Detection of moving objects using motion- and stereo-tuned operators.

A person moving through the world must be able to identify moving objects in order to interact with them and successfully navigate. While image motion alone is sufficient to identify moving objects under many conditions, there may be some ambiguity as to whether an object is stationary or moving, depending on the object's angle of motion and distance from the observer. Adding a measure of depth from stereo cues can eliminate this ambiguity. Here we show that a model using operators tuned to image motion and stereo disparity can accurately locate moving objects and distinguish between stationary and moving objects in a scene through which an observer is moving.