This week, I finally got my own laptop so I redownloaded all the necessary software and libraries for my gesture recognition system. Using the OpenCV library in Python, I was finally able to use the camera to detect the hand by separating the background with the foreground via thresholding. Then, I used findContours to identify the hand within a region of interest (roi). Finally, I made a copy of the the frame containing the roi and displayed the video in binary black and white. My code can now detect the hand with a static background.
Researched how image processing works (tutorials, examples using python and open-source software OpenCV). ~20 minutes on 1/19/19, ~30 minutes on 1/21/19
Made sure all necessary software was downloaded to my computer. ~30 minutes on 1/17/19
Adjusted timeline. ~15 minutes on 1/23/19
I have been reading up on documentation and research for the Leap Motion controller so that writing the code will be more easily managed in the future. I have also been updating the commented portions of my proposal, and I’m also changing certain sections so that it will make more sense with the context of the scope of my project.
I read more papers where the researchers used a Leap Motion controller to recognize gestures. People use a variety of methods to classify static and dynamic gestures. One of the more frequently used methods takes advantage of a ‘Hidden Markov Model”.
Additionally, I did research on the software available for the Leap Motion controller. By the end of this week I will finalize the framework of my project.
Read the papers and summarized them.
I am leaning more towards the gesture control system idea, but at the moment it seems like I keep finding more and more challenges to overcome with this project. Typing with gestures may not be feasible, and if I use a camera, there would be lag, making it suck.
This week, I decided to change my first project (soccer coaching tool) and do something different. I haven’t really thought to utilize my knowledge I’ve gained from classes and I want to do some type of AI or ML project.
Additionally, I found articles that relate to my ideas.
Idea 1: Soccer Coaching Tool
Did research to find similar softwares for coaching.
Idea 2: Hand/Finger Gesture Sensor for Browser Control and Navigation
Read research papers regarding similar ideas about monitoring hands and fingers. Found devices that provide the sensors and can easily be used with Google Chrome browser.
Idea 3: Thermal Modeling of Building(s) on Earlham’s Campus
Create 3D map of a building or buildings at Earlham and simulate the dynamics of energy loss and generation. Read papers regarding empirical model of temperature variation in buildings.