Time-sequential imagery is difficult to analyze because of its high dimensionality. This paper advances a new algorithm that screens input data in an intelligent way, discards data with negligible information, and uses the remaining images to represent the sequence in an optimal compact form. We present data to illustrate how this algorithm can be used to do novelty filtering, novelty detection, segmentation, background independent modeling, and classification.
Pieter J. E. Vermeulen,
David P. Casasent,
"Karhunen-Loeve techniques for optimal processing of time-sequential imagery," Optical Engineering 30(4), (1 April 1991). https://doi.org/10.1117/12.55812