Multimedia integration description scheme, method and system for MPEG-7
View Patent ↗The invention provides a system and method for integrating multimedia descriptions in a way that allows humans, software components or devices to easily identify, represent, manage, retrieve, and categorize the multimedia content. In this manner, a user who may be interested in locating a specific piece of multimedia content from a database, Internet, or broadcast media, for example, may search for and find the multimedia content. In this regard, the invention provides a system and method that receives multimedia content and separates the multimedia content into separate components which are assigned to multimedia categories, such as image, video, audio, synthetic and text. Within each of the multimedia categories, the multimedia content is classified and descriptions of the multimedia content are generated. The descriptions are then formatted, integrated, using a multimedia integration description scheme, and the multimedia integration description is generated for the multimedia content. The multimedia description is then stored into a database. As a result, a user may query a search engine which then retrieves the multimedia content from the database whose integration description matches the query criteria specified by the user. The search engine can then provide the user a useful search result based on the multimedia integration description.
1. A computer-implemented method for generating description records from media content, the method comprising:
based on media content, generating non-hierarchical entity relation graph descriptions for at least one multimedia type, wherein the non-hierarchical entity relation graph descriptions are associated with communication between multimedia objects and not spatial, temporal or semantic relationships between multimedia objects; and
integrating the multimedia object descriptions and the entity relation graph descriptions to generate at least one description record to represent content embedded within the multimedia content.
2. The method of claim 1 , further comprising generating, from the multimedia content, multimedia object hierarchy descriptions by object hierarchy construction and extraction processing, for at least one of the multimedia types.
3. The method of claim 1 , wherein the multimedia types include at least one of image, audio, video, synthetic, and text.
4. The method of claim 1 , wherein generating non- hierarchical entity graph descriptions for at least one multimedia object based on the media content further comprises:
identifying multimedia types and multimedia content; and
extracting of multimedia objects to generate multimedia object descriptions from the multimedia content for at least one of the multimedia types, wherein generating the non- hierarchical entity relation graph is based on at least in part on the multimedia object descriptions, and further wherein extracting of multimedia objects further comprises:
segmenting each multimedia content into segments including content from at least one of the multimedia types for the multimedia content; and
generating at least one feature description for at least one of the segments by feature extraction and annotation, wherein the generated multimedia object descriptions comprise the at least one feature description for the at least one segment.
5. The method of claim 4 , wherein the segments are selected from the group consisting of local segments and global segments.
6. The method of claim 4 , further comprising selecting the at least one feature description from the group consisting of media, semantic and temporal features.
7. The method of claim 6 , wherein the media features are further defined by at least one feature description selected from the group consisting of data location, scalable representation and modality transcoding.
8. The method of claim 6 , wherein the semantic features are further defined by at least one feature description selected from the group consisting of keywords, who, what object, what action, why, when, where and text annotation.
9. The method of claim 6 , wherein the temporal features are further defined by at least one feature description consisting of duration.
10. The method of claim 4 , wherein the extracting of multimedia objects further comprises:
generating media object descriptions from the multimedia segment for one of the multimedia types by media object extraction processing;
generating media object hierarchy descriptions from the generated media object descriptions by object hierarchy construction and extraction processing; and
generating media entity relation graph descriptions from the generated media object descriptions by entity relation graph generation processing.
11. The method of claim 10 , wherein generating media object descriptions further comprises:
segmenting the content of each multimedia type in the multimedia object into segments within the multimedia object by media segmentation processing; and
generating at least one feature description for at least one of the segments by feature extraction and annotation;
wherein the generated media object descriptions comprise the at least one feature description for the at least one of the segments.
12. The method of claim 11 , further comprising the step of selecting the at least one feature description from the group consisting of media, semantic and temporal.
13. The method of claim 11 , wherein generating media object hierarchy descriptions generates media object hierarchy descriptions of the media object descriptions based on media feature relationships of media objects represented by the media object descriptions.
14. The method of claim 11 , wherein generating media object hierarchy descriptions generates semantic object hierarchy descriptions of the media object descriptions based on semantic feature relationships of media objects represented by the media object descriptions.
15. The method of claim 11 , wherein generating media object hierarchy descriptions generates temporal object hierarchy descriptions of the media object descriptions based on temporal features relationships of media objects represented by the media object descriptions.
16. The method of claim 11 , wherein generating media object hierarchy descriptions generates media object hierarchy descriptions of the media object descriptions based on relationships of media objects represented by the media object descriptions, and wherein the relationships are selected from the group consisting of media feature relationships, semantic feature relationships, temporal feature relationships, and spatial feature relationships.
17. The method of claim 11 , wherein generating media entity relation graph descriptions generates entity relation graph descriptions of the media object descriptions based on relationship of the media objects represented by the media object descriptions, wherein the relationships are selected from the group consisting of media feature relationships, semantic feature relationships, temporal feature relationships and spatial feature relationships.
18. The method of claim 1 , wherein generating multimedia object hierarchy descriptions generates multimedia object hierarchy descriptions of the multimedia object descriptions based on media feature relationships of multimedia objects represented by the multimedia object descriptions.
19. The method of claim 1 , wherein generating multimedia object hierarchy descriptions generates semantic object hierarchy descriptions of the multimedia object descriptions based on semantic feature relationships of multimedia objects represented by the multimedia object descriptions.
20. The method of claim 1 , wherein generating multimedia object hierarchy descriptions generates temporal object hierarchy descriptions of the multimedia object descriptions based on temporal feature relationships of multimedia objects represented by the multimedia object descriptions.
21. The method of claim 1 , wherein generating multimedia object hierarchy descriptions generates multimedia object hierarchy descriptions of the multimedia object descriptions based on relationships of multimedia objects represented by the multimedia object descriptions, wherein the relationships are selected from the group consisting of media feature relationships, semantic feature relationships, temporal feature relationships and spatial feature relationships.
22. The method of claim 1 , wherein generating entity relation graph descriptions generates the entity relation graph descriptions of the multimedia object descriptions based on relationships of multimedia objects represented by the multimedia object descriptions, wherein the relationships are selected from the group consisting of media feature relationships, semantic feature relationships, temporal feature relationships and spatial feature relationships.
23. The method of claim 1 , further comprising receiving and encoding the multimedia object descriptions into encoded description information, and storing the encoded description information as the at least one description record.
24. The method of claim 1 , farther comprising combining the multimedia object description, the multimedia object hierarchy descriptions, and the entity relation graph description to form a multimedia description, and receiving and encoding the multimedia description into encoded description information, and storing the encoded description information as the at least one description record.