Category: Team Status Reports

The most significant risk at this point in the semester, since our MVP is complete, is ensuring that our design process is well documented and clear in the final report. We are mitigating this risk by taking the feedback we received during our final presentation and following the final report guidance provided on Canvas. We also made notes of the feedback we received from our midterm report and we will focus on the design trade offs section of the report as these are the primary areas we were asked to improve. For the results section that will be expanded on, based on the notes given to all teams during the final presentations, we shall ensure to include details such as size of datasets, number of trials and equations used for our percentages.

We were able to get our system to work on boot. This required creating a systemd service file to call our python script. Additionally we improved our frames per second by reducing the size of the cv2 frame the Jetson was seeing. No additional changes were made to our software or hardware design.

We have no changes to our schedule. We are finishing up the final deliverables of the semester: final video, public demo, poster and report.

At this moment, one risk that could jeopardize our success is that we may not have given ourselves enough time for adding concurrency to our integration of our drowsiness detection system and head pose estimation system, as well as testing it. We want to use Python threading to have our eye classification and head pose estimation run at the same time after the facial landmarking. Since we all do not have much experience with concurrency, we may have underestimated the challenges we may face with this. Our contingency plan is that we will not use concurrency, and instead do the EAR calculations and head pose classifications linearly, and then determine if the driver is drowsy. 

One change we made is that we are only going to use our own custom datasets for training of eye classification. Thus, we will only be using public datasets for testing. For instance, we will use DROZY, a drowsiness database, for testing our drowsiness detection. Additionally, another change we made is that, after comparing our calibration systems for head pose and eye classification, we decided to model the head pose calibration after the eye classification calibration. Therefore, each will use the calibration time to generate vectors to then train separate SVM models. This way, we can make our head pose system more accurate for the user. Additionally, we clarified what type of audio prompts we would like to use during calibration, so that our user experience will be as smooth as possible for this crucial step. We want the user to perform our calibration requests while still not inconveniencing the driver with repetitive, and thus seemingly excessive, calibration requests.

 

The most significant risks that we have, especially with the interim demo coming up, is that integration of head pose and eye classification will not work/be difficult. Currently, both Heidi and Vaheeshta are working on the algorithms separately and are testing on their own laptops. If integration takes too long or we run into problems, it may push back the rest of our schedule. In order to manage these risks, our team is communicating with each other extremely well. Also, Heidi and Vaheeshta are both using the same landmarking algorithm so there is a point of reference that may make this integration easier. Danielle set up the Jetson this week, so we will continue testing on the Jetson and will test together to ensure that we can solve any issues that may arise.

There are currently no changes being made to the design of the system. Perhaps within the next couple of weeks, as we begin integration of the algorithms, this may change.

There have been some changes to the schedule following the advice of Professor Mukherjee. We are currently putting a pin in creating our custom dataset, and focusing more on making sure that our algorithms are working.

Danielle has set up the Jetson and configured the Raspberry Pi Camera, and Heidi has begun testing of her algorithms on the Jetson! Pictures below !!! 🙂

The most significant risks at the moment that could jeopardize the success of the project is integrating all the software algorithms we have together and integrating the hardware components. We plan on testing each algorithm extensively before integrating in steps with the others. Once the algorithms are fully integrated for each hardware part. The plan to test communication between the two devices is to start with simple messaging examples and then proceed to our actual software connecting between the devices. We have done research about each of the components to ensure compatibility. Additional research will be done throughout the project as needed. Another concern will be making sure we are able to power both the Nano and Pi with power banks and enough power is received for multiple hours to run software on each. Before integration we will make sure that they work with charging cables, to observe performance and then move to using power banks. Another risk with the power source will be having scripts automatically run the algorithms when power is plugged in or to switch to using a switch to turn the Pi and Nano on and off. Our plan for this to test our script that runs the algorithms in the correct sequence to ensure it works properly without us intervening. Once this is working fully, we will add the command to start upon plugged into outlet, and then plugged into power bank.

So far no changes have been made, but there might be after the proposal presentation on Monday. Thus, there is no updated schedule.