The method comprises the steps of acquiring a water surface video, and parsing the water surface video into a single-frame image according to a frame rate of the water surface video; dividing the image into blocks, calculating the reflectivity of the water surface in each block, calculating information entropy of each block based on the reflectivity thereof according to each reflectivity, setting a threshold, when the information is less than the threshold, subdividing the block corresponding to the information entropy less than the threshold into new blocks, calculating the information entropy of each new block until the information entropy of each new block is greater than the threshold, and acquiring the height field of each block; and seaming the height fields of the blocks into a whole.

Description

technical field [0001] The invention relates to the fields of image processing and computer vision, in particular to a data-driven water surface reconstruction method and system. Background technique [0002] In various fields and applications of advertisements, film and television works, large-scale game scenes, and virtual reality, the rendering of natural scenes occupies an extremely important position. The embodiment of the core value of the product, so the realistic simulation of natural scenes has always been a hot spot in computer graphics research. Many domestic fluid simulation researchers are studying how to simulate more realistic fluids in computers, how to draw more realistic fluids and how to make them The simulation speed is faster, and the fluid simulation, especially the rapid modeling of large-scale water surfaces and waves and the realistic scene reconstruction technology have very wide application prospects and high practical application value. However, n...

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 Patents(China)
IPC IPC(8): G06T13/60
CPCG06T13/60
Inventor 朱登明王昱哲魏毅王兆其
Owner INST OF COMPUTING TECH CHINESE ACAD OF SCI
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