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

Object-oriented multi-level interpretation method and system for live-action three-dimensional model

A three-dimensional model, object-oriented technology, applied in computational models, 3D modeling, character and pattern recognition, etc., can solve problems such as poor classification results and loss, improve accuracy and robustness, and reduce the difficulty of interpretation. , Improve the effect of salt and pepper noise

Pending Publication Date: 2020-10-09
SHENZHEN UNIV
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Therefore, the technical problem to be solved by the present invention is to overcome the defects in the prior art that the classification results are poor due to the phenomenon of information loss in the interpretation process of the real-scene 3D model, thereby providing an object-oriented multi-level interpretation of the real-scene 3D model. translation method and system

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
  • Object-oriented multi-level interpretation method and system for live-action three-dimensional model
  • Object-oriented multi-level interpretation method and system for live-action three-dimensional model
  • Object-oriented multi-level interpretation method and system for live-action three-dimensional model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] An embodiment of the present invention provides an object-oriented multi-level interpretation method for a real-scene 3D model, such as figure 1 shown, including the following steps:

[0050]Step S1: Divide the 3D model of the real scene to be interpreted into two levels: the terrain surface part and the three-dimensional object part. In the embodiment of the present invention, the cloth simulation filter (Cloth Simulation Filter, CSF) algorithm is used to divide the three-dimensional model of the real scene to be interpreted into two levels: the terrain surface part and the three-dimensional object part. The terrain surface part in the embodiment of the invention refers to After removing the ground objects (such as trees, buildings, municipal facilities, etc.) above the ground in the entire real-world 3D model, the relatively undulating areas left behind, such as surface grasslands and gentle slopes, do not block other ground objects when changing the viewing angle Th...

Embodiment 2

[0092] Embodiments of the present invention provide an object-oriented real scene three-dimensional model multi-level interpretation system, such as image 3 shown, including:

[0093] The real-scene 3D model layering module 1 is used to divide the real-scene 3D model to be interpreted into two levels: terrain surface part and three-dimensional object part. This module executes the method described in step S1 in Embodiment 1, which will not be repeated here.

[0094] The terrain surface part classification module 2 is used for classifying the terrain surface part by using an object-oriented image classification method based on the orthophoto image of the terrain surface part. This module executes the method described in step S2 in Embodiment 1, which will not be repeated here.

[0095] The three-dimensional feature part classification module 3 is used to perform independent feature singulation processing on the three-dimensional feature part, and use machine learning algorit...

Embodiment 3

[0099] An embodiment of the present invention provides a computer device, such as Figure 4 As shown, the device may include a processor 51 and a memory 52, wherein the processor 51 and the memory 52 may be connected via a bus or in other ways, Figure 4 Take connection via bus as an example.

[0100] The processor 51 may be a central processing unit (Central Processing Unit, CPU). Processor 51 can also be other general processors, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or Other chips such as programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above-mentioned types of chips.

[0101] As a non-transitory computer-readable storage medium, the memory 52 can be used to store non-transitory software programs, non-transitory computer-exe...

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 discloses an object-oriented multi-level interpretation method and system for a live-action three-dimensional model. A to-be-interpreted live-action three-dimensional model is divided into a terrain surface part and a three-dimensional ground object part; the terrain surface part is classified by adopting an object-oriented image classification method based on the orthoimage of the terrain surface part; independent ground object monomerization processing is carried out on the three-dimensional ground object part, and based on the characteristics of independent ground object monomers, a machine learning algorithm is adopted to classify the three-dimensional ground object part; and classification results of the terrain surface part and the three-dimensional ground object part are integrated to obtain an interpretation result of the whole live-action three-dimensional model. According to the method, the live-action three-dimensional model is divided into two layers to be classified respectively, so that the model interpretation difficulty is reduced; an object-oriented model interpretation method is adopted, so that other salt and pepper noise phenomena generated in a classification process based on a patch algorithm can be improved; based on a multi-dimensional feature fusion strategy of geometry, texture and spectrum, the accuracy and robustness of a classificationresult are improved.

Description

technical field [0001] The invention relates to the field of computer vision and three-dimensional model processing, in particular to an object-oriented multi-level interpreting method and system for a real-scene three-dimensional model. Background technique [0002] In recent years, with the rapid development of computer vision and oblique photogrammetry technology, the real-world 3D modeling of the observation area using multi-view images has become more and more mature. Real-scene 3D models can very intuitively reflect the body structure, texture characteristics, spectral characteristics, etc. of ground objects, and have richer data dimensions than traditional remote sensing images, so they have been gradually applied in smart cities, disaster monitoring, ecological protection and other fields and shows great potential. [0003] However, the increase in data observation dimension does not directly bring about the increase of available information. Although the oblique ph...

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): G06T17/00G06K9/62G06N20/00
CPCG06T17/00G06N20/00G06T2200/04G06F18/23G06F18/24G06F18/253
Inventor 胡忠文刘志刚汪驰升张德津邬国锋李清泉
Owner SHENZHEN 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

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