Reconstructing Optical Flow Generated by Camera Rotation via Autoassociative Learning

We investigate methods to reconstruct the optical ow generated by camera rotation using autoassociative learning. A multi-layer perceptron is trained to reduce the dimensionality of ow data which are obtained from real image sequences while the camera is rotating against static scenes. After this learning, the perceptron is able to produce reconstructions of the ow removing the noises in the original ow data. It is also shown that robustness of reconstruction for noisy data is improved by two changes: introduction of con dence values of optical ow into the error function and application of an additional data correction method.