With the COVID-19 pandemic persisting for over a year as of May 2021, millions of students across the country are actively participating in newly-developed remote learning systems. A major challenge in remote learning faced by educators and students alike is the issue of distractions, as home environments tend to contain hundreds of visual and auditory micro distractions that decrease productivity and can slow progress down. While there are guidelines in place to help students detect and remove distractions from their workplace, most are either vague or ineffective at identifying exactly what qualifies as a distraction. A mechanism to effectively identify distractions for students to remove could boost the productivity in hundreds of thousands of schools across the country and has endless implications in remote learning. Using image and video classification technologies in OpenCV and TensorFlow, as well as a simple webcam, this study aims to examine the major and minor distractions that students face throughout hour-long intervals of studying. Furthermore, the study will develop a novel machine learning model to identify where these distractions occur relative to the workspace, as well as how often they occur.