Towards automated semantic 3D reconstruction for immersive city-level environment creation using low-cost overhead images and crowd-sourcing photographs

Abstract

This current process of 3D model generation usually goes to engineering grade LoDmodels, which demands high cost in time and resour"ces. The objective of this research isto combine the low-cost overhead imageries from high-resolution satellite archives andcrowdsourcing images for photorealistic 3D model generation. Both data source providecompensatory advantages and can used for large-scale scene modeling. This project willadvance the state of the art 3D scene modeling and leading to significantly reduced costand fast"er updates. The data generated by the proposed method can be use particularly foraugmented and mixed reality applications, such as"" battlefield training, virtual exploration,situational awareness, and digital documentation of city-scale 3D data.

Document Details

Document Type
DoD Grant Award
Publication Date
Nov 03, 2017
Source ID
N000141712928

Entities

People

  • Rongjun Qin

Organizations

  • Office of Naval Research
  • Ohio State University
  • United States Navy

Tags

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Distributed Systems and Data Platform Development
  • Military Training and Readiness Simulation

Technology Areas

  • Space