US6331859B1
Expired / Lapsed
US
⏱️ 0.0 years remaining
Video skimming system utilizing the vector rank filter
Assignee: Sharp Corp
•
Filing: 1999-04-06
•
Granted: 2001-12-18
•
Expires: 2019-04-06
Abstract
Abstract Automated summarization of digital video sequences is accomplished using a vector rank filter. The consecutive frames of a digital video sequence can be represented as feature vectors which are successively accumulated in a set of vectors. The distortion of the set by the addition of each successive vector or the cumulative distance from each successive vector to all other vectors in the set is determined by a vector rank filter. When the distortion exceeds a threshold value the end of a video segment is detected. Each frame in a video segment can be ranked according to its relative similarity to the other frames of the set by applying the vector rank filter to the feature vectors representing the video frames. To produce a summary of a video sequence which is most representative of the content of the sequence, frames are chosen that correspond to vectors that are the least distant to or produce the least distortion of the set of vectors representing the segment. The ranking of the relative distortion can be used as the basis for selecting more than one frame from each segment to produce a hierarchy of summaries containing greater numbers of the frames having the most representative content.
Inventors
- 👤 Regis J. Crinon
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-10 02:16
CPC Classifications
G; G06; G06F; G06F16/00; G06F16/70; G06F16/78; G06F16/783; G06F16/7847; G06F16/73; G06F16/738; G06F16/739
Claims Analysis
Total Claims: 90
Claim 1
Independent Claim
109 words
A method of creating a summary of a plurality of video frames comprising the steps of: (a) receiving a first frame; (b) receiving a subsequent frame; (c) resolving a homogeneity of content of said first frame and each said subsequent frame received; (d) identifying at least one key frame from said first frame and each said subsequent frame received having content most homogeneous with that of said first frame and each said subsequent frame; (e) comparing said homogeneity of said first frame and each said subsequent frame with a threshold homogeneity; and (f) repeating steps (b) through (e) until said homogeneity has some predefined relationship with said threshold homogeneity.
Claim 2
Independent Claim
109 words
A method of creating a summary of a plurality of video frames comprising the steps of: (a) receiving a first frame; (b) receiving a subsequent frame; (c) resolving a homogeneity of content of said first frame and each said subsequent frame received; (d) identifying at least one key frame from said first frame and each said subsequent frame received having content most homogeneous with that of said first frame and each said subsequent frame; (e) comparing said homogeneity of said first frame and each said subsequent frame with a threshold homogeneity; and (f) repeating steps (b) through (e) until said homogeneity has some predefined relationship with said threshold homogeneity.
Claim 3
Dependent Claim
20 words
The method of claim 1 wherein said homogeneity of content of said frames is resolved with a vector rank filter.
Claim 4
Independent Claim
64 words
A method of identifying a key video frame within a plurality of video frames comprising the steps of: (a) characterizing said plurality of video frames as a plurality of feature vectors; (b) identifying a key feature vector that minimizes the distortion of said plurality of feature vectors; and (c) identifying said video frame corresponding to said key feature vector as said key video frame.
Claim 5
Independent Claim
64 words
A method of identifying a key video frame within a plurality of video frames comprising the steps of: (a) characterizing said plurality of video frames as a plurality of feature vectors; (b) identifying a key feature vector that minimizes the distortion of said plurality of feature vectors; and (c) identifying said video frame corresponding to said key feature vector as said key video frame.
Claim 6
Dependent Claim
27 words
The method of claim 3 wherein said key feature vector that minimizes the distortion of said plurality of feature vectors is identified by a vector rank filter.
Claim 7
Dependent Claim
25 words
The method of claim 3 wherein at least one feature vector of said plurality of feature vectors is a vector signal describing an image histogram.
Claim 8
Dependent Claim
28 words
The method of claim 3 wherein at least one feature vector of said plurality of feature vectors is a vector signal describing an ordered set of image samples.
Claim 9
Dependent Claim
31 words
The method of claim 3 wherein at least one feature vector of said plurality of feature vectors is a vector signal which includes a component describing luminance of said video frame.
Claim 10
Dependent Claim
33 words
The method of claim 3 wherein at least one feature vector of said plurality of feature vectors is a vector signal which includes a component describing the average intensity of said video frame.
