This course teaches learners how to use Apache Beam to analyze and process football game stream feeds in near-real time. The goal is to detect events such as the start of the game, team detection, player tracking, and ball tracking, and perform analytics on these videos. The course covers creating streaming pipelines using Apache Beam Dataflow runner with Python SDK, utilizing sliding windows for video frame chunking, and hosting machine learning models on GPUs via TF-serving on Kubernetes. The output of the models is written to Google Cloud Bigtable for visualization on a front-end player. The course is suitable for individuals interested in video analytics, machine learning, and sports analytics.
Overview
Syllabus
Intro
PLAYER AND BALL CAN BE DETECTED PER FRAME
EVENT DETECTION REQUIRES SEQUENCE OF FRAMES
PROJECT CONTEXT
THE PROBLEM LANDSCAPE
TWO SOLUTION PARTS
THE DATA FACTS
LEVERAGE THE MODEL TO SPEED UP THE LABELING
THE MODELS
PLAYER DETECTION: FIELD TRANSFORM
A WALK IN FEATURE SPACE
SUBTRACT BACKGROUND TO REMOVE THE NOISE
COORDINATES AS UNLOCKED DOWNSTREAM FEATURE
START OF GAME MODEL BEATS THE OTHER GOAL MODELS (FOR NOW)
SOLUTION ARCHITECTURE
ABOUT APACHE BEAM
THE SOLUTION LANDSCAPE
FROM HLS TO JPEG
FULLY LEVERAGE MANAGED SERVICES
LEVERAGE THE BEAM MODEL FOR PROCESSING
WHERE THE DATA CRUNCHING HAPPENS
PIPELINE DEEP DIVE
LEVERAGE THE INTERNAL LOAD BALANCER OF GKE TO GET PREDICTIONS
DEWARPING THE BOUNDING BOXES TO GET COORDINATES
TEAM DETECTION WITHOUT BACKGROUND SUBTRACTION
DUMPING THE PREDICTIONS TO BIGTABLE
LEVERAGE THE BEAM MODEL TO WINDOW THE DATA
RESPECT THE BEAM MODEL TO GET DESIRED PARALLELIZATION
TEST IN STREAM MODE
Taught by
Devoxx
