Implementation of Robust Pipeline for Video Analysis for b-Trac

Solutions

• Implemented trigger-based script in the Amazon EC2 to transfer the videos from the Amazon EC2 EBS volume to the Amazon S3 bucket.
• Implemented Amazon Docker to run the script for slicing the videos into the frames and each frame gets stored in the bucket.
• Used AWS Lambda service for running the Amazon Rekognition APIs for each frame, and the Amazon SQS triggers this AWS Lambda by passing the frame details to it when the frame uploads into the bucket.
• The above step would give the preprocessed data by analyzing all the API responses, which would be stored in the bucket.
• Created a crawler in the AWS Glue for transferring the responses of all the frames, and the crawler runs when the responses stored in the bucket are completed.
• Implemented SQL query to analyze all the responses of all frames of a video for identifying the face angle detection, eye gaze detection, object detection, and new person detected in the video.
• Used a new AWS Lambda for storing the Amazon Athena aggregated results into the Amazon dynamodb table.
• We built a pipeline for analyzing the videos and storing the Amazon Athena results in the Amazon Dynamodb table. The pipeline starts when the video comes into the bucket.
• AWS Services used are Amazon ECS, Amazon VPC, Amazon ECR, Amazon S3, Amazon DynamoDB, Amazon SQS, Amazon CloudWatch, AWS IAM, AWS Lambda, Amazon Rekongnition.