Claim 11
Independent Claim
155 words
A method of determining a second boundary of a video segment within a plurality of video frames comprising the steps of: (a) defining a threshold distortion; (b) locating a first frame in said video segment; (c) defining a first feature vector representative of said first frame; (d) including said first feature vector in a set of segment feature vectors; (e) defining a next feature vector representative of a subsequent video frame; (f) including said next feature vector with said set of segment feature vectors; (g) calculating a distortion of said set of segment feature vectors resulting from the inclusion of said next feature vector in said set of segment feature vectors; (h) comparing said distortion of said set of segment feature vectors with said threshold distortion; and (i) repeating steps (e) through (h) until said distortion of said set of segment feature vectors has a predefined relationship to threshold distortion thereby defining said second boundary.
Claim 12
Independent Claim
155 words
A method of determining a second boundary of a video segment within a plurality of video frames comprising the steps of: (a) defining a threshold distortion; (b) locating a first frame in said video segment; (c) defining a first feature vector representative of said first frame; (d) including said first feature vector in a set of segment feature vectors; (e) defining a next feature vector representative of a subsequent video frame; (f) including said next feature vector with said set of segment feature vectors; (g) calculating a distortion of said set of segment feature vectors resulting from the inclusion of said next feature vector in said set of segment feature vectors; (h) comparing said distortion of said set of segment feature vectors with said threshold distortion; and (i) repeating steps (e) through (h) until said distortion of said set of segment feature vectors has a predefined relationship to threshold distortion thereby defining said second boundary.
Claim 13
Dependent Claim
22 words
The method of claim 9 wherein said first feature vector and said next feature vector are vector signals describing an image histogram.
Claim 14
Dependent Claim
22 words
The method of claim 9 wherein said distortion of said set of segment feature vectors is determined with a vector rank filter.
Claim 15
Dependent Claim
24 words
The method of claim 9 wherein said threshold distortion has a predefined relationship to a minimum distortion of said set of segment feature vectors.
Claim 16
Dependent Claim
27 words
The method of claim 12 wherein said predefined relationship to said minimum distortion is a function of a noise power of an image in a video frame.
Claim 17
Dependent Claim
32 words
The method of claim 12 wherein said predefined relationship to said minimum distortion is a function of a compression ratio to be achieved by a summary of said plurality of video frames.
Claim 18
Independent Claim
194 words
A method of creating a summary of a plurality of video frames comprising the steps of: (a) defining a threshold distortion; (b) locating a first frame in a segment of video frames having relatively homogenous content; (c) defining a first feature vector representative of said first frame; (d) including said first feature vector in a set of segment feature vectors; (e) defining a next feature vector representative of a subsequent video frame; (f) including said next feature vector with said set of segment feature vectors; (g) calculating the distortion of said set of segment feature vectors resulting from the inclusion of said next feature vector with said set of segment feature vectors; (h) comparing said distortion of said set of segment feature vectors with said threshold distortion; (i) repeating steps (e) through (h) until said distortion of said set of segment feature vectors has a predefined relationship to said threshold distortion thereby defining a second boundary of said video segment; (j) identifying a key feature vector that minimizes said distortion of said set of segment feature vectors; and (k) identifying said video frame corresponding to said key feature vector as a key video frame.
Claim 19
Independent Claim
194 words
A method of creating a summary of a plurality of video frames comprising the steps of: (a) defining a threshold distortion; (b) locating a first frame in a segment of video frames having relatively homogenous content; (c) defining a first feature vector representative of said first frame; (d) including said first feature vector in a set of segment feature vectors; (e) defining a next feature vector representative of a subsequent video frame; (f) including said next feature vector with said set of segment feature vectors; (g) calculating the distortion of said set of segment feature vectors resulting from the inclusion of said next feature vector with said set of segment feature vectors; (h) comparing said distortion of said set of segment feature vectors with said threshold distortion; (i) repeating steps (e) through (h) until said distortion of said set of segment feature vectors has a predefined relationship to said threshold distortion thereby defining a second boundary of said video segment; (j) identifying a key feature vector that minimizes said distortion of said set of segment feature vectors; and (k) identifying said video frame corresponding to said key feature vector as a key video frame.
