Author: sct1

One suggestion we received was to add a live video of the user so they can see themselves during their workout. However, we were thinking this feature wouldn’t be necessary because of the group we are creating this product for. People are mostly working out at home right now, and using YouTube workout videos, but they mostly aren’t watching themselves do the exercises. I don’t think many home workouts are done in front of a mirror (at least according to people I’ve asked). We’re also concerned about how much latency this feature would add to our product.

Even if they did do the workouts in front of a mirror, we think that the ability to watch themselves during the workout will distract the users. To look up at the live video, the user will need to use incorrect form. This is something we don’t want to encourage the users to do, because incorrect form can lead to injuries over time because of strain caused to certain areas of the body. Also, during workouts, the users should be focusing on engaging the muscle groups that a particular exercise is targeting.

Maybe as a compromise, we could add an overview of the generated workout so that users can learn how to perform the exercises before the actual workout starts. This part of the product could be controlled by the user; as in, they could choose when to see the next exercise (press the next arrow key) so they can take as much time as they need to learn one exercise before seeing the next. This would also allow users to skip exercises they already know, so they can focus on learning only new exercise forms. In this, we could provide the same looped videos so the users can copy them. The users would be able watch the demo video, find a mirror (or we could provide the live stream video here), and try to mimic the demonstrator’s form correctly.

This week we received feedback from our design review presentation. One of the most significant risk was comparing the poses at different speeds. Our plan was to select specific frames from the user input based on time and compare them with the poses from the workout library, which would not work if someone is doing the exercises much faster/slower. We are looking in to dynamic time warping as suggested by Prof. Savvides, and trying to apply that in our project to correct what we compare by looking for the best alignments between time series.

We also need to figure out more quantitive and detailed ways to measure accuracy of pose alignment and comparison. We planned to test it with different body types and poses, and check whether it can align the points and distinguish the poses correctly.

We started working on our design review report.

We decided to use a Jetson TX2 Xavier board instead of a Jetson NX Xavier or Jetson AGX Xavier. This is because The 18-500 parts inventory had both the AGX and TX2 boards from previous years. We didn’t want to buy another board if there were already 3 usable boards available. We originally wanted to borrow an AGX, but other groups requested the 2 in inventory earlier than we did, so we weren’t able to borrow them. The inventory still had a TX2, so we submitted a request to borrow that instead, and were able to do so.

Borrowing the boards instead of buying a new one allowed us to stay exactly on schedule. If we bought an NX, then we would’ve been at least 2 days behind because the shipping time is 2 days. It also decreased our costs, so we’re only paying for a camera currently.

To adjust to the board we chose, the TX2, we decided to use a different library: Tensorflow OpenPose. This library was able to analyze some sample images (on Zixuan’s laptop) much faster than the original OpenPose was. While she was testing OpenPose, she was able to verify that the images we took from YouTube videos are usable with Tensorflow OpenPose.

This week, we also worked on our design presentation slides and tried to incorporate the feedback we got from the proposal presentation. So, we added more pictures/visuals, and a testing plan (not actually in the slides, but will be talked about). We’re currently still working on our reasoning for our metrics, but this should be done by the time we present.

Currently, the most significant risk to the success of our project is that we are already behind schedule (based on our Gantt chart). We wanted to have our board by this coming Monday, but we haven’t ordered a board yet because we are potentially changing our first choice board from the Xavier NX to the Xavier AGX. This is because the AGX is available according to the inventory list, so it’s now within our budget. The only thing that is preventing us from finalizing our decision is that we haven’t been able to find as many resources for using OpenPose on the AGX as we have been able to find for using OpenPose on the NX.

We’re planning on finalizing which board we want to use by Sunday so we will still have time to get an NX approved by our TA and ordered by Tuesday. If we end up choosing to use an AGX, we won’t be very behind schedule because we could pick that board up on Monday.

The biggest risks to the success of our project are our hardware performance and overall latency (from hardware and software). We made backup plans to address both concerns, in case our initial plans don’t meet our performance goals.

Our current plan is to use the Xavier NX, though our backup plan for hardware is to use a Jetson Nano, which is cheaper than a Xavier NX or AGX Xavier. If that doesn’t work well, or our budget doesn’t allow, our next backup will be our laptops.

Our backup plan for latency (because we want to perform real-time processing of images of the user) is to end workouts with a “Score loading” screen, to provide some extra buffer time for our scoring/image processing algorithms to finish.

We divided our project into tasks (and subtasks) and divided them up among ourselves. We reflected this division of labor in our Gantt Chart.