I’ll be the Design Review presenter. This week, I worked on the software block diagram, testing verification and metrics, and risk factor slides. I researched the various parts of our design to figure out how the software components will work together. I found that OpenCV will be needed to convert our live video feed from the Arducam to the Jetson. The live video feed and selected image of clothing will be run through a clothing detection module. We were originally planning on using DeepMark, but deprecation may lead us to use another option: https://github.com/lzhbrian/deepfashion2-kps-agg-finetune. After our meeting with the TA on Wednesday, we added scope discussion on the solution approach slide and indication of how the software and hardware components will work together in the block diagrams. Most of my time this week has been spent on research and preparing for the presentation.
Team Status Report for March 6
This week, we finalized our hardware list and filled out the forms for ordering our parts and are waiting on them to come in this week. We’ve starting thinking more about the details of how we will implement our design. Drawing the block diagrams allowed us to realize pieces of our design that we haven’t ironed out the details of such as the matching module. We’ll have to check the outputs of OpenPose and DeepMark and figure out how each set of fixed points correlate. At this point, this is still an unknown and is high priority to test out. Furthermore, the Jetson SDK’s interaction with the other software components are also unknown at this point, but we’ll have to hold on this until we get the Jetson. Our hardware and software block diagrams are shown below.
Team Status Report for Feb 27
This week we mainly focused on the proposal presentation and trying to be as prepared as we could for that. We got some good feedback from our peers and really tried to focus on the lack of metrics we had for the testing phase. Now that we have a relatively formalized gant chart, we have a better idea of the big picture and what should be happening right now, so all of us are doing more research on the specificities of our respective tasks (Christina on torso recognition, Devon on clothing recognition, Judy on UI/mapping).
Christina’s Status Report for Feb 27
This week I finished up on the problem, solution, requirements, and software technical challenges slides of the proposal presentation. Devon and I listened and gave feedback on Judy’s presentation. We got good feedback from our peers and professor afterwards and we realized we really needed to have more defined metrics for testing and are discussing more specific metrics to judge success such as having 50% precision on matching fixed points with superimposing and 80% with warping within 2cm.
Christina’s Status Report for Feb 20
I did some general/preliminary research on the suggestions Marios gave us on various aspects of the project including Raspberry Pi vs. Jetson Xavier NX and various hardware costs. I also worked on the Use Case, Requirements, and Software Technical Challenges sections of the proposal presentation. I think we’re all starting to think more about attainable design which is great.