Shirley’s Status Report: Week 8

Progress

1. Establish local web socket image transfer and object detection pipeline using pertained yolov3 model
2. Tested camera frame gather and object detection on RPi locally, tested with different resolution to see the limit of yolov3 model (Since we would like image transfer to capture less network bandwidth)
3. Start labeling Vizio TV dataset, prepare for trainig

Schedule

1. Done setting up websocket & object detection pipeline,
2. Keep collecting and labeling data for testing purposes

Deliverables Next Week

1. Set up GPU training server environment, finish labeling at least 300 images
2. Polish websocket server such that it supports multi threading in preparation for supporting multiple IrMans in future