To track a moving boundary in MATLAB, the general approach is to use image processing techniques to detect the boundary in successive frames and then use computer vision algorithms to track the movement of the detected boundary. One common technique for detecting the boundary of an object in an image is edge detection.
Here's some sample code for tracking a moving boundary using edge detection:
main.m913 chars35 lines
This code uses the edge function to detect the edges in the image, then uses bwperim to convert the edge map to a binary image representing the boundary. Optical flow is used to track the movement of the boundary between frames. The visboundaries function is used to display the boundary on top of the original images.
gistlibby LogSnag