Claim 20
Dependent Claim
22 words
The method of claim 15 wherein said distortion of said set of segment feature vectors is determined with a vector rank filter.
Claim 21
Dependent Claim
22 words
The method of claim 15 wherein said first feature vector and said next feature vector are vector signals describing an image histogram.
Claim 22
Dependent Claim
24 words
The method of claim 15 wherein said threshold distortion has a predefined relationship to a minimum distortion of said set of segment feature vectors.
Claim 23
Dependent Claim
22 words
The method of claim 18 wherein said distortion of said set of segment feature vectors is determined with a vector rank filter.
Claim 24
Dependent Claim
22 words
The method of claim 18 wherein said first feature vector and said next feature vector are vector signals describing an image histogram.
Claim 25
Independent Claim
114 words
A method of creating a summary of a plurality of video frames comprising the steps of: (a) dividing said plurality of video frames into at least one video segment of relatively homogeneous content comprising at least one said video frame; (b) defining feature vectors representative of each of said video frames; (c) ranking said feature vectors representing said video frames included in said video segment according to a distortion produced in a set of said feature vectors representing said segment by each of said feature vectors in said set of feature vectors; and (d) including in said summary said video frames represented by said feature vectors ranked as producing a minimum of said distortion.
Claim 26
Independent Claim
114 words
A method of creating a summary of a plurality of video frames comprising the steps of: (a) dividing said plurality of video frames into at least one video segment of relatively homogeneous content comprising at least one said video frame; (b) defining feature vectors representative of each of said video frames; (c) ranking said feature vectors representing said video frames included in said video segment according to a distortion produced in a set of said feature vectors representing said segment by each of said feature vectors in said set of feature vectors; and (d) including in said summary said video frames represented by said feature vectors ranked as producing a minimum of said distortion.
Claim 27
Dependent Claim
16 words
The method of claim 21 wherein said relative distortion is determined with a vector rank filter.
Claim 28
Dependent Claim
15 words
The method of claim 21 wherein said feature vectors are vector signals characterizing image histograms.
Claim 29
Dependent Claim
35 words
The method of claim 21 further comprising the step of including in said summary said video frames represented by said feature vectors ranked as producing relative distortion greater than said minimum of said relative distortion.
Claim 30
Dependent Claim
161 words
The method of claim 21 wherein the step of dividing said plurality of video frames into at least one video segment comprises the steps of: (a) defining a threshold distortion; (b) locating a first frame in said video segment; (c) defining a first feature vector representative of said first frame; (d) including said first feature vector in a set of segment feature vectors; (e) defining a next feature vector representative of a subsequent video frame; (f) including said next feature vector with said set of segment feature vectors; (g) calculating a distortion of said set of segment feature vectors resulting from including said next feature vector with said set of segment feature vectors; (h) comparing said distortion of said set of segment feature vectors with said threshold distortion; and (i) repeating steps (e) through (h) until said distortion of said set of segment feature vectors has a predefined relationship to said threshold distortion thereby defining a second boundary of said segment.
Claim 31
Dependent Claim
22 words
The method of claim 25 wherein said distortion of said set of segment feature vectors is determined with a vector rank filter.
Claim 32
Dependent Claim
19 words
The method of claim 25 wherein said threshold distortion has a predefined relationship to said minimum of said distortion.
Claim 33
Independent Claim
93 words
An apparatus to skim a plurality of video frames of relatively homogeneous content comprising: (a) a receiver to receive said plurality of frames; (b) a vector converter to characterize said plurality of frames as a plurality of vector signals; (c) a vector filter to rank said vector signals according to a relative distortion produced by each of said vector signals in a set of all said vector signals; and (d) a skimmer to identify each of said frames corresponding to each of said vector signals producing said relative distortion of a specified rank.
Claim 34
Independent Claim
93 words
An apparatus to skim a plurality of video frames of relatively homogeneous content comprising: (a) a receiver to receive said plurality of frames; (b) a vector converter to characterize said plurality of frames as a plurality of vector signals; (c) a vector filter to rank said vector signals according to a relative distortion produced by each of said vector signals in a set of all said vector signals; and (d) a skimmer to identify each of said frames corresponding to each of said vector signals producing said relative distortion of a specified rank.
Claim 35
Dependent Claim
15 words
The apparatus of claim 28 wherein said vector signals characterize image histograms of said frames.
