| | 1 | [[TOC(Other/Summer/2020/SmartIntersection/*, depth=1, heading=Smart Intersection)]] |
| | 2 | |
| | 3 | = Smart Intersection - daily traffic flow = |
| | 4 | **WINLAB Summer Internship 2021** |
| | 5 | |
| | 6 | **Group Members: Sandeep Alankar, Anthony Siu** |
| | 7 | |
| | 8 | == Project Website == |
| | 9 | https://bzz3ru.wixsite.com/smartintersection |
| | 10 | |
| | 11 | == Gitlab Repositories == |
| | 12 | **!DeepStream and YOLOv3 Application:** https://gitlab.orbit-lab.org/si2020-smartintersection/smart-intersection-ds-yolov3-app |
| | 13 | |
| | 14 | **OpenCV- Add Bounding Boxes to Video:** https://gitlab.orbit-lab.org/si2020-smartintersection/add-bounding-boxes |
| | 15 | |
| | 16 | == Project Objective == |
| | 17 | |
| | 18 | The goal of this project is to create a method for estimating the statistics for vehicle count/traffic flow into one intersection in New York City. As an example, record videos of the northbound traffic on Amsterdam Avenue, as vehicles are entering the 120th St./Amsterdam Av. intersection. Using YOLOv3 deep learning model, detect and count vehicles as they approach/enter the intersection from south, making sure that there is no double-counting. Use 180 second long video fragments (approximately two traffic light cycles), and repeat up to half a dozen times a day, for a number of workweek/weekend days during the same times of each day. Compare the vehicle count (traffic flow) as a function of the time of the day. Utilize NVIDIA !DeepStream deployed on COSMOS GPU compute servers to run the model. The method should be generalizable/expandable to any direction of vehicle movement, when appropriate camera views are available. |
