Abstract
This paper develops a solution to the task of tracking the position and movement of large (relative to pixel and image size) bodies through a visible-light camera?s field of view. Noise sources such as dynamic backgrounds, vibration, variation in appearance, and rapidly changing lighting environments contribute to the complexity. Given that a low number of targets may be present at any one time and some assumptions about the dynamic nature of the image and targets, a solution to this problem is herein formulated which localizes and tracks objects in the field of view. The algorithm is capable of distinguishing between multiple targets which are in close proximity to the camera and to each other. 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 generating ridership statistics for transit agencies; to count persons getting on or off a bus.