Nii-Okaitey Tetteh, Chi Nguyen, Likhitha Chintareddy | Carnegie Mellon ECE Capstone, Spring 2023
The most significant risks that could jeopardize the success of the project is probably the hardware component because we received the Jetson Nano so close to the interim demo and was experiencing trouble setting it up in the beginning of the week (this problem has …
The goal of this past week has been obviously to work on our product to showcase at the interim demo. I’ve been working on polishing my parts to make sure that the CV algorithm is able to process videos and output the bounding boxes of …
Over the past week, I updated the UI and the AJAX required to update live wait time information: https://github.com/santacalculus/No-Time-to-Dine-capstone. I’m working on refining the CSS design at the moment to make the webpage appear cleaner, and debugging the code for the main menu page where users choose which restaurant to go to (menu.html file in templates folder and base.css file in static folder) – there is an issue with the alignment of cards for dining halls that I’m trying to figure out how to fix. The icons that represent individuals in line are not rendering on the page, which is another problem I’m planning on debugging. But because the AJAX has been implemented, once we integrate the system for testing i.e. the Jetson Nano and CV algorithm, it should be able to update live wait time every 2 seconds – and I will be able to assess any errors in the event of it not working.
Over the next week, my aim is to make sure the web app does its part of the job wrt interim demo – display wait time information and update in the given constraints. This means by the end of the week, I need to test whether there are any issues with my AJAX implementation and fix the problem with the icons not rendering.
Because I’m currently debugging the code, I’m slightly behind the schedule and have updated it accordingly: https://docs.google.com/spreadsheets/d/172baIWKtfkJjnvyUFb2y0nYx2lQU0aVvdxOXiqKtKBI/edit?usp=sharing
The most significant risks that could jeopardize the success of the project is that we have trouble setting up the hardware side which leads to us having trouble integrating the whole system together. We are concerned about this because it’s difficult to estimate the current …
Since we were having some trouble setting up the hardware, I’ve been continuing working on the software code and test it with my own test cases that I made. To be more specific, I’ve been writing the code for the wait time algorithm and I …
This week, I continued implementing the UI while simultaneously working on AJAX with some dummy hardcoded data. The login page and registration page have been implemented without OAuth and only using Django’s authentication package for now – I’m a little unfamiliar with implementing OAuth so the first priority is to get the registration and login working and then introducing OAuth that will enable users to login using their Google accounts at a later time after implementing most other UI features. The rough mockup of our updated UI is attached below.
The left half that displays the time of arrival has been implemented. However, the barometric needle on the right side has been a challenge to implement due to the complexities of the angle of the needle which has to change with dynamic data (which we do not have, at the moment), and I’m currently working on it. I’m still on schedule, it’s just that I’m working on both UI and AJAX simultaneously so I should be able to finish both by the end of the AJAX implementation part of the schedule.
I’ve finished fixing the errors on the CV side and fine-tuning it so the code should be ready to run on the Jetson Nano. Testing the code is not a one-time task and it’s something that I will keep doing every week. As we’ve finally …
In the earlier week, I went through the results of the user studies conducted with various design ideas and came across an interesting paper [linked HERE] that led to a massive redesign of our initial idea. This resulted in our idea going from a simple …
As a team, the week was mostly spent on doing the design review report. We were still waiting on some hardware components to arrive so that we could finally start setting them up in public space.
We think the risks that could jeopardize the success of our project right now is that we need to figure out how to set up the camera in the public space and able to gather enough data for testing. The integration of the whole system will take a while and it’s crucial that we do this as soon as possible. We also need to test the CV algorithm on a real dataset to make sure that our demo in early April will go smoothly. We currently have plans to set up the camera at La Prima by the end of the week after classes when the space is empty and we can invite people we know who give us consent to be included in the video. Then, we can assure that our hardware side is set up and works properly and we can use this dataset to test the software side. Regardless of whether some of our parts will arrive by then for camera setup, we will also use phone camera to gather data to test software side.
All the final changes to the design and costs were mentioned in the previous status reports and in our final design review report. There are no further changes made as of now and it’s unlikely that there will be any.
As we’ve established a set of sub-systems necessary to implement our project, it’s necessary that our team learns how to use Replit. Each team member should prepare code and data files so that Replit can run each project component smoothly.
The week was mainly spent on writing the design review report as there was a lot to be done. I also spent time on fixing the bugs and fine tuning the YOLOv7 code so that it works to our needs. Since we haven’t been able …