NSF Org:	CNS Division Of Computer and Network Systems
Recipient:	THE UNIVERSITY OF CENTRAL FLORIDA BOARD OF TRUSTEES
Initial Amendment Date:	August 10, 2021
Latest Amendment Date:	August 10, 2021
Award Number:	2120240
Award Instrument:	Standard Grant
Program Manager:	Jie Yang jyang@nsf.gov  (703)292-4768 CNS  Division Of Computer and Network Systems CSE  Directorate for Computer and Information Science and Engineering
Start Date:	October 1, 2021
End Date:	September 30, 2023 (Estimated)
Total Intended Award Amount:	$77,922.00
Total Awarded Amount to Date:	$77,922.00
Funds Obligated to Date:	FY 2021 = $77,922.00
History of Investigator:	Ryan McMahan (Principal Investigator) rpm@vt.edu Charles Hughes (Co-Principal Investigator) Lori Walters (Co-Principal Investigator)
Recipient Sponsored Research Office:	The University of Central Florida Board of Trustees 4000 CENTRAL FLORIDA BLVD ORLANDO FL  US  32816-8005 (407)823-0387
Sponsor Congressional District:	10
Primary Place of Performance:	The University of Central Florida 4000 CNTRL FLORIDA BLVD Orlando FL  US  32816-8005
Primary Place of Performance Congressional District:	10
Unique Entity Identifier (UEI):	RD7MXJV7DKT9
Parent UEI:
NSF Program(s):	CCRI-CISE Cmnty Rsrch Infrstrc
Primary Program Source:	01002122DB NSF RESEARCH & RELATED ACTIVIT
Program Reference Code(s):	7359
Program Element Code(s):	735900
Award Agency Code:	4900
Fund Agency Code:	4900
Assistance Listing Number(s):	47.070

ABSTRACT

Numerous Computer and Information Science and Engineering (CISE) research communities leverage datasets comprised of visual images or 3D virtual environments to conduct research in computer vision, robotics, multimedia systems, virtual reality, and mixed reality. Many of these datasets consist of either images previously captured with cameras and other optical sensors, or synthetic images previously rendered from 3D virtual environments. The static nature of these datasets limits their usefulness and potential applications. Recently, some researchers have provided datasets and tools for synthesizing new images from 3D virtual environments using customizable virtual camera positions, which broadens their research applications. However, many of these datasets consist of lower-fidelity indoor virtual environments that yield non-photorealistic images. Furthermore, such datasets are missing outdoor virtual environments, and tools for sharing custom camera positions within the research community are not currently available.

This planning project prepares to address the limitations of prior datasets by investigating the feasibility of using high-quality terrestrial laser scanners to capture and create high-fidelity, photorealistic virtual environments of real-world locations, both indoor and outdoor. This will be coupled with surveys of the relevant CISE research communities through workshops held at top academic conferences. This project will result in the development of two preliminary datasets, one indoor and one outdoor, using the proposed laser-scanner methodology, and the identification of community needs, priorities, and support for the proposed InfraStructure for Photorealistic Images and Environment Synthesis (I-SPIES). Undergraduate students will be engaged in the development of the preliminary datasets through the University of Central Florida?s EXCEL STEM program, a former NSF STEP program

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

PROJECT OUTCOMES REPORT

Disclaimer

This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.

Overview

This planning project investigated the feasibility of using high-quality laser scanners to capture and create high-fidelity, photorealistic virtual environments of real-world locations, both indoor and outdoor, for the purposes of proposing a new infrastructure for multiple Computer and Information Science and Engineering (CISE) research communities. The project resulted in the development of two preliminary datasets, one indoor and one outdoor, using the proposed method. The project also resulted in the development of an open-source tool called “RecolorCloud” for editing and improving the colors of 3D point clouds (i.e., sets of colored 3D points representative of real-world objects and environments). Furthermore, four academic workshops on creating synthetic photorealistic images of environments were organized and hosted. Through these workshops, the needs and priorities of four CISE research communities (multimedia, mixed reality, computer vision, and robotics) with regard to the proposed infrastructure were identified. 

Intellectual Merit

This project resulted in the development of a pipeline for synthesizing photorealistic images from high-quality laser scans. This pipeline consists of four steps: 1) cleaning up the point clouds captured by the laser scanners to remove erroneous points and artifacts, 2) segmenting the point clouds into relevant portions (e.g., trees, buildings, etc.), 3) using “RecolorCloud” to edit and correct the colors of the point clouds based on the segments, and 4) using a raytracing computer-graphics rendering method to create photorealistic images from the corrected point clouds.

Broader Impacts

Through this project, we have open sourced a new tool for editing and refining point clouds captured with laser scanners called “RecolorCloud”, which is openly available via GitHub. We have also open-sourced examples of datasets improved with “RecolorCloud” on the Open Science Framework. Finally, this project has directly resulted in the professional development and training of one Ph.D. candidate and one undergraduate student at the University of Central Florida (UCF).

Last Modified: 03/26/2024
Modified by: Ryan P Mcmahan

Image

  

• 

Please report errors in award information by writing to: awardsearch@nsf.gov.