Video Analytics for Football Games

Video Analytics for Football Games

Devoxx via YouTube Direct link

FROM HLS TO JPEG

18 of 29

18 of 29

FROM HLS TO JPEG

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Video Analytics for Football Games

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 PLAYER AND BALL CAN BE DETECTED PER FRAME
  3. 3 EVENT DETECTION REQUIRES SEQUENCE OF FRAMES
  4. 4 PROJECT CONTEXT
  5. 5 THE PROBLEM LANDSCAPE
  6. 6 TWO SOLUTION PARTS
  7. 7 THE DATA FACTS
  8. 8 LEVERAGE THE MODEL TO SPEED UP THE LABELING
  9. 9 THE MODELS
  10. 10 PLAYER DETECTION: FIELD TRANSFORM
  11. 11 A WALK IN FEATURE SPACE
  12. 12 SUBTRACT BACKGROUND TO REMOVE THE NOISE
  13. 13 COORDINATES AS UNLOCKED DOWNSTREAM FEATURE
  14. 14 START OF GAME MODEL BEATS THE OTHER GOAL MODELS (FOR NOW)
  15. 15 SOLUTION ARCHITECTURE
  16. 16 ABOUT APACHE BEAM
  17. 17 THE SOLUTION LANDSCAPE
  18. 18 FROM HLS TO JPEG
  19. 19 FULLY LEVERAGE MANAGED SERVICES
  20. 20 LEVERAGE THE BEAM MODEL FOR PROCESSING
  21. 21 WHERE THE DATA CRUNCHING HAPPENS
  22. 22 PIPELINE DEEP DIVE
  23. 23 LEVERAGE THE INTERNAL LOAD BALANCER OF GKE TO GET PREDICTIONS
  24. 24 DEWARPING THE BOUNDING BOXES TO GET COORDINATES
  25. 25 TEAM DETECTION WITHOUT BACKGROUND SUBTRACTION
  26. 26 DUMPING THE PREDICTIONS TO BIGTABLE
  27. 27 LEVERAGE THE BEAM MODEL TO WINDOW THE DATA
  28. 28 RESPECT THE BEAM MODEL TO GET DESIRED PARALLELIZATION
  29. 29 TEST IN STREAM MODE

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.