Video analysis methods and apparatus

• US 10,217,226 B2
• Filed: 01/19/2016
• Issued: 02/26/2019
• Est. Priority Date: 12/16/2015
• Status: Active Grant

• Current Assignee: Oneberry Technologies Pte., Ltd.
• Original Assignee: Vi Dimensions Pte Ltd.
• Inventors: Maranatha, Yosua Michael, Tay Meng Keat, Christopher, Looi, Raymond, Sriram, Ashish
• Primary Examiner(s): Dang, Duy M
• Application Number:
  US15/000,418
• Publication Number:
  US 20170178343A1
• Time in Patent Office: 1,134 Days
• CPC Class Codes: G06F 18/217 Validation; Performance evaluation; Active pattern learning techniques
• CPC Class Codes: G06F 18/23 Clustering techniques
• CPC Class Codes: G06F 18/254 of classification results, e.g. of results related to same input data
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/251 involving models
• CPC Class Codes: G06V 10/776 Validation; Performance evaluation
• CPC Class Codes: G06V 10/809 of classification results, e.g. where the classifiers operate on the same input data
• CPC Class Codes: G06V 20/41 Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items segmenting video sequences G06V20/49
• CPC Class Codes: G06V 20/44 Event detection
• CPC Class Codes: G06V 20/46 Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69

Abstract

Video analysis methods are described in which abnormalities are detected by comparing features extracted from a video sequence or motion patterns determined from the video sequence with a statistical model. The statistical model may be updated during the video analysis.

Claims

1. A method of identifying abnormal events in a video sequence, the method comprising a detection process which uses a trained statistical model, the detection process comprising:

extracting features from the video sequence;

discretizing the extracted features;

determining an abnormality measure for each feature by comparing the extracted features with the trained statistical model, the trained statistical model comprising a histogram indicating a frequency distribution of discretized features extracted from the video sequence, wherein the abnormality measure is determined from the histogram;

identifying an abnormal event using the abnormality measure; and

updating the frequency distribution with the extracted discretized features.

2. A method according to claim 1, the detection process further comprising pruning the updated frequency distribution if the updated frequency distribution exceeds a threshold number of entries.

3. A method according to claim 1, the detection process further comprising determining for a portion of the video sequence, a set of discretized features present in the portion of the video sequence and a frequency of occurrence in the portion of the video sequence of each discretized feature of the set of discretized features.

4. A method according to claim 3, the detection process further comprising determining an abnormality measure for the portion of the video sequence as a function of the abnormality measures for each of the discretized features and the frequency of occurrence of the discretized features.

5. A method according to claim 1, wherein identifying an abnormal event using the abnormality measure comprises comparing the abnormality measure with a threshold and identifying an abnormal event when the abnormality measure is greater than the threshold.

6. A method according to claim 1, further comprising displaying to a user an indication of the location of the abnormal event on a frame of the video sequence.

7. A method according to claim 1, further comprising receiving a user indication of a set of discretized features and modifying the frequency in the frequency distribution of the indicated set of discretized features.

8. A method according to claim 1, wherein the features comprise optical flow.

9. A non-transitory computer readable carrier medium carrying processor executable instructions which when executed on a processor cause the processor to carry out a method according to claim 1.

10. A method of identifying abnormal events in a video sequence, the method comprising:

extracting features from the video sequence;

determining an abnormality measure for each feature by comparing the extracted features with a statistical model;

applying a pre-defined rule to the video sequence to generate a rule based event indication; and

identifying an abnormal event by determining a correlation between the abnormality measure and the rule based event indication.

11. An apparatus for identifying abnormal events in a video sequence, the apparatus comprising:

a computer processor and a data storage device, the data storage device having a feature extractor module and an abnormality detector module comprising non-transitory instructions operative by the processor to carry out a detection process which uses a trained statistical model, the detection process comprising;

extract features from the video sequence;

discretize the extracted features;

determine an abnormality measure for each feature by comparing the extracted features with the trained statistical model, the trained statistical model comprising a histogram indicating a frequency distribution of discretized features extracted from the video sequence, wherein the abnormality measure is determined from the histogram;

identify an abnormal event using the abnormality measure; and

update the frequency distribution with the extracted discretized features.

12. An apparatus according to claim 11, wherein the features comprise optical flow.