Modelling spatio-temporal trajectories and face signatures on partially recurrent neural networks

Addresses the problem of trajectory prediction in machine vision applications using variants of Elman's partially recurrent networks. The authors use dynamic context to constrain the representation learnt by a network and explore the characteristics of various input representations. Network stability and generalisation from training on complex 2D trajectories are tested. The authors train such networks to encode knowledge about "trajectories" in dynamic face recognition using an extended "temporal signature" eigenface representation of face image sequences. Eigenvector decomposition on each time step of a motion sequence allows for natural variations in view and. Scale. This application makes use of on-line head detection and face tracking from image sequences and achieves a high success rate when tested on sequences of known and unknown individuals with large viewpoint differences.