Cooperative focus and stereo ranging

Abstract

The authors present a cooperative computer vision procedure in which focus ranging and stereo ranging operate together, verifying each other's results in computing the position (but not the shape) of arbitrary objects in a stationary, unknown environment. The procedure increases the reliability of the position measurements by enforcing measurement consistency using mutual constraint, and increases their accuracy by combining them with a maximum-likelihood estimator into an estimate of lower variance than any of the measurements alone. The results of experiments show that the integrated range values are highly reliable. Results confirm the value of using multiple sensors.