Team Status Report for 04/30
For this week, our team’s focus is on preparing for the final poster, and we’re working on the setup of final demo video. There’s nothing much regarding change of design at this moment, and we’re only making some minor improvement to the CV model.
Yuxin’s Status report for 04/30
What did you personally accomplish this week on the project?*
– Finish testing subsystems
– Work on the final poster with Ke
– Work on the final demo video
– Start drafting final report
Is your progress on schedule or behind?*
My progress is currently on schedule
What deliverables do you hope to complete in the next week?*
Finish all the documents and demo videos.
Team Status Report for 04/23
For this week, our team’s concentration is on the implementation of a high-accuracy ML model for plate recognition. The previous OpenCV model, although can be run on Pi, is not robust enough for low-resolution pictures taken with our cameras. We’ve completed the implementation of the model, and we’re working on the communication between CV component and AWS server, and testing the latency. For next week, we’ll mostly focus on the integration of all subsystems with this new ML model. And we’ll start to work on the final poster, and develop testing plan for our final demo video.
Yuxin’s Status Report for 04/23
What did you personally accomplish this week on the project?
- Completed the testing and integration of ultrasound and navigation subsystems.
- Scaled up the subsystems for final demo.
- Helped with the literature research of ML model for CV functionality.
- Designing the testing plan for final prototype.
Is your progress on schedule or behind?
My progress is currently on schedule
What deliverables do you hope to complete in the next week?
I plan to help with the preparation of slides for final demo and work on the final poster for next week.
Yuxin’s Status Report for 04/16
What did you personally accomplish this week on the project?
Made multiple modifications of the script that controls the LED strip.
Test delay and accuracy of ultrasound sensor subsystem. Test I/O with server. Discuss with team about OpenCV backup plan.
Is your progress on schedule or behind?
My progress is currently on schedule
What deliverables do you hope to complete in the next week?
I plan to finish testing of ultrasound/LED subsystems next week. And I’ll help with the OpenCV part if needed.
Team Status Report for 04/16
For this week, the biggest risk is still OpenCV. The current algorithm doesn’t have sufficient accuracy possibly due to low resolution camera. After talking with Prof. Kim, we temporarily gave up on including car color as an additional feature to recognize cars. Instead, we’ve tried multiple preprocessing techniques that may enhance image quality before feeding into the model (detail in Ke’s report). Currently, the most feasible plan is to send images to the server and process plate recognition with more advanced model on the server side. Meanwhile, we’re also working on the navigation algorithm as advised by Prof. Kim. The change of plan mostly comes from the limitation of OpenCV algorithm, and server side also needs to be modified to accommodate the image processing component.
Team Status Report for 04/11
For the last week, we’ve spent fair amount of efforts on the interim demo. We’ve set up our hardwares in the garage and record outputs of our software component. On the OpenCV side, Ke has worked on the improvement of the current OpenCV algorithm. The software side has successfully been integrated with the hardware components. So far, the most risk comes from the OpenCV part, where inaccuracy happened occasionally. There were situations where nothing was picked up. We’ll be working on the back up plan for recognizing cars with very low accuracy, such as including car color as a metric. We’re currently behind schedule due to the inaccuracy of OpenCV part.
Yuxin’s Status Report for 04/11
What did you personally accomplish this week on the project?
Worked with group on the interim demo. Prepare video for the demo. During testing we discovered that the hardware connection is very unstable especially since it was very windy on the testing day, so I soldered the LED parts. I also worked with the team on the discussion of OpenCV back up plan.
Is your progress on schedule or behind?
My part is currently on schedule.
What deliverables do you hope to complete in the next week?
I hope to work with Ruizhe and Ke on the OpenCV part to make our plate recognition part more robust, which is the key focus at this point.
Yuxin’s Status Report for 04/02
What did you personally accomplish this week on the project?
I’ve completed the design and implementation of the LED controlling circuit. I wrote python scripts that are compatible with the software side, which can be executed and controlled to light up LED strips representing specific directions.
Is your progress on schedule or behind?
My part is on schedule so far.
What deliverables do you hope to complete in the next week?
I’ll work on the demo early next week. After the demo, I plan to start working on building a website with Django for visualization purposes. I’ll also work on ordering of more Raspberry Pi’s for our final prototype.