Claim 36
Independent Claim
151 words
An apparatus for identifying a last frame in a segment of video frames of relatively homogeneous content within a plurality of video frames comprising: (a) a receiver to receive said plurality of frames; (b) a vector converter to characterize each of said plurality of frames as a vector signal; (c) an accumulator to accumulate a set of said vector signals comprising said vector signal corresponding to a first frame in said segment and successively thereafter said vector signal corresponding to at least one subsequent frame; (d) a vector filter to calculate a distortion of said set of vector signals as each said vector signal is accumulated with said set of vector signals; and (e) a comparator to identify said frame corresponding to said vector signal producing said distortion of said set of vector signals having a predefined relationship to a specified threshold distortion thereby identifying said last frame in said segment.
Claim 37
Independent Claim
151 words
An apparatus for identifying a last frame in a segment of video frames of relatively homogeneous content within a plurality of video frames comprising: (a) a receiver to receive said plurality of frames; (b) a vector converter to characterize each of said plurality of frames as a vector signal; (c) an accumulator to accumulate a set of said vector signals comprising said vector signal corresponding to a first frame in said segment and successively thereafter said vector signal corresponding to at least one subsequent frame; (d) a vector filter to calculate a distortion of said set of vector signals as each said vector signal is accumulated with said set of vector signals; and (e) a comparator to identify said frame corresponding to said vector signal producing said distortion of said set of vector signals having a predefined relationship to a specified threshold distortion thereby identifying said last frame in said segment.
Claim 38
Dependent Claim
25 words
The method of claim 30 wherein said threshold distortion has a predefined relationship to a minimum of said distortion of said set of vector signals.
Claim 39
Independent Claim
201 words
An apparatus for producing a summary of a plurality of video frames comprising: (a) a receiver to receive said plurality of frames; (b) a vector converter to characterize each of said plurality of frames as a vector signal; (c) an accumulator to accumulate a set of said vector signals comprising said vector signal corresponding to a first frame in a segment of frames having relatively homogeneous content and successively thereafter said vector signal corresponding to at least one subsequent frame; (d) a vector filter to calculate a distortion in said set of vector signals as each said vector signal is accumulated in said set of vector signals and rank each said vector signal relative to each other said vector signal in said set of vector signals according to a relative measure of said distortion; (e) a comparator to identify said vector signal producing said distortion in said set of vector signals having a predefined relationship to a specified threshold distortion thereby identifying a last frame in said segment of frames of relatively homogeneous content; and (g) a skimmer to identify each said frame in said segment corresponding to each of said vector signal producing said distortion of a specified relative rank.
Claim 40
Independent Claim
201 words
An apparatus for producing a summary of a plurality of video frames comprising: (a) a receiver to receive said plurality of frames; (b) a vector converter to characterize each of said plurality of frames as a vector signal; (c) an accumulator to accumulate a set of said vector signals comprising said vector signal corresponding to a first frame in a segment of frames having relatively homogeneous content and successively thereafter said vector signal corresponding to at least one subsequent frame; (d) a vector filter to calculate a distortion in said set of vector signals as each said vector signal is accumulated in said set of vector signals and rank each said vector signal relative to each other said vector signal in said set of vector signals according to a relative measure of said distortion; (e) a comparator to identify said vector signal producing said distortion in said set of vector signals having a predefined relationship to a specified threshold distortion thereby identifying a last frame in said segment of frames of relatively homogeneous content; and (g) a skimmer to identify each said frame in said segment corresponding to each of said vector signal producing said distortion of a specified relative rank.
Claim 41
Dependent Claim
17 words
The apparatus of claim 32 wherein said vector signal characterizes an image histogram of said video frame.
Claim 42
Dependent Claim
23 words
The apparatus of claim 32 wherein said threshold distortion has a predefined relationship to a minimum distortion of said set of vector signals.
Claim 43
Independent Claim
116 words
A method of creating a summary of a plurality of video frames comprising the steps of: (a) receiving a first frame; (b) receiving a subsequent frame; (c) resolving a homogeneity of content of said first frame and each said subsequent frame received; (d) comparing said homogeneity of said first frame and each said subsequent frame with a threshold homogeneity; (e) repeating steps (b) through (d) until said homogeneity has some predefined relationship with said threshold homogeneity; and (f) identifying at least one key frame from the set of said first frame and each said subsequent frame received having content that represents a minimum distortion within said set of said first frame and each said subsequent frame.
