Progress Completed training Yolov3 model for 4 classes, 200 Epochs in total. Accuracy of the trained model is not yet confirmed, will validate later. Modified CV server to migrate from OpenCV inference to PyTorch inference. Improved style by wrapping up threads in separate classes. Tested the possibility of panorama, reached Read more…
Progress: I primarily worked on the mechanical design of the physical device and started 3d printing the main body of the IR man.I am waiting for the mechanical parts to arrive to start assembling the parts. I also helped with collecting training data. Schedule: I am pretty much on schedule. Read more…
Progress Trained primary yolov3 model supporting one class only (AC). Model being able to recognize AC in camera captured frame. Tested image stitching before object detection. Turned out that object detection fails for panorama, suspecting the reason being the warping edges and irregular input image size. Gave up using panorama Read more…
Progress In week 11, as a team, the following objectives were done. Successfully delivered INTERIM DEMO: Pending feedback from Profs and TAs. Collected new IR Devices and populated it with the IR Database Fully tested functionality of turning on DingSun Audio Amp and Disco LED light remotely using WebApp LED Light Read more…
Progress In week 11, I had progress in recording the IR Code for the IR Audio Amplifier and the IR Disco LED lights. In addition, we successfully did our interim demo, showcasing our current progress on IRMAN development. Shirley and I have also tested on image transmission and the image Read more…
Progress In week 10, as a team, the following objectives were done. Collected new IR Devices and populated it with the IR Database Fully tested functionality of turning on Vizio TV and A/C remotely using WebApp Web App Successfully Deployed and Tested Mechanical Design: Rotating Base Design Done – Pending Read more…
Progress: Integrated the webapp server with the python client, Helped deploy cv server on EC2, Looked into python async io for the python client on the raspberry pi, Designed preliminary mechanical design for the rotating base, decided on parts to buy, Testing on TV and AC Schedule: We are ready Read more…
Progress In week 10, I had progress in recording the IR Code for the TrusTech portable A/C, fully tested the functionality of turning on Vizio TV and A/C remotely using WebApp, testing the image-stitching and homography on the local machine. This marks the phase 3 exits and we are ready Read more…
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 Read more…
Progress In week 9, as a team, the following objectives were done. Web App Successfully Deployed LIRC Database migrated to IR Man’s MongoDB database Web to IR Circuit Local Testing Done and Passed Raspberry Pi Motor Control Done Motor Controller Soldering Done OpenCV ran successfully locally Set up GPU instance Read more…