Object descriptors are just one of the components needed for an effective computer vision system. This year’s research will focus on descriptors, machine learning, and object tracking. A machine learning algorithm will be used to train the computer vision system to be capable of detecting pedestrians at various scales and in various lighting conditions. An object tracking system is necessary to follow detected objects as they move through the field of view. A combination of robust detection and tracking will provide the information necessary for the computer to identify dangerous situations (ie. an object or person moving into the path of travel.) This project aims to work toward such a system.