This week I worked on our plate recognition algorithm. I fine-tuned our OpenCV algorithm by cropping the image size and sliding window. However, the plate in PA may contain words other than license plate number. Those words will interfere our result, making our accuracy lower than expected. Next week I will continue to solve this problem. Hopefully, we are able to solve this probelm. Otherwise, we have to upload the images to AWS and do the plate recognition using ML-based algorithms.
ruizhezh’s Status Report for 02/26
What did you personally accomplish this week on the project? Give files or photos that demonstrate your progress. Prove to the reader that you put sufficient effort into the project over the course of the week (12+ hours).
The week is still mostly comprised of prototyping work to help with the design doc;
I am starting to implement the framework of the parking lot management system as well as the navigation system, and making small design changes and new design decisions as my openCV counterpart continues to shed more information on car plate recognition;
Main work completed this week are:
- Re-designed package structure for server application to ensure better class separation;
- Significant progress on designing parking management part of application, as well as some implementation;
- Worked with teammates to complete setup of raspberry pi workstation for ultrasound development;
Please track the current progress through the GitHub repository posted.
(To be added to the GitHub repository, please contact me via email)
Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?
I am on schedule for this week;
What deliverables do you hope to complete in the next week?
I am expecting to finish:
- Designing Parking management part of the application;
- Significant portions of the implementation of the management system;
- Discussing backup plans in case openCV development failure; see team report for more information on this.
Yuxin’s Status Report for 02/26
This week I’ve worked on the presentation for our design review. In addition, I start to work on the parking component of our project. I designed the circuit to wire a single ultrasound sensor to the raspberry pi. I’m currently writing some Python scripts for distance measurement. The component will be completed once I receive the resistors of ideal resistance (next Tuesday expected). And for next week, I’ll try to connect multiple (>=3) ultrasound sensors to the raspberry pi for MVP testing.
Team Status Report for 02/26
What are the most significant risks that could jeopardize the success of the project? How are these risks being managed? What contingency plans are ready?
1) The accuracy of plate recognition is the biggest challenge for our project right now. The resolution of pictures taken by our camera is not high enough for OCR OpenCV algorithms. In addition, there are letters other than plate number (e.g. state name) that add noise to the model. We’ll look into more ML algorithms and consider cropping out the plate region as preprocessing.
2) We foresee that there may be communication latency. The designated parking spot may not be sent to raspberry pi’s at intersections in time, and drivers will need to wait for instructions for a longer time. We’re still thinking about solution to this issue.
Proposed solutions:
Proposed backup for (1):
We can move the work of recognition to the AWS EC2 servers which can sustain a higher processing load without too much latency; this will require the camera image be uploaded to the EC2 servers at a reasonable latency and speed; the current tested round trip time is 0.5 second on average under very moderate traffic; we have yet to test the round trip time under heavy traffic. This part of research is assigned to ruizhezh;
Proposed backup for (2):
The proposing of backup solution for this issue relies on solving (1) first; currently no proposals are concretely stated for this issue, but many are planned; ruizhezh will investigate further on this in the coming weeks.
Were any changes made to the existing design of the system (requirements, block diagram, system spec, etc)? Why was this change necessary, what costs does the change incur, and how will these costs be mitigated going forward?
No change.
This is also the place to put some photos of your progress or to brag about a component you got working.
Server API framework:
https://github.com/Roger-ZRZ/SR_18500_Spring2022/tree/main/ParkingAdmin
(the project is currently private, please request access and I will add you)
Ke Xu’s Status Report for 02/19
This week I worked with my team to visit the East Campus Garage to determine the hardware set up for our MVP presentation. Also, I proposed some abnormal cases that we need to handle during our discussion with Professor Kim. For the CV algorithm part, I have tested openCV algorithm for car plate recognition. However, the recognition accuracy is lower than we expected. So, next week I’m going to test some ML-based recogtion methods to see if our requirements can be reached (processing time will be a major consideration). If ML-based methods can fulfill our requirement then I’m on schedule. If none of the methods work, then I will need to speedup and consider other solutions.
Team Status Report for 02/19
What are the most significant risks that could jeopardize the success of the project? How are these risks being managed? What contingency plans are ready?
