Progress
- 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.
- 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.
- Collected and labeled image dataset for Vizio TV and Trustech AC.
- Refined Gantt chart for incoming weeks.
Schedule
- Train labeled image dataset.
- Wrap up CV pipeline without post-processing.
Deliverables Next Week
- Interim demo incoming.
- Present a crude yolov3 model for AC and vizio TV, start collecting dataset for the rest of the devices.
- Start combining client sides on RPi for multiple servers.
- Test panorama inference possibility and start working on data-postprocessing.
0 Comments