| This thesis developed a solution to the task of tracking the position and movement of large (relative to pixel size) bodies through a camera's field of view. Noise sources such as dynamic backgrounds, vibration, variation in appearance, and rapidly changing lighting environments contribute to the complexity. Two separate methods are presented for accomplishing this goal. The first relies on both motion in the picture as well as on how the current image is different from a background image. The second method is much more complex, and is capable of distinguishing between multiple targets as it detects and tracks them. A major consideration in the development is that the implemented system should be able to process the data in real time with moderate computational power. The present area of application is that of automatically detecting ridership statistics for the Utah Transit Authority (UTA) to count persons getting on or off a bus. |
