Our original description
The project was created by the group named is D.S.P. which stands for Digital SnowPrints. The purpose of this project is to track the movement of up to three animals through a snowy field. Three sets of snowprints were obtained from reputable biological sources. Using Matlab's arsenal of built-in functions, these images will be converted into matrices. The print will then be mirrored to create the complementary paw, hoof, or foot. Each snowprint will be rotated in seven different angular orientations. All of these images will be used for correlation in the matched filter. This gives a total of (3 x8) 24 images to be convolved with each scene.
The various footprint images will be distributed on a white snowy background. Their placement will be generated randomly, but will adhere to constraints that will result in realistic paths that an animal could travel in the snow. This will be known as the "detection area." A Matlab *.m file will be created that will scan the detection area row by row, looking for snowprints. The detection area will be divided into small regions or windows. For each window, the matched filter will compare its contents with all 24 possible images. If the correlation is low, the scanning continues. If the correlation is high, the window is marked as a match for the appropriate animal. The *.m file will draw a dot in the window where the snowprint appears. After the image has been fully scanned, an interpolation algorithm will connect all the points for a given animal and fit a curve to trace the path. These curves will chart the path travelled by each animal.
There are 3 different techniques employed in this project to detect the animal prints: straight convolution, convolution with whitespace elimination, and convolution with gait optimization. Each technique varies in terms of its complexity and computational efficiency. Description and analysis of the various algorithmic tradeoffs are included in the final report.