Computational Perception of Scene Dynamics
Abstract
Understanding observations of interacting objects requires one to reason about qualitative scene dynamics. For example, on observing a hand lifting a can, we may infer that an ‘active’ hand is applying an upwards force (by grasping) to lift a ‘passive’ can. We present an implemented computational theory that derives such dynamic descriptions directly from camera input. Our approach is based on an analysis of the Newtonian mechanics of a simplified scene model. Interpretations are expressed in terms of assertions about the kinematic and dynamic properties of the scene. The feasibility of interpretations can be determined relative to Newtonian mechanics by a reduction to linear programming. Finally, to select plausible interpretations, multiple feasible solutions are compared using a preference hierarchy. We provide computational examples to demonstrate that our model is sufficiently rich to describe a wide variety of image sequences.
Cite
Text
Mann et al. "Computational Perception of Scene Dynamics." European Conference on Computer Vision, 1996. doi:10.1007/3-540-61123-1_167Markdown
[Mann et al. "Computational Perception of Scene Dynamics." European Conference on Computer Vision, 1996.](https://mlanthology.org/eccv/1996/mann1996eccv-computational/) doi:10.1007/3-540-61123-1_167BibTeX
@inproceedings{mann1996eccv-computational,
title = {{Computational Perception of Scene Dynamics}},
author = {Mann, Richard and Jepson, Allan D. and Siskind, Jeffrey Mark},
booktitle = {European Conference on Computer Vision},
year = {1996},
pages = {528-539},
doi = {10.1007/3-540-61123-1_167},
url = {https://mlanthology.org/eccv/1996/mann1996eccv-computational/}
}