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.

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 current results are if we run the algorithm on the Jetson Nano. However, given how much progress we were able to make, we believe that our work is achievable within this upcoming week. We are managing these risks by putting more hours of work into our team meetings to make sure we’ll speed up our progress and meet our goals quickly to leave room for any risk mitigation. Currently, the contingency plan is that we use a mp4 video to work on the software side while waiting for the other team member to figure out the hardware side. Once that is resolved, the next step is to ensure the software side works well with the Jetson Nano and the live video footage captured by the camera.

To answer the week-specific question, we are planning to set up the camera in the lab and test the whole system with live video footages captured in the lab since the environment in the lab is similar to the environment where we’ll showcase our final demo. Our output result is very straightfoward, which is simply wait time at any given point. We’ll compare them directly against the actual result we record using a timer on our phone to calculate the margin of error to evaluate the accuracy. In order to evaluate the performance, we can simply set up timer directly within the code and have it automatically calculated for us how fast the algorithm runs.

There were no changes to the existing design of the system and hence no additional costs were incurred.

Here’s our current schedule.