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.
Ke Xu’s status report for 04/16
What did you personally accomplish this week on the project?
Tried sharpening the images
Tried color recognition algorithm
Researched ML algorithm for plate recognition
Implementing ML algorithm for plate recognition
Is your progress on schedule or behind?
My part is behind schedule because of poor performance of plate recognition algorithm during test situation. As discussed with Professor Kim and TA Manny, I tried sharpening the image, but it does not work well. So we decide to upload the image to AWS server and run ML algorithm for plate recognition.
What deliverables do you hope to complete in the next week?
Finish ML algorithm for plate recognition. Set up environment on AWS server for ML algorithm and integrate it to our project.
ruizhezh’s Status Report for 04/16
What did you personally accomplish this week on the project?
Worked on integrating all parts of the parking management software system;
Worked on revising the navigation system as per advised by Professor Kim; Not finished but making progress;
Worked on finding the source of some communication issues and potential racing conditions;
Also worked on helping XuKe with his OpenCV part to speed up his progress.
Is your progress on schedule or behind?
My progress is behind due to
- Still blocked on XuKe’s OpenCV plate visual recognition development. There is a very high rate of inaccuracy, which will hinder the success and function of our system; same as last week, still NOT resolved 🙁 , also causing extra work load as we revised plan to put graphics processing on AWS servers, and I am the only person familiar with AWS systems.
- I am facing some issues and bugs here and there. I am working to solve them.
What deliverables do you hope to complete in the next week?
Planning to get revised navigation system fully functional and fully tested.
Planning to work with XuKe on migrating the Graphic Recognition Pipeline to AWS servers.
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.
Ke Xu’s Status Report for 04/10
What did you personally accomplish this week on the project?
Worked on interim demo video with our group
Worked on improving performance of plate recognition algorithm
Did some research in other recognition such as car model and color.
Is your progress on schedule or behind?
My part is behind schedule because of poor performance of plate recognition algorithm during test situation. As discussed with Professor Kim, we need to have backup plans when plate recognition does not work.
What deliverables do you hope to complete in the next week?
Start implementing other backup plans such as car model and color recognition.
ruizhezh’s Status Report for 04/10
What did you personally accomplish this week on the project?
Worked on integrating all parts of the parking management software system;
Worked on making a presentation video for the interim demo, and presented video to Professor Kim and TA Manny at demo;
Also worked on helping XuKe with his OpenCV part to speed up his progress.
Is your progress on schedule or behind?
My progress is behind due to
- Still blocked on XuKe’s OpenCV plate visual recognition development. There is a very high rate of inaccuracy, which will hinder the success and function of our system;
- I am facing some issues with raspberry Pis sustaining unstable connection with the server. I am trying to rectify the issue as quickly as possible.
What deliverables do you hope to complete in the next week?
I am planning to work on enhancing the navigation system next week and help XuKe and Grace with their critical parts (openCV and LED strip controls);
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.
Team Status Report for 04/02
On the OpenCV side, we’ve connected Pi with camera, and ran multiprocessing on the Pi. As discussed with Prof. Kim, one concern is the resolution of photo taken during motion, and the processing speed of photos coming from multiple directions (details in Ke’s report). On the server side, we’ve fixed the http request forwarding issue, and several functionalities are in progress (see Ruizhe’s report). On the hardware side, we finished the circuit for the LED display component. We’ve also been working on the demo next week.
We’re currently on schedule, and there may be modification of design on the computer vision component to resolve the issue of blurred images.
Ke Xu’s Status Report for 04/02
What did you personally accomplish this week on the project?
Tested pi with multiprocessing
Working on pi with multiple cameras
Researching the problem of frame choosing
Is your progress on schedule or behind?
My part is a little bit behind schedule because of the limited numebr of pi we have (need to do multiprocessing using pi) and the frame choosing algorithm (brought up by Professor Kim during Wednesday’s meeting). Professor Kim also mentions a problem: the camera should not keep taking frames while there aren’t any cars coming. I will solve this problem later.
What deliverables do you hope to complete in the next week?
Integrate the plate recognition part into our project and prepare for our demo.
Keep working on the similarity score algorithm and frame choosing algorithm.