OpenCV may not be usable or may not achieve the desired accuracy for recognition, AI models may be used;
However, using AI models will likely strain the raspberry Pis for their processing power; more powerful hardware may have to be used; We currently have two options if this does happen:
- We can move the computation to AWS and endure the ~2 second delay in image processing time;
- We can spend more money to include neural network co-processors for the raspberry Pis;
Everything else is deemed rather feasible at this point;
Were any changes made to the existing design of the system (requirements, block diagram, system spec, etc)? Why was this change necessary, what costs does the change incur, and how will these costs be mitigated going forward?
No. There currently aren’t any outstanding changes;
Provide an updated schedule if changes have occurred.
No. There currently aren’t any outstanding changes;
This is also the place to put some photos of your progress or to brag about a
component you got working.
Server API framework:
https://github.com/Roger-ZRZ/SR_18500_Spring2022/tree/main/ParkingAdmin
(the project is currently private, please request access and I will add you)
ruizhezh’s Status Report for 02/19
What did you personally accomplish this week on the project? Give files or photos that demonstrate your progress. Prove to the reader that you put sufficient effort into the project over the course of the week (12+ hours).
The week is mostly comprised of prototyping work to help with the design doc;
I want to ensure that the basic design is feasible, and have tested multiple modules in simulated circumstances to ensure that they will work as expected;
- Raspberry Pi Configuration;
- Installed operating system (resolved multiple issues);
- Configured system applications, python, OCR framework, openCV, etc;
- Configured testing framework for openCV license plate recognition;
- => Handed over to Xu Ke for openCV workloads;
- Went to CMU parking garage to further specify design with field information;
- Filmed a test run clip to test openCV recognition;
- Initial deployment of AWS Restful API framework for the project;
- Wrote RESTFUL API prototype (placeholders);
- Deployed on AWS ec2 instance and tested with Postman client;
Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?
I am ahead of schedule for this week due to the AWS API initial deployment taking less time than expected;
What deliverables do you hope to complete in the next week?
I am expecting to finish:
- constructing a fully usable Raspberry Pi portable testing station (with screens, keyboard, etc);
- finish AWS configuration and most parts of the API specification (design) and some implementation;
I am planning to test:
- request sending on Raspberry PI to AWS server and test round-trip-time;
Gathering test videos for license plate recognition in east parking garage
[image-failed-to-process]
Testing AWS Restful API prototype
[image-failed-to-process]
[image-failed-to-process]
Yuxin’s Status Report for 02/19
Since we finally have a project idea approved, we’ve been working on the implementation design of the project. I worked with team to visit the East Campus Garage and analyzed the setup of camera/raspberry pi at the ceilings. I further polished our use case and quantitive use case requirements based on comments from professor Kim and peers, searched for and ordered supplies, and prepared the design review slides. Since I’m the speaker for the upcoming presentation, I’ve also spent time on the preparation of the presentation. For next week, I’ll start to work on Web development component towards our MVP with Ruizhe.
Ke Xu’s Status Report for 02/12
This week:
- Finished our design review presentation slides
- Presented our initial design review presentation during course meeting
- Discussed our initial design with team and Professor Kim
- Proposed our new proposal “Smart Parking System with Monitoring and Metering”
- Discussed our new proposal with team and Professor Kim
- Literature review in CV algorithms and hardware requirements for our new proposal
- Discussed abstract and presentation slides with team for our new proposal
After discussion wit Professor Kim about our initial design, we found there are several difficult problems that we may not be able to solve. After several meetings with Professor Kim brainstorming and discussing our new proposal, our new proposal is approved by Professor Kim. Since we are starting from the beginning again, we spent significantly amount of time catching up with the schedule. For next week, I will continue to do literature review in CV algorithms and hardware requirements to find appropriate solutions for our design.
Yuxin’s Status Report for 02/12
Our team is behind schedule for this week since multiple of our initial projects proposals couldn’t meet requirements. I worked with the team in preparation for the proposal presentation and searched for necessary supplies for our previous project ideas. We also spent a fair amount of time brainstorming and discussing with Prof.Kim. For next week, I plan to search for/finalize/order supplies, and conduct some literature review and background research.