G06V 20/30
Definition
Diese Klassifikationsstelle umfasst:(Für diese Definition ist die deutsche Übersetzung noch nicht abgeschlossen)
Generating groups or clusters from images or video based on their similarity, based on events, backgrounds, identified individuals, etc.
Comparing and forming connections between image collections using matching, classification and clustering.
Detecting or recognising events in an image collection and ordering these events in an event timeline, based on image content.
Construction of a social network by analysis of an image collection.
Examples
Steps for constructing a dynamic social network from raw video data of observations of people
Querverweise
Informative Querverweise
| Global feature extraction by analysis of the whole pattern, e.g. global shape, global boundary descriptors or involving frequency domain transformations or autocorrelation | G06V 10/42 |
| Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components, edge linking or neighbouring slice analysis | G06V 10/44 |
| Recognition using clustering in general | G06V 10/762 |
| Recognition of patterns in video content, e.g. in a film or a TV broadcasting | G06V 20/40 |
| Recognition of scenes under surveillance or monitoring activities, e.g. recognising suspicious objects | G06V 20/52 |
| Labelling scene content, e.g. semantic segmentation | G06V 20/70 |
| Recognition of human bodies within image or video data | G06V 40/10 |
| Recognition of human faces, e.g. facial parts, sketches or expressions within image or video data | G06V 40/16 |
| Information retrieval of image data | G06F 16/50 |
| Information retrieval of video data | G06F 16/70 |
Spezielle Klassifizierungsregeln
Detection of events in video surveillance, in particular suspicious activities or objects is classified in group G06V 20/52. Labelling of scene content, e.g. by semantic segmentation is classified in group G06V 20/70.
G06V 20/30
Definition Statement
This place covers:Generating groups or clusters from images or video based on their similarity, based on events, backgrounds, identified individuals, etc.
Comparing and forming connections between image collections using matching, classification and clustering.
Detecting or recognising events in an image collection and ordering these events in an event timeline, based on image content.
Construction of a social network by analysis of an image collection.
Examples
Steps for constructing a dynamic social network from raw video data of observations of people
References
Informative references
| Global feature extraction by analysis of the whole pattern, e.g. global shape, global boundary descriptors or involving frequency domain transformations or autocorrelation | G06V 10/42 |
| Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components, edge linking or neighbouring slice analysis | G06V 10/44 |
| Recognition using clustering in general | G06V 10/762 |
| Recognition of patterns in video content, e.g. in a film or a TV broadcasting | G06V 20/40 |
| Recognition of scenes under surveillance or monitoring activities, e.g. recognising suspicious objects | G06V 20/52 |
| Labelling scene content, e.g. semantic segmentation | G06V 20/70 |
| Recognition of human bodies within image or video data | G06V 40/10 |
| Recognition of human faces, e.g. facial parts, sketches or expressions within image or video data | G06V 40/16 |
| Information retrieval of image data | G06F 16/50 |
| Information retrieval of video data | G06F 16/70 |
Special rules of classification
Detection of events in video surveillance, in particular suspicious activities or objects is classified in group G06V 20/52. Labelling of scene content, e.g. by semantic segmentation is classified in group G06V 20/70.