Category: Team Status Reports

This week we focused on debugging our device and also assembling the belt and attaching it to our Raspberry Pi + camera. We tested it out at the stoplight again and found that in some cases it was having problems, so debugged those.

Risks and Mitigations

Current risks include the latency of our device and the accuracy. We had to settle for a minimum for the accuracy, but the latency is currently too long for a user to safely use it at a traffic light. We are looking into what else could be done to cut that time down.

Schedule

We need to just wrap up our final presentation requirements such as the video, poster, and final report. Last minute things include maybe any adjustments to the belt to make it more comfortable.

 

StATUS

• Traffic Light CV – Yasaswini
  • Functional CV model to detect boundaries of traffic lights in a scene (yay!)
• Look Light Detection – Shayan
  • Improvements on traffic light detection
  • Work on detection using full scene in case CV doesn’t properly work
• Raspberry Pi Interface – Jeanette
  • Validation testing of camera and button setup.
  • Beginning testing code integration with the code in the GitHub right now.

CHANGES TO THE SYSTEM

• Nothing new this week 🙂

CURRENT RISKS AND MITIGATIONS

• No new risks/mitigations this week. Shayan needs to validation of his algorithm with the outputs of the Yasaswini’s CV as input.

StATUS

• Traffic Light CV – Yasaswini
  • Integrated git with the cloud so its all set up for the model to start training as soon as the current algorithm is done
• Look Light Detection – Shayan
  • mostly working look light traffic light detection via the Traffic Light Color algorithm but may need some modifications
• Raspberry Pi Interface – Jeanette
  • Set up camera and the button to the Raspberry Pi and the camera has been checked to be working. With the battery pack connected as well, it’s basically ready to go.

CHANGES TO THE SYSTEM

• Nothing new this week

CURRENT RISKS AND MITIGATIONS

• Yasaswini – need to see what the training accuracy is on the images and need this going into next week
• Shayan – need to further experiment with the angle/light to make sure all situations are accounted for

THIS WEEK…

• Traffic Light CV – Yasaswini
  • With AWS credits procured, need to finalize AWS integration with Git development to facilitate cloud computing
• Look Light Detection – Shayan
  • With understanding of Hough Transform, need to optimize Look Light search with preprocessing input to Hough Transform
• Raspberry Pi Interface – Jeanette
  • Now that we have the parts and components, need to set up RPi and interface components with it

STATUS…

• Yasaswini – AWS cloud deployment setup finalized, integrated COCO dataset with AWS API, and began implementing training model with AWS setup in mind
• Shayan – further optimized look light detection to more accurately search for the colored lights in traffic lights through image size regularization as well as red, yellow, and green color masks/filters
• Jeanette – completed Raspberry Pi setup, RPi camera setup and verification, acquired remaining components

CHANGES TO THE SYSTEM

• Nothing new this week 🙂

CURRENT RISKS AND MITIGATIONS

• Yasaswini – when running the training next week and checking accuracy, we will be able to better determine shortcomings in the CV algorithm
• Shayan – need to further preprocess images to account for excess light / saturation in photos

This week:

• Begin to set up AWS network
• Research image processing techniques for circle recognition
• Set up raspberry pi

Risks:

• We have had difficulty in setting up the AWS cloud
• Delay in shipped goods (arrived on Thursday)

Mitigations:

• Updated schedule

Now that we have finished set up and received supplies we hope to make significant progress on our algorithms this week.

This week…

• Continued refreshed code for project, e.i. tensorflow, opencv and raspberry pi
  • Actually started implementing and debugging code
• Prepared for the Design Review slide presentation
• Got insights from visually impaired user, gained a broader understand of how the visually impaired cross intersections, and correspondingly amended our use case and end user
• Finalized Bill of Materials and ordered hardware
  • Incl. finalizing the camera we’re using: a RPi camera

Status…

• On time but still need to obtain AWS credits

Changes to the system

• Altering mechanical form factor from headband to belt

Current risks and mitigations

• None with development currently

This week…

• Refreshed code for project, e.i. opencv and raspberry pi
• Prepared for the proposal project
• Presented the proposal project
• Reached out to out interviewee
• Took photos of intersection for data set
• organized photos for dataset

Status…

• On time but need to order components next week

Changes to the system

• None at the moment

Current risks and mitigations

• if there should be an enable button for our device
• distractions from other attributes of the intersection
• how all our devices will fit in the headband