Video analysis methods and apparatus
First Claim
Patent Images
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.
4 Assignments
0 Petitions
Accused Products
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.
13 Citations
12 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. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
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. - View Dependent Claims (12)
-
Specification