Claim 44
Independent Claim
116 words
A method of creating a summary of a plurality of video frames comprising the steps of: (a) receiving a first frame; (b) receiving a subsequent frame; (c) resolving a homogeneity of content of said first frame and each said subsequent frame received; (d) comparing said homogeneity of said first frame and each said subsequent frame with a threshold homogeneity; (e) repeating steps (b) through (d) until said homogeneity has some predefined relationship with said threshold homogeneity; and (f) identifying at least one key frame from the set of said first frame and each said subsequent frame received having content that represents a minimum distortion within said set of said first frame and each said subsequent frame.
Claim 45
Dependent Claim
20 words
The method of claim 35 wherein said homogeneity of content of said frames is resolved with a vector rank filter.
Claim 46
Dependent Claim
19 words
The method of claim 35 wherein said homogeneity of content is characterized by a distortion of a vector signal.
Claim 47
Independent Claim
72 words
A method of identifying a key video frame within a plurality of video frames comprising the steps of: (a) characterizing said plurality of video frames as a plurality of feature vectors; (b) identifying a key feature vector characterized by a minimal cumulative distance to all said other feature vectors of said plurality of feature vectors; and (c) identifying said video frame corresponding to said key feature vector as said key video frame.
Claim 48
Independent Claim
72 words
A method of identifying a key video frame within a plurality of video frames comprising the steps of: (a) characterizing said plurality of video frames as a plurality of feature vectors; (b) identifying a key feature vector characterized by a minimal cumulative distance to all said other feature vectors of said plurality of feature vectors; and (c) identifying said video frame corresponding to said key feature vector as said key video frame.
Claim 49
Dependent Claim
23 words
The method of claim 38 wherein said key feature vector characterized by said minimal cumulative distance is identified by a vector median filter.
Claim 50
Dependent Claim
25 words
The method of claim 38 wherein at least one feature vector of said plurality of feature vectors is a vector signal describing an image histogram.
Claim 51
Dependent Claim
28 words
The method of claim 38 wherein at least one feature vector of said plurality of feature vectors is a vector signal describing an ordered set of image samples.
Claim 52
Dependent Claim
34 words
The method of claim 38 wherein at least one feature vector of said plurality of feature vectors is a vector signal which includes a component describing a luminance sample value of said video frame.
Claim 53
Dependent Claim
33 words
The method of claim 38 wherein at least one feature vector of said plurality of feature vectors is a vector signal which includes a component describing the average intensity of said video frame.
Claim 54
Independent Claim
146 words
A method of determining a second boundary of a video segment within a plurality of video frames comprising the steps of: (a) defining a threshold value; (b) locating a first frame in said video segment; (c) defining a first feature vector representative of said first frame; (d) including said first feature vector in a set of segment feature vectors; (e) defining a next feature vector representative of a subsequent video frame; (f) including said next feature vector with said set of segment feature vectors; (g) calculating a cumulative distance from said next feature vector to each said feature vector in said set of segment feature vectors; (h) updating said cumulative distance; (i) comparing said updated cumulative distance with said threshold value; and (j) repeating steps (e) through (i) until said updated cumulative distance has a predefined relationship to said threshold value thereby defining said second boundary.
Claim 55
Independent Claim
146 words
A method of determining a second boundary of a video segment within a plurality of video frames comprising the steps of: (a) defining a threshold value; (b) locating a first frame in said video segment; (c) defining a first feature vector representative of said first frame; (d) including said first feature vector in a set of segment feature vectors; (e) defining a next feature vector representative of a subsequent video frame; (f) including said next feature vector with said set of segment feature vectors; (g) calculating a cumulative distance from said next feature vector to each said feature vector in said set of segment feature vectors; (h) updating said cumulative distance; (i) comparing said updated cumulative distance with said threshold value; and (j) repeating steps (e) through (i) until said updated cumulative distance has a predefined relationship to said threshold value thereby defining said second boundary.
Claim 56
Dependent Claim
22 words
The method of claim 44 wherein said first feature vector and said next feature vector are vector signals describing an image histogram.
