Unlock instant, AI-driven research and patent intelligence for your innovation.

Distributed computing system for 3d reconstruction and 3d reconstruction method

A distributed computing, distributed key-value technology, applied in computing, resource allocation, program control design, etc.

Active Publication Date: 2020-05-22
GUANGZHOU HKUST FOK YING TUNG RES INST
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Thus, unmanned aerial technology makes building data collection easier but challenges the scalability and effectiveness of current 3D reconstruction procedures

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
  • Distributed computing system for 3d reconstruction and 3d reconstruction method
  • Distributed computing system for 3d reconstruction and 3d reconstruction method
  • Distributed computing system for 3d reconstruction and 3d reconstruction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] figure 1 A distributed computing system for 3D reconstruction according to an embodiment of the invention is shown. In this embodiment, the distributed computing system for 3D reconstruction may include a distributed file system 100 and a cluster composed of multiple machines, wherein one of the multiple machines is elected as the master machine 200 and The remaining machines are working machines 300 . Wherein, a plurality of working machines 300 share the distributed file system 100, and the distributed file system 100 is compatible with the portable operating system interface standard, so that existing stand-alone 3D reconstruction programs, such as C++ programs, can utilize its Own standard file API to read and write files, just like using a local disk.

[0033] The main control machine 200 receives a 3D reconstruction project (project) submitted by a user. The 3D reconstruction project is composed of a plurality of jobs (jobs), and each job is composed of a plural...

Embodiment 2

[0037] figure 2 A distributed computing system for 3D reconstruction according to another embodiment of the present invention is shown. In the embodiment of the present invention, the distributed computing system further includes a distributed key-value storage system 400 in addition to the distributed file system 100 , the master computer 200 , and a plurality of working computers 300 . Wherein, the master control machine 200 and the plurality of working machines 300 belong to a cluster composed of a plurality of machines, and a plurality of machines run for the master control machine, while the remaining machines are working machines. In an alternative embodiment of the present invention, such as image 3 As shown, at S300, the plurality of machines put their respective IDs (identifiers) on the master key of the distributed key-value storage system, but only one machine can successfully put the ID into the master on the machine key; at S320, the plurality of machines obta...

Embodiment 3

[0042] In an optional implementation manner of the present invention, the distributed computing system for 3D reconstruction may have the functions, structures, and features described in Embodiment 1 or Embodiment 2 above. In addition, further, the attributes of the job may include job type, task quantity and restriction conditions. The jobs have logical dependencies and IO dependencies. In this way, the master control machine 200 schedules the multiple jobs to run on the multiple working machines 300 according to the logical dependencies and IO dependencies among the jobs. For example, scheduling jobs with IO dependencies to run on the same worker machine. As a result, data locality is improved.

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 a distributed computing system for 3D (three-dimensional reconstruction) and a 3D reconstruction method. The distributed computing system comprises a distributed document system and a cluster composed of multiple machines, one of the machine is selected as a main control computer while the rest machines are operation machines; the machines share the distributed document system, and the distributed document system is compatible with interface standard of a portable operating system; the main control computer dispatches received multiple operation of a 3D reconstruction engineer to the operation machines, and the operation machines operate the received operations to complete 3D reconstruction. By the adoption of the distributed computing system, an existing one-machine 3D reconstruction program can be easily transformed to the cluster with no need of source code modification.

Description

technical field [0001] Embodiments of the present invention relate to a distributed computing system for 3D reconstruction and a 3D reconstruction method. Background technique [0002] Building data collection has become easier with the advent of unmanned aerial technology. A day of flying can collect several Tera Bytes of data. Large-scale three-dimensional (3D) reconstructions, such as urban 3D reconstructions, require massive computing resources, running for weeks to months on typical consumer-grade machines. Moreover, the current 3D reconstruction program is a huge project written in C++, which can only run on a single machine, and is not suitable for the current popular distributed architecture, for example, Hadoop (Hadoop is a distributed system infrastructure developed by the Apache Foundation ) and Spark (Spark is a general parallel framework for Hadoop MapReduce open sourced by UC Berkeley AMP lab (AMP Lab of the University of California, Berkeley)). Because the ...

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): G06F9/50G06F11/30G06F11/20
CPCG06F9/5083G06F11/202G06F11/3006G06F2209/5017
Inventor 戴作卓方天权龙
Owner GUANGZHOU HKUST FOK YING TUNG RES INST