Category: Uncategorized

This week Devon and Christina came over multiple times this week to work on finalizing the mirror! We got the mirror screen calibration pretty much done. With the reflection of the mirror it looks like the user is actually trying on the clothes. I also went to tech spark on Monday and got a small .75 inch hole cut on the side of the mirror. This way we can have the camera embedded into the mirror creating a more seamless look. I went home on Thursday so we moved the mirror from my house to Devon’s house. At home, I filled in the poster and I am waiting on some detailed pictures of the mirror and the poster will be ready for the demo. We still have some work left to do like enhancing the user interface so that they could try on multiple clothes at once. However, we made great progress so far!

The team is wrapping up on all the deliverables due this week. Judy is working on the poster. Devon and Christina are working on the video. We’re all collaboratively working on the final report based off the design report. Specific to the actual project, Judy has been working out the kinks in the subprocess calls. Christina is working on image calibration to the model. Devon is working on integrating the warping model.

This week I have been working on wrapping up all of the deliverables. Specifically, Devon and I are working on the video. I am refining the appearance of the current UI and calibrating the size and position of the clothing image to fit best true to life (this is for superimposition). One thing to note is that it is really hard to take good images of our project since it’s reflective, but we’re trying our best to show it. Here are some screenshots from our final video.

This week we worked on preparing our final presentation. I worked on the project management slides as well as taking pictures of our mirror and user interface for the slides. In addition to this, I worked on integrating the UI with the matching algorithm with the script. There are still some issues with the display of the matching. When running the script, the matching tkinter screen doesn’t load. Next week, along with preparing the video and demo, I will be working on getting the tkinter screen to load.

This week I continued working on our model using our custom data. I ran into some issues with data resizing so I worked mainly on adjusting the code so that it could work with our custom data. As of now, the output of the model is not completely satisfactory, but I will continue working on it this week. In preparation for the demo, we also mounted the mirror on the TV and tested in person.

This week, in class we talked about ethics. It was eye opening hearing other classmates discuss the ethics of the smart mirror. Many of the other students brought up many great questions as to how inclusive the mirror is. It gave us a lot to think about as we continue to build the mirror. In addition to this, I worked on creating the user interface for the mirror this week. I used Pkinter to make a simple UI that allows the user to either upload a shirt to try on, or choose from the existing shirts to try on. We are working on connecting the interface with the rest of the mirror.

This week I worked mainly on training the model that we will be using for our clothing recognition and image warping.  I had some difficulties training initially on my computer as CPU-only so I put everything on Google Colab and trained from there. I will experiment with different training methods once we deploy it on the Jetson. Judy and I built the TV stand and I helped her with some of the set up of Open Pose on the Xavier. I think that we will be in a good place for the demo on Wednesday and I’m excited to see everything start to come together a bit more. I feel like we are currently working at a good pace, and hopefully things will go smoothly next week.

This week we made some exciting strides as a team. We were able to successfully deploy OpenPose on the Xavier and start running tests. As expected, we had some initial hiccups with the deployment but we sorted through them. Unfortunately, our camera strip broke and we had to order a new one so we will continue testing for our demo when it comes in. Our TV stand was delivered and we built it and attached the monitor. It was a perfect height and we were very happy with the way the stand looks and functions. We also laser cut the mirror but we will be holding off on glueing it to the monitor until we have everything running smoothly. We also began working with the ACGPN model which solves our issues of clothing recognition and image warping. Our updated Gantt chart for the remainder of the class is attached below.

This week we were mainly preparing for the demo. Devon and I assembled the TV stand and place the TV monitor on the stand. We place it vertically so that the tv could show more of the torso. In addition to this, I wrote a script that allowed the camera to take images of the body, then send the pictures directly to openpose to analyze. However, the script that I wrote took over 90 seconds to take picture and analyze in OpenPose. Marios gave us the recommendation to use the GPU version of OpenPose so that it will run faster. I downloaded the GPU version and Openpose did indeed work a lot faster. However, while testing the script, the plastic that connected the camera to the Jetson smoked and burned a little, so the camera is not working anymore. I ordered more of the plastic strips so they are coming on Sunday so we can test before the demo next week. In addition to this, I brought the mirror to Ansys and got the mirror laser cut to fit the screen. We are going to try and glue the mirror to the tv. We left a one inch border around the tv so we could potentially cut a hole for the camera to peak through.

This week we worked on configuring openpose onto the Jetson. We all went over to Judy’s house to work on the mirror in person. We decided on how we want to actually display the mirror, so we ordered a tv mount. We want to glue the mirror onto the screen then put the screen vertically on the tv mount with the keyboard and mouse on the bottom. In addition to this, we got openpose installed onto the Jetson, however we ran into issues when running openpose. After talking to Marios, we realized that the issue was with the display openpose was using but openpose still works. We tested openpose on the sample images as well as on images of shirts and both work! We have also been researching how we want to cut out the background of images of shirts because we just want the shirt and not the person or the background. And lastly we have been working on the matching algorithm and the user interface.