Project: #304 Image Processing Approaches to Traffic Situation Understanding, Risk Assessment, and Safety Progress Report - Reporting Period Ending: Sept. 30, 2019 Principal Investigator: Keith Redmill Status: Active Start Date: Oct. 1, 2018 End Date: Sept. 30, 2021 Research Type: Advanced Grant Type: Research Grant Program: FAST Act - Mobility National (2016 - 2022) Grant Cycle: 2019 Mobility21 UTC Progress Report (Last Updated: Oct. 1, 2019, 7:52 a.m.) % Project Completed to Date: 20 % Grant Award Expended: 8 % Match Expended & Document: 0 USDOT Requirements Accomplishments This project will explore several potential applications of image processing, including neural network/deep learning technologies, to the analysis of traffic scenes involving passenger and transit vehicles. To date, we have mostly focused on one of the applications mentioned in the proposal: optical flow for automated vehicle lane following. We will begin work on the other two applications in the next year. Impacts To date, results have been presented in an MS thesis and through a small workshop sponsored by the Japanese New Energy and Industrial Technology Development Organization (NEDO) involving OSU, Nagoya University, Johns Hopkins, and UT Dallas and shared as part of student and faculty visits between OSU and Nagoya University. The student working on this project spent two months this summer working in Nagoya with Prof. Kazuya Takeda's group. Other none Outcomes New Partners none Issues Funding for this project became available at OSU in mid-August, 2019. Linda Capito Ruiz, a Fullbright MS fellow, worked on the project in 2019 and the charges for the supplemental funding of her fellowship stipend for January-June 2019 are being transferred to the project. The postdoc supported by this project will join OSU in November, 2019.