Shirley’s Status Report: Week 9

Progress

1. Added multi-threading feature to the local socket object-detector. Now separates image transfer and computer vision into two different threads, and the gathered image is passed between threads through a shared image queue. Data post-processing is substituted by drawing back, and will be completed as we start to output motor positions for devices
2. Finished setting up GPU server. Installed Darknet for training purposes.
3. Cannot access the TV in 220 lab, and start collecting dataset for the air-conditioner

Schedule

1. Figuring image dataset for train and labeling
2. Wrapping up the pipeline barebones

Deliverables Next Week

1. Finish training model
2. Wrap up the pipeline barebones and prepare for multiple incoming instruction types in server side. Try mimic multi-image sending process