This week, I worked a lot on setting up the Jetson and preparing the accelerometer so it can be integrated with the Jetson. It took a lot of time to get to a point where the sensor was able to be detected and the program to run the accelerometer code worked because versions of certain dependencies needed to updated in very specific ways. We were able to get it working to a point where we could classify the sensor moving backwards and the sensor slowing down motion. I also did more work with the computer vision code and helped with increasing the accuracy and classification of the head pose estimation code.
We are on track according to the updated Gantt chart.
By next week, we hope to have the hardware and software integration completely done and start testing in the car with the new camera.
The tests we plan to run include user testing in the car with the fully integrated project. We will analyze the anticipated measured results by timing how long it takes for the computation and feedback, as well as how useful the feedback is for the user and correcting their driving.