I’ve been working on the rotation puzzle piece issue, but have gotten the piece matching issue working! More to come soon.
Connor’s Status Update for 4/4
This week I have been designing the user interface for our system. The challenge has been creating an interface that doesn’t need direct interaction. I have been drafting interfaces with wireframe. This week we are looking forward to completing a design presentation, planning integration, and finishing our design.
Aneek’s Status Update for 4/4
- This week I was focused on getting finger detection in OpenCV working. The issue of various phantom ‘fingers’ being detected in the background was mitigated by using a plain, consistent background for the images (I tested on a white table and a black blanket). While that demonstrated that the approach I was using was working, the background will not be so consistent when puzzle pieces are laid out on the surface below the hand, so my next steps were to test out various methods of improving the detection on more complex backgrounds. The approach that seems the most promising is using a color mask to isolate the hand before running the edge detection to determine the fingertip. However, the color of the hands surface is drastically different depending on skin tone and lighting conditions, so my next steps to improve this are to continue research on alternative methods and/or ways to broaden the color mask to function across a broad spectrum of hands.
A0 Team Status Update for 4/4
Overall our team has been working on making our project ready for the midsemester demo on Monday. We are hoping to have all of our individual pieces of our project put together enough so that we can focus a majority of our efforts on piecing together our final project before the time comes to complete our additional trade studies.
Andrew’s Status Update for 4/4
This week I solved a major problem that was blocking me for a while. I am now able to do a very major part of my project that I was having a lot of trouble with for the last few weeks. I am able to match a piece of an image within the larger image, without using a very naiive approach of doing a simple subtraction of the image block from the overall image.
This is one of 6 methods. 5 of those 6 methods that use the template image among some that convolve the image and find the features and match them among the original image. I am still working on ways of making this as robust to rotations as possible. I need to do more testing to ensure that this is possible and I can meld this with previous research. This is my largest contribution for this week, the rest has been touching up previous pieces of code and working on the overall pieces of the pipeline.
Team Status Update 3/28
We’ve been working on implementing our new responsibilities as well as ordering our new parts. Overall we have been working on implementing the different pieces of our pipeline but have yet to put them all together.
Andrew’s Status Update for 3/28
This week has been focused on ensuring that we have the parts that we need. I have been working on piece identification as well ensuring that the piece features can match to the overall image. I’ve been splitting up some of the work from future weeks, but it feels like a natural progression.
Team Status Report for 3/21
Our team has been discussing ways of adapting our project given that the university is closing and we will not have access to any physical materials for our project. We have decided to move to a simulation based project that keeps the core of our project the same. While scaling back the physical parts of our project we are able to include design studies to trade off and test the limits of our algorithm. We will be able to test our algorithms against down-sampled versions of the image pieces so that we will hopefully be able to see what camera resolution would be needed if the original project was physically realizable.
Connor’s Status Update for 3/21
It has been an unbelievable week for all of us. Given that the Carnegie Mellon education has gone completely remote, we have been tasked to redesign our project. I have mainly spent my time on brainstorming how we can tackle similar engineering problems, within our new constraints. However, all week the situation has been rapidly changing. Along with my teammates, I have helped formulate our new product idea. Next week, I’d like to refine our project by heavily researching some of our tradeoffs, like which packages to use for our UI or what algorithm to use for the puzzle creation.
Aneek’s Status Update for 3/21
This week our project changed significantly due to the COVID-related moves to remote instruction. Unfortunately, the main work I’ve done so far relating to the finger & tap detection is no longer a part of our final project, which is moving to a completely digital project and containing more significant design trade studies on various CV algorithms. This week Andrew, Connor, and I mostly worked on how to change our project to work under these new conditions and the exact mechanics of what this new, digital puzzle solver will look like to the user.