Nii-Okaitey Tetteh, Chi Nguyen, Likhitha Chintareddy | Carnegie Mellon ECE Capstone, Spring 2023
Nii-Okaitey Tetteh, Chi Nguyen, Likhitha Chintareddy | Carnegie Mellon ECE Capstone, Spring 2023
Last week I worked on the speedometer as the transition wasn’t smooth. For this, my existing knowledge of HTML, CSS, and JS wasn’t enough and as I mentioned in my previous status reports, I have had to learn how to use D3 JS more extensively. …
The significant risk that could jeopardize the success of the project right now is that we haven’t integrated our system yet and each team member is still working on perfecting our individual parts. To manage this risk, we will be dedicating the majority of the …
This week, I’ve been working on minimizing the margin of error that the algorithm produces. The reason for the margin of error that we saw from our results was because the checkout “region” was not clearly defined which made the recorded wait time for each person to be off by a few seconds. I’ve also been working on the linear regression model that can help estimate the best average wait time based on the data that we’ve seen. I’m currently still working on finishing the code to make sure that it will output the best result of the test case that we’ve seen in the presentation and hopefully I will be able to achieve my goal soon and will upload my results on here tomorrow because our group is meeting on Sunday to work together for the whole day. I’ve also been looking for a way to optimize the performance of the algorithm on the Jetson Nano because it’s running very slow and we need to achieve our goal before our final report.
My progress is a little bit behind so I’ll dedicate the majority of this last week to catch up and make sure our final product satisfies the use case requirements.
By the end of next week, I should be able to achieve the final product.
You could find my code and results here.
This week, I made changes to the AJAX implementation when I realized during testing that it had some bugs. I also used the knowledge about SQLite queries in Django that I learned in past weeks to test whether the implementation works as it should. It …
I made a lot of progress this week after a few weeks of being confused about how to get to the solution efficiently and putting things together. A major part of the wait time algorithm is how to calculate the average wait time each person …
The most significant risk that could jeopardize the success of the project currently are the accuracy of our wait time algorithm and how to transfer the data from our Jetson to our database SQLite. Now that Nii has almost finished his duties, he will be shifting over to help Chi optimize the algorithm to hopefully make the algorithm produce better results. Another risk to consider is whether or now we will be able to get the Jetson to transfer the data.We have already integrated the hardware and the backend software side so the very last step is to integrate it with the frontend side which communicate by transferring data through JSON. Since we have the Jetson hooked up to WiFi already, we will all be working together tomorrow to have this issue resolved very soon.
No changes were made to the existing design.
You may find our current schedule here.
This week I was able to finally download all the packages with compatible version types to allow the jetson to run our Computer Vision code. The jetson now successfully runs our base current YOLO algorithm: Additionally, I was able to integrate the webcam into the …
This week, I worked on updating the UI and am reworking the AJAX portion of the web app. I made slight changes to the design of the barometer on the Javascript end so that it should render differently when functioning i.e. the colors fill up …
After the interim demo last Monday, I have been working on the final part of the project which is to integrate the system and do more testing, making sure that the code can count the number of people correctly at any given time and output the correct wait time for the users. There were some challenges at first but I’ve been able to come up with a plan to calculate the result correctly and I have been working on putting it in the code. Right now the code can correctly output the number of people in line at any given time. The next step I’ve been working on is to send this data to the database. What the backend server will do whenever there’s a new user is to output the wait time corresponding to the most updated number of people in line from the database.
Right now, my schedule is on schedule and I should be able to achieve near the end result by the end of the week but I’ll need to put extra hours of work into it.
I’m hoping to achieve something close to the final product by the end of the week so that we have more time to run more testings, monitor any potential issue and have time to mitigate risks.
We believe that the current most significant risk that could jeopardize the success of the project is that we are still working on integrating the hardware and software parts which means performance and accuracy are still our main concerns because we aren’t sure what the …