Creature Movement Modeling Project Spring 2018

Over the term, Dr. Stonedahl and I have worked on the videos of the chicks to find a way to accurately track their movements and create a model of them. So far, we have accomplished the following goals: ·        We effectively remove the background of the video by using Gaussian blur and threshold to convert the video into black-and-white. We further use erosion to reduce the area of the chicks so that it decreases the occasions when the chicks move next to one another and they merge in the process. We also use the contour tool to mark the center of the chicks (the blue dot) because it makes it easier to store the coordinates of the current position of each chick further on. Background Removal  ·        Learning from the Whirligig Beetle Project, we also successfully create a multiple frame tracking function. We create a Chick class where it stores the current location of one chick. Then we use 3 lists of the Chick object to keep track of all the chicks: one to store the chic

This week, Dr. Stonedahl and I focused on labeling the chicks and storing their movement coordinates. We labeled each chick with a unique string of numbers and letters, and a color. Each time the chicks merge together, the string will change to a new one and store that information. Finally, we draw a graph to visualize the chain of movement of the chicks over time. The graph below illustrates the movements of the chicks throughout the whole video. We can see that the chicks pretty much move all over the places, with the concentration of the lower left and lower right corners. Full-length Movement Graph The graph below illustrates the movements of the 3 initial chicks (from frame 4100 to frame 20000). In this graph, the 3 chicks often gather around in the middle and the upper right corner of the box. 3-chicks Movement Graph The graph below illustrates the movements of the 6 chicks at the end of the video (from frame 39400 to the end frame 48958). Unlike the case of 3 chi

Over the past few weeks, Dr. Stonedahl and I have decided to change our focus to The Chick Tracking Project instead. Our mission is to create an algorithm to track the movements of the chicks and make the coordinates as exact as possible. So far, we attempted to remove the background by using OpenCV so that we can further identify the position of the chicks. It works quite well when the chicks are separated. However, when the chicks begin to move towards one another (especially when they come into contact), the function fails as it cannot differentiate between the "merged chick" and the individual chick (as seen below). I have tried to come up with some ways to fix this problem but none of them seemed to work yet.