Progress

  1. Improved CV pipeline by supporting multiple message types. Now object detecting server stores requested device list before inference and save inference results of different IrMans separately.
  2. Tested pipeline flow from object detector server on AWS EC2 instance to client on RPi. Successfully transmitted image from client to server for object detection.
  3. Collected and labeled image dataset for Vizio TV and Trustech AC.
  4. Refined Gantt chart for incoming weeks.

Schedule

  1. Train labeled image dataset.
  2. Wrap up CV pipeline without post-processing.

Deliverables Next Week

  1. Interim demo incoming.
  2. Present a crude yolov3 model for AC and vizio TV, start collecting dataset for the rest of the devices.
  3. Start combining client sides on RPi for multiple servers.
  4. Test panorama inference possibility and start working on data-postprocessing.

0 Comments

Leave a Reply

Your email address will not be published. Required fields are marked *