Changes between Version 2 and Version 3 of Other/Summer/2020/SmartIntersection


Ignore:
Timestamp:
Jun 5, 2020, 1:15:37 AM (4 years ago)
Author:
bzz3
Comment:

added project website link; minor typo corrections

Legend:

Unmodified
Added
Removed
Modified

  • Other/Summer/2020/SmartIntersection

    v2 v3  
     1[[TOC(Other/Summer/2020/SmartIntersection/*, depth=1, heading=Smart Intersection)]]
     2
    13= Smart Intersection - daily traffic flow  =
     4
     5Project Website: https://bzz3ru.wixsite.com/smartintersection
    26
    37== Project Objective ==
    48
    5 The goal of this project is to create a method for estimating the statististics 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 Yolo V3 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.
     9The 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.
    610
    711== Reading Material ==
    … …  
    1115
    1216* Get ORBIT/COSMOS account and familiarize oneself with the testbed procedures
    13 * Learn about YoloV3 deep learning models for object detection
    14 * Read about NVIDIA deepstream
    15 * Explore the image (set of computing tools) available on COSMOS, which uses deepstream and can deploy YoloV3
     17* Learn about YOLOv3 deep learning models for object detection
     18* Read about NVIDIA !DeepStream
     19* Explore the image (set of computing tools) available on COSMOS, which uses !DeepStream and can deploy YOLOv3
    1620* Record and save 6 videos during one day (to be repeated when the method is debugged and fully functional)
    1721* Brainstorm about vehicle counting/traffic flow estimation methodology
    18