Posted on

Anoushka’s status report for 10/9

This week I worked more on edge detection and grid detection. I tried chess board edge detection on various pictures of boards and had challenges in cases where there was a shadow or the color of the chessboard was similar to the table. I have been looking into ways of removing shadows before I detect the edges using canny edge detection. 

 

An easy solution is making them put the chessboard on a light colored table but that is a last resort. I also worked with Demi to explain my requirements for the board so I can do CV on it. I have now started working on CV on the real board because we got pieces this week.

Posted on

Team Status Report for 10/09

This week we spent our time preparing for our Design Review presentation. We met on Saturday outside of class to finalize our slides and Yoorae presented on Wednesday. We received feedback that our metrics seem inaccurate, so we discussed with Professor Yu to get ideas to make our metrics more reasonable as well as get new metric ideas that would measure more useful things. For example, we decided to change our illegal move detection accuracy to instead be a latency measure. This is because illegal move detection itself doesn’t make sense to measure because it should reasonably be 100% accurate. We also decided on more metrics that helped capture useful features of our design (like how much the distance of the center of the piece can be from the center of the square).

We also received our chess pieces and Demi created the sample chessboard, so we can now start testing our CV.

 

Posted on

Demi’s Status Report for 10/2

This week I finalized the specifics of the board. Each square will be laser cut into 2×2 inches using green and white translucent acrylic sheets. The squares will be welded together using acrylic weld on glue. An 8×8 RGB LED matrix will be installed under the board. The front of the board will be laser cut to fit the push button and LCD screen in.

My goal for this week was to have the squares ready. It is important for us to have the top of the board as soon as possible so Anoushka and Yoorae can start testing with CV. However, the acrylic sheets have not arrived yet. In the meantime, I made a drawing for the squares using SolidWorks, so I will be able to laser cut the squares as soon as the sheets arrive.

Posted on

Anoushka’s status report for 10/2

This week I worked on finalising the Camera compatible with Rpi that we will be using for the CV. I also began working on using OpenCV to detect edges of an image of a chess board. I then began working on detection of squares in a chess board image. I am thinking of starting at the middle of the chess board, and going one-by-one in all directions till I hit a large color gradient. This would be the edge of the square in that direction. Because our sample chess board hasn’t arrived yet, I had to use an image off the internet. However, at least the basic algorithm will be transferable to our chess board. I also discussed with Demi the requirements that our chess board must satisfy so that I am able to detect the squares and the pieces on the board.  fo

Posted on

Team Status Report for 10/2

This week our team finalized our decisions on parts we will be using for the project, and completed the order request forms. We mainly worked on preparing for design presentation that is coming up on next week. On the proposal presentation, we got feedback that our timing requirements were arbitrary. So, we worked with the professors and TAs to refine our timing requirements based on real chess game data. We also made sure that the board Demi will be designing meets the requirements for the CV processing (eg: it should have contrast between adjacent chess squares). We also made sure that we are budgeting our money correctly.

Posted on

Yoorae’s Status Report for 10/02

I mainly spent this week preparing for the design presentation as a presenter that is coming up on next week. I started to set up an environment for OpenCV image processing, and started researching image detection algorithms we are going to use for the project. For the project, we are likely to use canny edge detection to detect the board squares and background subtraction algorithm to detect the player’s move (change in chess board pieces). I also started researching about code environment for Stockfish AI that we will be using for the project.