Claims Analysis
Total Claims: 21
Claim 1
Independent Claim
60 words
A method for browsing compressed video comprising the steps: building hierarchically a scene transition graph, wherein said graph building step includes the step of providing a graph layout including at least a main scene transition graph having a plurality of nodes representing scenes with the transition paths illustrated for a video sequence; and browsing through the resulting scene transition graph.
Claim 2
Independent Claim
60 words
A method for browsing compressed video comprising the steps: building hierarchically a scene transition graph, wherein said graph building step includes the step of providing a graph layout including at least a main scene transition graph having a plurality of nodes representing scenes with the transition paths illustrated for a video sequence; and browsing through the resulting scene transition graph.
Claim 3
Dependent Claim
36 words
The method of claim 1, wherein said graph building step further includes the step of providing a user in said browsing step the capability to selectively highlighting a particular node of said main scene transition graph.
Claim 4
Dependent Claim
26 words
The method of claim 2, wherein said graph building step further includes the step of providing a window showing the video shots representing the highlighted node.
Claim 5
Dependent Claim
32 words
The method of claim 3, wherein said graph building step further includes the step of providing a window showing the video shots of said main scene transition graph arranged in temporal order.
Claim 6
Dependent Claim
32 words
The method of claim 2, wherein said graph building step further includes the step of providing a window showing the video shots of said main scene transition graph arranged in temporal order.
Claim 7
Dependent Claim
46 words
The method of claim 1, wherein said graph building step further includes the step of reducing said plurality of nodes of said main scene transition graph to show nodes associated with complete scene changes with the transition paths illustrated to provide a top-level scene transition graph.
Claim 8
Dependent Claim
39 words
The method of claim 6, wherein said graph building step further includes the step of providing a user in said browsing step the capability to selectively highlight a particular one of said nodes of said top-level scene transition graph.
Claim 9
Dependent Claim
26 words
The method of claim 7, wherein said graph building step further includes the step of providing a window showing the video shots representing the highlighted node.
Claim 10
Dependent Claim
32 words
The method of claim 8, wherein said graph building step further includes the step of providing a window showing the video shots of said top-level scene transition graph arranged in temporal order.
Claim 11
Dependent Claim
32 words
The method of claim 7, wherein said graph building step further includes the step of providing a window showing the video shots of said top-level scene transition graph arranged in temporal order.
Claim 12
Dependent Claim
26 words
The method of claim 1, wherein said graph building step further includes the step of arranging the identified video shots of a sequence in temporal order.
Claim 13
Dependent Claim
50 words
The method of claim 1, wherein said step of building hierarchically a scene change transition graph, includes the steps of: extracting DC sequences from the compressed video; detecting scene changes between frames of the DC sequences; identifying video shots from said detected scene changes; and clustering the identified video shots.
Claim 14
Independent Claim
90 words
A method for extracting a hierarchical decomposition of a complex video selection for browsing, comprising the steps of: identifying video collecting key frames from said video shots for representing each video segment; classifying the collections of key frames according to gross visual information; and building a graphical representation of the video, the graphical representation being based upon the results of said classifying step and temporal information associated with each video shot, wherein said graphical representation building step includes the step of representing each category of video shot by a node.
Claim 15
Independent Claim
90 words
A method for extracting a hierarchical decomposition of a complex video selection for browsing, comprising the steps of: identifying video collecting key frames from said video shots for representing each video segment; classifying the collections of key frames according to gross visual information; and building a graphical representation of the video, the graphical representation being based upon the results of said classifying step and temporal information associated with each video shot, wherein said graphical representation building step includes the step of representing each category of video shot by a node.
Claim 16
Dependent Claim
29 words
The method of claim 13, wherein said graphical representation building step further includes the step of establishing each edge of said graphs for denoting a temporal relationship between categories.
Claim 17
Dependent Claim
24 words
The method of claim 13, further including the step of using said graphical representation for analyzing the underlying story structure of said video selection.
Claim 18
Dependent Claim
18 words
The method of claim 13, further including the step of compressing said video selection before said identifying step.
Claim 19
Dependent Claim
50 words
The method of claim 13, wherein said building step includes the steps of: grouping said video shots of said key frames into clusters denoted by measures of similarity; and allowing user interaction in said building step via hierarchial clustering of said video shots paired by similarity in said grouping step.
Claim 20
Dependent Claim
23 words
The method of claim 17, wherein said grouping step further includes grouping shots by their proximity values which are not grouped by similarity.
Claim 21
Dependent Claim
32 words
The method of claim 13, wherein said graphical representation is a directed graph, the graph being based upon the results of said classifying step and temporal information associated with each video shot.