H.-H. Nagel, H. Kollnig, M. Haag, and H. Damm, Association of situation graphs with temporal variations in image sequences, in Computational Models for Integrating Language and Vision, pp. 1--8, November 1995.  Home/Search   Document Details and Download   Summary   Related Articles   Check

.... networks, also known as belief networks, have been used for visual recognition of static objects (e.g. 27] and others) and for visual attention selection (e.g. 43] Promising work on recognizing single agent action from trajectory information using transition diagrams and fuzzy reasoning [30] led us to investigate the use of belief networks for multiagent action recognition, which more explicitly represent knowledge dependencies and are computationally well understood. Bayesian networks have been used to relax the strict assumptions of plan hierarchy models such as [25] For example, ....

H.-H. Nagel, H. Kollnig, M. Haag, and H. Damm, Association of situation graphs with temporal variations in image sequences, in Computational Models for Integrating Language and Vision, pp. 1--8, November 1995.

.... networks, also known as belief networks, have been used for visual recognition of static objects (e.g. 27] and others) and for visual attention selection (e.g. 43] Promising work on recognizing single agent action from trajectory information using transition diagrams and fuzzy reasoning [30] led us to investigate the use of belief networks for multi agent action recognition, which more explicitly represent knowledge dependencies and are computationally well understood. Bayesian networks have been used to relax the strict assumptions of plan hierarchy models such as [25] For example, ....

H.-H. Nagel, H. Kollnig, M. Haag, and H. Damm. Association of situation graphs with temporal variations in image sequences. In Computational Models for Integrating Language and Vision, pages 1--8, November 1995.

....[28, 3, 31] are sensitive to noisy data and detectors. Belief networks have been used for visual recognition of static objects [20, 1] and for visual attention selection[29] Promising work on recognizing single agent action from trajectory information using transition diagrams and fuzzy reasoning [19, 23] led us to investigate the use of belief networks, which more explicitly represent knowledge dependencies and are computationally well understood, for multi agent action recognition. Previous work in traffic understanding has used an agent based belief network and agent centered features for ....

H.-H. Nagel, H. Kollnig, M. Haag, and H. Damm. Association of situation graphs with temporal variations in image sequences. In Computational models for integrating language and vision, pages 1--8, November 1995.

....and incomplete image information: a camera model, a (hierarchical) ground plane model, a (volumetric) object model, and, finally, a behavioural model postulating that activities, for instance within a traffic scene, are by no means random events, but instantiations of intentions of some agents. Nagel et al. 95] pursue and predict the temporal development of traffic situations by explicitly modeling potential transitions between situations and by taking the possible actions into account which are available to a human agent assuming the agent has in fact a certain intention. Chung Nevatia 95] argue ....

H.--H. Nagel, H. Kollnig, M. Haag, and H. Damm, The Association of Situation Graphs with Temporal Variations in Image Sequences. In: Working Notes AAAI-95 Fall Symposium Series `Computational Models for Integrating Language and Vision', 10--12 November 1995, pp. 1--8, Cambridge/MA, USA

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC