You are here

MAP-Tk: Motion Imagery Aerial Photogrammetry Toolkit

Award Information
Agency: Department of Defense
Branch: Air Force
Contract: FA8650-14-C-1820
Agency Tracking Number: F131-151-0505
Amount: $749,991.00
Phase: Phase II
Program: SBIR
Solicitation Topic Code: AF131-151
Solicitation Number: 2013.3
Timeline
Solicitation Year: 2013
Award Year: 2014
Award Start Date (Proposal Award Date): 2014-09-11
Award End Date (Contract End Date): 2016-12-12
Small Business Information
28 Corporate Drive
Clifton Park, NY 12065-8688
United States
DUNS: 000000000
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: No
Principal Investigator
 Matthew Leotta
 R&D Engineer
 (518) 371-3971
 matt.leotta@kitware.com
Business Contact
 Vicki Rafferty
Title: Contracts Administrator
Phone: (518) 371-3971
Email: contracts@kitware.com
Research Institution
 Stub
Abstract

ABSTRACT: Kitware proposes MAP-Tk, the open-source Motion imagery Aerial Photogrammetry Toolkit, designed for optimized sparse bundle adjustment (SBA) of FMV and WAMI. The software will use aerial video imagery to accurately estimate the pose and path of the camera as well as a sparse point cloud of 3D structure, even when GPS is denied. Our proposed toolkit has a highly configurable and modular design supporting interchange of implementations for algorithms such as feature detection, description, correspondence, and SBA. Our Phase 1 work was highly successful, and in Phase 2 Kitware will continue this work by creating an online processing mode and pushing the performance toward real-time. Accuracy and speed will continue to improve through advancements in algorithms as well as GPU and multithreaded parallel processing. Additionally, Phase 2 will add new features such a graphical user interface (GUI), a Python scripting interface, mosaic image generation, and geographic registration to reference imagery. MAP-Tk has great potential in both the military and commercial UAS markets. Applications range from mapping crop damage in precision agriculture to 3D terrain modeling to autonomous GPS-denied navigation. BENEFIT: The primary benefit of the proposed work is a solution to problem of camera calibration from motion imagery that is far faster and more accurate than the existing state-of-the-art. This solution will reduce reliance of intelligence, surveillance, and reconnaissance (ISR) systems on inertial navigation and global positioning, which are often unreliable or unavailable. Likewise, it will have the same benefit for commercial mapping applications that rely on aerial video for mapping and 3D urban modeling. The commercial applications of the proposed work center on the emerging civil unmanned aerial systems (UAS) market. The proposed work will enable UAS technology and services companies to integrate a readily customizable toolkit to provide their customers with more accurate mosaicking and 3D models from FMV and WAMI video coupled with UAS flight paths. This technology will benefit the range of customers leveraging UAS, including precision agriculture; security and monitoring for public safety; exploration, aid efforts, and disaster recovery; journalism, filmmaking, and entertainment; and environmental monitoring.

* Information listed above is at the time of submission. *

US Flag An Official Website of the United States Government