Because a dragline bucket's rigging is flexible, its position cannot be inferred from knowledge of rope length and boom position only. Moreover, active devices cannot be placed on the bucket itself to sense position because of the risk of damage. This paper describes a new machine vision system which is being developed to sense bucket position remotely. It is based on a single camera observing the field in which the bucket moves. An image segmentation process is used to classify the bucket and to identify its position in the scene. This data is used to determine the angle between the bucket and the vertical boom plane, which is used as position feedback in a closed loop system to control bucket motion. The segmentation processes employed, based on colour and intensity are outlined, and experimental results are presented.<<ETX>>