Machine Learning Model Computer Vision Project

The purpose of this model is to identify Cervidae native to North Western America. The classes included are Elk/Wapiti (Cervus canadensis) Caribou/Reindeer (Rangifer tarandus) Moose (Alces alces) Mule Deer (Odocoileus hemionus) and White-Tailed Deer (Odocoileus virginianus). These classes were chosen based on their overlap in habitat and common sightings in the defined region. This model is intended for those who work in conservation and tracking of these animals, as well as anybody who comes across these animals both in nature and in urban/suburban environments. This model can also be used to sift through large data sets of images from trail cameras, dash cameras, or home security systems in order to track the increasing overlaps between humans and these animals. All of the images used in training and testing the model were found using iNaturalist, this allowed for a wide variety of backgrounds and extraneous data to be covered in order to avoid biases. This model was created for a class assignment in AI and Natural History at St. Mary’s College of Maryland.