1 / 15

Exploiting Simple Hierarchies for Unsupervised Human Behavior Analysis

Exploiting Simple Hierarchies for Unsupervised Human Behavior Analysis. Fabian Nater Helmut Grabner Luc Van Gool CVPR2010. Abstract. A data-driven, hierarchical approach for the analysis of human actions in visual scenes Completely unsupervised

davis
Download Presentation

Exploiting Simple Hierarchies for Unsupervised Human Behavior Analysis

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Exploiting Simple Hierarchies for Unsupervised Human Behavior Analysis Fabian NaterHelmut Grabner Luc Van Gool CVPR2010

  2. Abstract • A data-driven, hierarchical approach for the analysis of human actions in visual scenes • Completely unsupervised • The model is suitable for coupled tracking and abnormality detection on different hierarchical stages

  3. Introduction • Previous work: detect anomalies as outliers to previously trained models • Our work: supporting autonomous living of elderly or handicapped people • Rule-based systems: predefined dangerous cases, lacks general applicability

  4. Introduction • Two hierarchical representations: human appearances and sequences of appearances(actions, behavioral patterns) • Map these images to a finite set of symbols describing what is observed • Characterize in which order the observations occur • learning the temporal (e.g. within a day or a week) and spatial dependencies

  5. Appearance hierarchy • Image stream ,arbitrary feature space • Group similar image descriptors together using k-means to create a finite number of clusters • Distance measuredefined in the feature space

  6. Appearance hierarchy(H1) • Eventually, each feature vector is mapped to a symbol • Remove statistical outliers at every clustering step • Distribution of distances of all the samples assigned to this cluster

  7. Feature extraction • Background subtraction • Rescaled to fixed size • Distance measure: chi-squared

  8. Action hierarchy(H2) • Basic actions to encode a state change • Only frequently occurring symbol changes are considered • Higher level micro-actions are combination of lower level micro-actions • Represent image stream as a series of macri-actions of different lengths

  9. Illustration

  10. Anomalies • H1 will be used for tracking and the interpretation of the appearance, H2 is used for the interpretation of actions • To decide which cluster the extracted feature belongs to(high dimension), use data-dependent inlier: • Threshold: 0.05  classified as outlier if its distance to the considered cluster center is larger than 95% of the data in that cluster

  11. Update procedure • Not all possible appearances and actions can be learnt off-line • Include frequent appearances classified as outliers • New leaf node clusters are established and new symbols defined

  12. Update procedure • Update micro-actions using the principle of exponential forgetting • Start with empty database, everything considered abnormal at the beginning

  13. Experiments • Single person in-door videos • 1. Ourliers • 2. Symbols • 3. Actionlength

  14. Experiments • 1. Frequently occurring scenes and abnormal scenes • 2. Previously normal scenes • 3. New frequent normal scenes • 4. Anomalies

  15. Conclusion • Unsupervised analysis of human action scenes. • Two automatically generated and updated hierarchies learned • Normality and anomaly classification • Allows for model update

More Related