Claim 57
Dependent Claim
19 words
The method of claim 44 wherein a minimum of said cumulative distance is determined with a vector median filter.
Claim 58
Dependent Claim
25 words
The method of claim 46 wherein said threshold value has a predefined relationship to said minimum cumulative distance of said set of segment feature vectors.
Claim 59
Dependent Claim
28 words
The method of claim 47 wherein said predefined relationship to said minimum cumulative distance is a function of a noise power of an image in a video frame.
Claim 60
Dependent Claim
33 words
The method of claim 47 wherein said predefined relationship to said minimum cumulative distance is a function of a compression ratio to be achieved by a summary of said plurality of video frames.
Claim 61
Independent Claim
178 words
A method of creating a summary of a plurality of video frames comprising the steps of: (a) defining a threshold value; (b) locating a first frame in a segment of video frames having relatively homogenous content; (c) defining a first feature vector representative of said first frame; (d) including said first feature vector in a set of segment feature vectors; (e) defining a next feature vector representative of a subsequent video frame; (f) including said next feature vector with said set of segment feature vectors; (g) calculating a cumulative distance from said next feature vector to each said feature vector in said set of segment feature vectors; (h) updating said cumulative distance; (i) comparing said updated cumulative distance with said threshold value; (j) repeating steps (e) through (i) until said updated cumulative distance has a predefined relationship to said threshold value thereby defining said second boundary of said video segment; (j) identifying a key feature vector that minimizes said cumulative distance; and (k) identifying said video frame corresponding to said key feature vector as a key video frame.
Claim 62
Independent Claim
178 words
A method of creating a summary of a plurality of video frames comprising the steps of: (a) defining a threshold value; (b) locating a first frame in a segment of video frames having relatively homogenous content; (c) defining a first feature vector representative of said first frame; (d) including said first feature vector in a set of segment feature vectors; (e) defining a next feature vector representative of a subsequent video frame; (f) including said next feature vector with said set of segment feature vectors; (g) calculating a cumulative distance from said next feature vector to each said feature vector in said set of segment feature vectors; (h) updating said cumulative distance; (i) comparing said updated cumulative distance with said threshold value; (j) repeating steps (e) through (i) until said updated cumulative distance has a predefined relationship to said threshold value thereby defining said second boundary of said video segment; (j) identifying a key feature vector that minimizes said cumulative distance; and (k) identifying said video frame corresponding to said key feature vector as a key video frame.
Claim 63
Dependent Claim
19 words
The method of claim 50 wherein a minimum of said cumulative distance is determined with a vector median filter.
Claim 64
Dependent Claim
22 words
The method of claim 50 wherein said first feature vector and said next feature vector are vector signals describing an image histogram.
Claim 65
Dependent Claim
25 words
The method of claim 50 wherein said threshold value has a predefined relationship to said minimum cumulative distance of said set of segment feature vectors.
Claim 66
Dependent Claim
17 words
The method of claim 53 wherein said minimum cumulative distance is determined with a vector rank filter.
Claim 67
Dependent Claim
22 words
The method of claim 53 wherein said first feature vector and said next feature vector are vector signals describing an image histogram.
Claim 68
Independent Claim
113 words
A method of creating a summary of a plurality of video frames comprising the steps of: (a) dividing said plurality of video frames into at least one video segment of relatively homogeneous content comprising at least one said video frame; (b) defining a feature vector representative of each of said video frames; (c) ranking said feature vectors according to a relative cumulative distance from each of said feature vectors to all other said feature vectors in a set of said feature vectors representing said video frames of said segment; and (d) including in said summary said video frames represented by said feature vectors ranked as having a minimum of said relative cumulative distance.
Claim 69
Independent Claim
113 words
A method of creating a summary of a plurality of video frames comprising the steps of: (a) dividing said plurality of video frames into at least one video segment of relatively homogeneous content comprising at least one said video frame; (b) defining a feature vector representative of each of said video frames; (c) ranking said feature vectors according to a relative cumulative distance from each of said feature vectors to all other said feature vectors in a set of said feature vectors representing said video frames of said segment; and (d) including in said summary said video frames represented by said feature vectors ranked as having a minimum of said relative cumulative distance.
