Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Building Camera based Intelligent Applications

Nabarun Pal
September 02, 2017

Building Camera based Intelligent Applications

Presented at PyData Delhi 2017

Nabarun Pal

September 02, 2017
Tweet

More Decks by Nabarun Pal

Other Decks in Technology

Transcript

  1. • Final Year Undergrad @ IITR • Software Engineer Intern

    @ rorodata • Systems Engineer @ Team Robocon IITR • Love my kindle and hacking through things About Me nabarun.in github.com/palnabarun
  2. Overview • Introduction • Use Cases • Components of the

    pipeline • Bottlenecks & Challenges • Our approach ◦ Camera Agent ◦ Cloud Architecture ◦ Firefly ◦ Dashboard • Code Samples • Ending notes
  3. Use Cases • Surveillance • Agricultural yield estimation • Object

    classification • Barcode recognition on conveyor
  4. Bottlenecks and Challenges • What tools to use? • How

    to capture data? • Where to store? • Where should my ML code run? • How should I visualize the output?
  5. • Takes 2-3 weeks for building an application • Of

    that, only 2 days may be spent on actual machine learning • Majority of the time is spent in software engineering rather than ML Typical Timeline
  6. Camera Agent • Program running on end device • Connects

    to pre-configured server • Captures and uploads pictures/videos • Remotely configurable by the server
  7. Cloud Architecture • Server to get data from the agents

    and store them • Admin Dashboard to control the capture frequency, type of data captured, see logs and uploads from registered devices • Storage provider can be changed • Provides a client library for fetching data
  8. Firefly • Framework to deploy Python functions as REST web

    service • Very easy and flexible to use • Used to deploy ML models and pre-processing functions • Easily deployable using WSGI servers like gunicorn • Open Source !
  9. Dashboard • Variety of visualization options • Data provided by

    the client library or a firefly function running Machine Learning Code • Run anywhere • Plotting and charting using Dash by plot.ly or any other visualization tool
  10. Ending Notes • End to end application development in 3-4

    days • Majority of time spent on ML • Robust infrastructure • Versatile data storage options • Scalability