Segmentation of action streams human observers vs. Bayesian binning

Authors:
Dominik Endres;Andrea Christensen;Lars Omlor;Martin A. Giese
Affiliations:
Dept. of Cognitive Neurology, University Clinic, CIN, HIH and University of Tübingen, Tübingen, Germany;Dept. of Cognitive Neurology, University Clinic, CIN, HIH and University of Tübingen, Tübingen, Germany;Dept. of Cognitive Neurology, University Clinic, CIN, HIH and University of Tübingen, Tübingen, Germany;Dept. of Cognitive Neurology, University Clinic, CIN, HIH and University of Tübingen, Tübingen, Germany
Venue:
KI'11 Proceedings of the 34th Annual German conference on Advances in artificial intelligence
Year:
2011

Citing 9
Cited 0

Motion signal processing

SIGGRAPH '95 Proceedings of the 22nd annual conference on Computer graphics and interactive techniques
Segmenting motion capture data into distinct behaviors

GI '04 Proceedings of the 2004 Graphics Interface Conference
Exact and efficient Bayesian inference for multiple changepoint problems

Statistics and Computing
Generic temporal segmentation of cyclic human motion

Pattern Recognition
Parametric model for video content analysis

Pattern Recognition Letters
Parabolic movement primitives and cortical states: merging optimality with geometric invariance

Biological Cybernetics
Feature extraction from spike trains with Bayesian binning: `Latency is where the signal starts'

Journal of Computational Neuroscience
Factor graphs and the sum-product algorithm

IEEE Transactions on Information Theory
Bayesian bin distribution inference and mutual information

IEEE Transactions on Information Theory

Quantified Score

Hi-index	0.00

Visualization

Abstract

Natural body movements are temporal sequences of individual actions. In order to realise a visual analysis of these actions, the human visual system must accomplish a temporal segmentation of action sequences. We attempt to reproduce human temporal segmentations with Bayesian binning (BB)[8]. Such a reproduction would not only help our understanding of human visual processing, but would also have numerous potential applications in computer vision and animation. BB has the advantage that the observation model can be easily exchanged. Moreover, being an exact Bayesian method, BB allows for the automatic determination of the number and positions of segmentation points. We report our experiments with polynomial (in time) observation models on joint angle data obtained by motion capture. To obtain human segmentation points, we generated videos by animating sequences from the motion capture data. Human segmentation was then assessed by an interactive adjustment paradigm, where participants had to indicate segmentation points by selection of the relevant frames. We find that observation models with polynomial order ≥ 3 can match human segmentations closely.