Color Segmentation using GMM
Gaussian Mixture Model in Python
The aim of this project is to train an unsupervised learning model for identification of objects with different color distributions present in a challenging environment (underwater video feed).
Where’s my Buoy!!
In principle, colors can be characterized by their RGB value. However, in the real world, any object placed in an environment will not have a solid single color. Its surface will reflect a variety of shades depending on the lighting conditions. Therefore, in order to recognize an object of a certain color distribution X, we need to teach a learning model to understand the different distribution of X in that environment. Once the shades are recognized, we can narrow in on the distribution of shades that matches our object the most thereby increasing the probability of identifying the object. This can be achieved using Gaussian Mixture models. In this project, our goal is to identify the distribution of orange, green and yellow underwater buoys from a video sequence and draw tight bounding contours around the detected buoys.
