Hybrid object recognition in image sequences
Franz Kümmert, Gernot A. Fink, Gerhard Sagerer, Elke Braun · 2002
We present a hybrid approach attaching probabilistic formalisms, as artificial neural networks or hidden Markov models, to concepts of a semantic network for a robust and efficient detection of objects. Additionally, an efficient processing strategy for image sequences is outlined which propagates the structural results of the semantic network as an expectation for the next image. This method allows one to produce linked results over time supporting the recognition of events and actions.