论文信息 - Hybrid object recognition in image sequences

Hybrid object recognition in image sequences

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.

[1] Heinrich Niemann,et al. Control and explanation in a signal understanding environment , 1993, Signal Process..

[2] Helge J. Ritter,et al. Neural computation and self-organizing maps - an introduction , 1992, Computation and neural systems series.

[3] Helge J. Ritter,et al. A neural 3-D object recognition architecture using optimized Gabor filters , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[4] Marvin Minsky,et al. Logical Versus Analogical or Symbolic Versus Connectionist or Neat Versus Scruffy , 1991, AI Mag..

[5] Heinrich Niemann,et al. Semantic Networks for Understanding Scenes , 1997, Advances in Computer Vision and Machine Intelligence.

[6] Franz Kummert,et al. A hybrid system to detect hand orientation in stereo images , 1994 .

[7] Helge J. Ritter,et al. A Hybrid Approach to Signal Interpretation Using Neuronal and Semantic Networks , 1993, DAGM-Symposium.

[8] L. N. Kanal,et al. Interactive pattern analysis and classification systems: A survey and commentary , 1972 .

[9] Gerhard Sagerer,et al. Neuronal, Statistisch, Wissensbasiert: Ein Beitrag zur Paradigmendiskussion für die Mustererkennung , 1993, DAGM-Symposium.