Patent · US Active

Efficient retrieval of anomalous events with priority learning

US9158976B2 · kind B2 · utility

5Cited by
3References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 18, 2011
Grant dateOct 13, 2015
Priority date
Expiry dateFeb 12, 2034

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG16B40/00
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Local models learned from anomaly detection are used to rank detected anomalies. The local models include image feature values extracted from an image field of video image data with respect to different predefined spatial and temporal local units, wherein anomaly results are determined by failures to fit to applied anomaly detection module local models. Image features values extracted from the image field local units associated with anomaly results are normalized, and image feature values extracted from the image field local units are clustered. Weights for anomaly results are learned as a function of the relations of the normalized extracted image feature values to the clustered image feature values. The normalized values are multiplied by the learned weights to generate ranking values to rank the anomalies.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.