Project: #192 Low-Cost 3D model acquisition for rapid accident investigation Progress Report - Reporting Period Ending: Sept. 30, 2019 Principal Investigator: Christoph Mertz Status: Overdue Project Start Date: Aug. 1, 2017 End Date: June 30, 2019 Research Type: Applied Grant Type: Research Grant Program: FAST Act - Mobility National (2016 - 2022) Grant Cycle: 2017 Mobility21 UTC Progress Report (Last Updated: Sept. 27, 2019, 2:29 p.m.) % Project Completed to Date: 100 % Grant Award Expended: 100 % Match Expended & Document: 0 USDOT Requirements Accomplishments In this project we developed several tools to better analyze accidents. They involve shape completing, parts segmentation, unsupervised multi-view stereopsis, and 3D transformer networks. The detailed description and evaluation of these can be found in the publications. The long-term goal is to have a set of tools that can automatically analyze an accident from a set of images. Two students earned their Master's in Robotics through this research. Impacts The results have been published in papers and presented in conferences and a symposium. They contribute to the wider field of computer vision and scene understanding. Other The web page for our accident reconstruction effort is: http://www.cs.cmu.edu/~reconstruction/ Outcomes New Partners Nothing to report Issues We had contact with a facility staging crashes for research and tests, but it was not possible for us to visit the site because of customer restrictions. Because of this the work was more theoretical than experimental.