Claim 70
Dependent Claim
17 words
The method of claim 56 wherein said relative cumulative distance is determined with a vector rank filter.
Claim 71
Dependent Claim
15 words
The method of claim 56 wherein said feature vectors are vector signals characterizing image histograms.
Claim 72
Dependent Claim
39 words
The method of claim 56 further comprising the step of including in said summary said video frames represented by said feature vectors ranked as being at a relative cumulative distance greater than said minimum of said relative cumulative distance.
Claim 73
Dependent Claim
154 words
The method of claim 56 wherein the step of dividing said plurality of video frames into at least one video segment comprises the steps of: (a) defining a threshold value; (b) locating a first frame in said video segment; (c) defining a first feature vector representative of said first frame; (d) including said first feature vector in a set of segment feature vectors; (e) defining a next feature vector representative of a subsequent video frame; (f) including said next feature vector with said set of segment feature vectors; (g) calculating a cumulative distance from said next feature vector to each said feature vector in said set of segment feature vectors; (h) updating said cumulative distance; (i) comparing said updated cumulative distance with said threshold value; and (j) repeating steps (e) through (i) until said updated cumulative distance has a predefined relationship to said threshold value thereby defining said second boundary of said video segment.
Claim 74
Dependent Claim
19 words
The method of claim 60 wherein a minimum of said cumulative distance is determined with a vector median filter.
Claim 75
Dependent Claim
20 words
The method of claim 60 wherein said threshold value has a predefined relationship to said minimum of said cumulative distance.
Claim 76
Dependent Claim
17 words
The method of claim 56 wherein said relative cumulative distance is determined with a vector clustering algorithm.
Claim 77
Independent Claim
100 words
An apparatus to skim a plurality of video frames of relatively homogeneous content comprising: (a) a receiver to receive said plurality of frames; (b) a vector converter to characterize said plurality of frames as a plurality of vector signals; (c) a vector filter to rank said vector signals according to a relative cumulative distance from each of said vector signals to all other said vector signals in a set of all said vector signals; and (d) a skimmer to identify each of said frames corresponding to each of said vector signals producing said relative cumulative distance of a specified rank.
Claim 78
Independent Claim
100 words
An apparatus to skim a plurality of video frames of relatively homogeneous content comprising: (a) a receiver to receive said plurality of frames; (b) a vector converter to characterize said plurality of frames as a plurality of vector signals; (c) a vector filter to rank said vector signals according to a relative cumulative distance from each of said vector signals to all other said vector signals in a set of all said vector signals; and (d) a skimmer to identify each of said frames corresponding to each of said vector signals producing said relative cumulative distance of a specified rank.
Claim 79
Dependent Claim
15 words
The apparatus of claim 64 wherein said vector signals characterize image histograms of said frames.
Claim 80
Independent Claim
160 words
An apparatus for identifying a last frame in a segment of video frames of relatively homogeneous content within a plurality of video frames comprising: (a) a receiver to receive said plurality of frames; (b) a vector converter to characterize each of said plurality of frames as a vector signal; (c) an accumulator to accumulate a set of said vector signals comprising said vector signal corresponding to a first frame in said segment and successively thereafter said vector signal corresponding to at least one subsequent frame; (d) a vector filter to calculate a relative cumulative distance from said vector signal to each other said vector signal of said set of vector signals as each said vector signal is accumulated with said set of vector signals; and (e) a comparator to identify said frame corresponding to said vector signal characterized by said relative cumulative distance having a predefined relationship to a specified threshold value thereby identifying said last frame in said segment.
Claim 81
Independent Claim
160 words
An apparatus for identifying a last frame in a segment of video frames of relatively homogeneous content within a plurality of video frames comprising: (a) a receiver to receive said plurality of frames; (b) a vector converter to characterize each of said plurality of frames as a vector signal; (c) an accumulator to accumulate a set of said vector signals comprising said vector signal corresponding to a first frame in said segment and successively thereafter said vector signal corresponding to at least one subsequent frame; (d) a vector filter to calculate a relative cumulative distance from said vector signal to each other said vector signal of said set of vector signals as each said vector signal is accumulated with said set of vector signals; and (e) a comparator to identify said frame corresponding to said vector signal characterized by said relative cumulative distance having a predefined relationship to a specified threshold value thereby identifying said last frame in said segment.
