Event detection apparatus and event detection method
First Claim
1. An event detection apparatus comprising:
- at least one processor and memory coupled to each other and cooperating to act as;
an input unit configured to input a plurality of time-sequential images;
a first extraction unit configured to extract sets of first image samples, the sets of first image samples composed of a plurality of layers, wherein each layer from the plurality of layers corresponds to a different sampling interval from a first time range of the plurality of time-sequential images, wherein each set of first image samples is composed of a plurality of image samples;
a second extraction unit configured to extract sets of second image samples, the sets of second image samples composed of a plurality of layers, wherein each layer from the plurality of layers corresponds to a different sampling interval from a second time range of the plurality of time-sequential images, wherein each set of second image samples is composed of a plurality of image samples;
a dissimilarity calculation unit configured to calculate a dissimilarity between a set of the first image samples and a set of the second image samples that have the same sampling interval, for each layer from the plurality of layers; and
a detection unit configured to detect an event from the plurality of time-sequential images based on the calculated dissimilarity for each layer from the plurality of layers.
1 Assignment
0 Petitions
Accused Products
Abstract
An event detection apparatus includes an input unit configured to input a plurality of time-sequential images, a first extraction unit configured to extract sets of first image samples according to respective different sample scales from a first time range of the plurality of time-sequential images based on a first scale parameter, a second extraction unit configured to extract sets of second image samples according to respective different sample scales from a second time range of the plurality of time-sequential images based on a second scale parameter, a dissimilarity calculation unit configured to calculate a dissimilarity between the first and second image samples based on the sets of the first and second image samples, and a detection unit configured to detect an event from the plurality of time-sequential images based on the dissimilarity.
-
Citations
11 Claims
-
1. An event detection apparatus comprising:
-
at least one processor and memory coupled to each other and cooperating to act as; an input unit configured to input a plurality of time-sequential images; a first extraction unit configured to extract sets of first image samples, the sets of first image samples composed of a plurality of layers, wherein each layer from the plurality of layers corresponds to a different sampling interval from a first time range of the plurality of time-sequential images, wherein each set of first image samples is composed of a plurality of image samples; a second extraction unit configured to extract sets of second image samples, the sets of second image samples composed of a plurality of layers, wherein each layer from the plurality of layers corresponds to a different sampling interval from a second time range of the plurality of time-sequential images, wherein each set of second image samples is composed of a plurality of image samples; a dissimilarity calculation unit configured to calculate a dissimilarity between a set of the first image samples and a set of the second image samples that have the same sampling interval, for each layer from the plurality of layers; and a detection unit configured to detect an event from the plurality of time-sequential images based on the calculated dissimilarity for each layer from the plurality of layers. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. An event detection method comprising:
-
inputting a plurality of time-sequential images; extracting sets of first image samples, the sets of first image samples composed of a plurality of layers, wherein each layer from the plurality of layers corresponds to a different sampling interval from a first time range of the plurality of time-sequential images, wherein each set of first image samples is composed of a plurality of image samples; extracting sets of second image samples, the sets of second image samples composed of a plurality of layers, wherein each layer from the plurality of layers corresponds to a different sampling interval from a second time range of the plurality of time-sequential images, wherein each set of second image samples is composed of a plurality of image samples; calculating a dissimilarity between a set of the first image samples and a set of the second image samples that have the same sampling interval, for each layer from the plurality of layers; detecting an event from the plurality of time-sequential images based on the calculated dissimilarity for each layer from the plurality of layers. - View Dependent Claims (11)
-
Specification