This scholorship was provided by Udacity.It was five-lesson plan which provided insight how to make Edge application which make deeep learning model run locally on the device. OpenVINVO tool allows us to convert a deep learning model and configure it to run on a specialized hardware.
Defined as edge computing as “a part of a distributed computing topology in which information processing is located close to the edge – where things and people produce or consume that information".
This folder cantains a project which analyze the video and return the time two particular set of pets are in camera scene and returns the time stamp when a particular event occurs.
Files contained are:-
- prototype.xml:- xml reprenstaion of Deep Learning Model used as a consequence to model
- prototype.bin:- bin reprenstaion of Deep Learning Model
- Interpretation 2020-02-23 201346.png:- Screenshot of image
- App.py :- Main file of python
In this project, Data was transfered from Edge Application to the web Server using MQTT and FFmpeg servers.Input video was converted to output video and was dispalyed along with data like speed and classes counted from JSON server.
Files contained are:-
- app.py :- Main file of python
- consequence.py:- supporting file for app.py
- Captured.PNG:- Screenshot of server with video server
- test_video.mp4:- Input video given to program
- out_video.mp4 :- output video seen on server
- OpenVino toolkit
- openCV for image processing
- paho.mqqt
- Tensorflow
- Numpy
Issued to Devanshu Vashishtha
| All Rights Reserved | 2020