Project: #42 Enhanced pedestrian and vehicle detection using surround-view camera system Progress Report - Reporting Period Ending: Dec. 31, 2016 Principal Investigator: Vijayakumar Bhagavatula Status: Completed Start Date: Jan. 1, 2016 End Date: Dec. 31, 2016 Research Type: Advanced Grant Type: Research Grant Program: MAP-21 TSET National (2013 - 2018) Grant Cycle: 2016 TSET UTC Progress Report (Last Updated: March 18, 2019, 10:57 a.m.) % Project Completed to Date: 90 % Grant Award Expended: 100 % Match Expended & Document: 100 USDOT Requirements Accomplishments We have obtained good segmentation performance on Cityscapes dataset. These algorithms are currently being refined and may result in a future publication that will highlight this accomplishment. Impacts Successful segmentation and classification of the objects should lead to improved safety for both self-driving and human-driven vehicles by providing situational awareness of the moving and stationary objects within the vicinity of those vehicles. Other Outcomes New Partners Issues Getting real video data and having objects in these video frames labelled is an issue as it requires significant human effort.