Claim 82
Dependent Claim
20 words
The method of claim 66 wherein said threshold value has a predefined relationship to a minimum of said cumulative distance.
Claim 83
Independent Claim
213 words
An apparatus for producing a summary of a plurality of video frames comprising: (a) a receiver to receive said plurality of frames; (b) a vector converter to characterize each of said plurality of frames as a vector signal; (c) an accumulator to accumulate a set of said vector signals comprising said vector signal corresponding to a first frame in a segment of frames having relatively homogeneous content and successively thereafter said vector signal corresponding to at least one subsequent frame; (d) a vector filter to calculate a cumulative distance from each said vector signal to each other said vector signal of said set of vector signals as each said vector signal is accumulated in said set of vector signals; and rank each said vector signal relative to each other said vector signal in said set of vector signals according to a relative measure of said cumulative distance; (e) a comparator to identify said vector signal characterized by said relative cumulative distance having a predefined relationship to a specified threshold value thereby identifying a last frame in said segment of frames of relatively homogeneous content; and (g) a skimmer to identify each said frame in said segment corresponding to each said vector signal characterized by said relative cumulative distortion of a specified relative rank.
Claim 84
Independent Claim
213 words
An apparatus for producing a summary of a plurality of video frames comprising: (a) a receiver to receive said plurality of frames; (b) a vector converter to characterize each of said plurality of frames as a vector signal; (c) an accumulator to accumulate a set of said vector signals comprising said vector signal corresponding to a first frame in a segment of frames having relatively homogeneous content and successively thereafter said vector signal corresponding to at least one subsequent frame; (d) a vector filter to calculate a cumulative distance from each said vector signal to each other said vector signal of said set of vector signals as each said vector signal is accumulated in said set of vector signals; and rank each said vector signal relative to each other said vector signal in said set of vector signals according to a relative measure of said cumulative distance; (e) a comparator to identify said vector signal characterized by said relative cumulative distance having a predefined relationship to a specified threshold value thereby identifying a last frame in said segment of frames of relatively homogeneous content; and (g) a skimmer to identify each said frame in said segment corresponding to each said vector signal characterized by said relative cumulative distortion of a specified relative rank.
Claim 85
Dependent Claim
17 words
The apparatus of claim 68 wherein said vector signal characterizes an image histogram of said video frame.
Claim 86
Dependent Claim
24 words
The apparatus of claim 68 wherein said threshold distortion has a predefined relationship to a minimum cumulative distance for said set of vector signals.
Claim 87
Independent Claim
117 words
A method of creating a summary of a plurality of video frames comprising the steps of: (a) receiving a first frame; (b) receiving a subsequent frame; (c) resolving a homogeneity of content of said first frame and each said subsequent frame received; (d) comparing said homogeneity of said first frame and each said subsequent frame with a threshold homogeneity; (e) repeating steps (b) through (d) until said homogeneity has some predefined relationship with said threshold homogeneity; and (f) identifying at least one key frame from the set of said first frame and each said subsequent frame received having content that represents a minimum cumulative distance to said set of said first frame and each said subsequent frame.
Claim 88
Independent Claim
117 words
A method of creating a summary of a plurality of video frames comprising the steps of: (a) receiving a first frame; (b) receiving a subsequent frame; (c) resolving a homogeneity of content of said first frame and each said subsequent frame received; (d) comparing said homogeneity of said first frame and each said subsequent frame with a threshold homogeneity; (e) repeating steps (b) through (d) until said homogeneity has some predefined relationship with said threshold homogeneity; and (f) identifying at least one key frame from the set of said first frame and each said subsequent frame received having content that represents a minimum cumulative distance to said set of said first frame and each said subsequent frame.
Claim 89
Dependent Claim
20 words
The method of claim 71 wherein said homogeneity of content of said frames is resolved with a vector median filter.
Claim 90
Dependent Claim
31 words
The method of claim 71 wherein said homogeneity of content is characterized by a cumulative distance from a vector signal to all other vector signals in said set of vector signals.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2004-12-17 | 2005-06-18 | 2005-12-18 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2008-12-17 | 2009-06-18 | 2009-12-18 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2012-12-17 | 2013-06-18 | 2013-12-18 | $7700.00 | Window Closed / Lapsed |