DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Objections
Claims 2-4, 6, 9-11, 13, 16-18 and 20 are objected to because of the following informalities:
Claim 2, line 4, “of each of video frame features” should read “of each of the video frame features”
Similar issue in claim 3, line 1 and line 5
Similar issue in claim 9, line 4
Similar issue in claim 10, line 1 and line 5
Similar issue in claim 16, line 4
Similar issue in claim 17, line 2 and line 6
Claim 4 claims Ki,j is the similarity between an i-th video frame feature Fj, and should instead be Fi
Similar issue in claim 11
Similar issue in claim 18
Claim 6, Fi is claimed, but there is no Fi in the equation of claim 6. It appears Ft should be referenced instead
Similar issue in claim 13
Similar issue in claim 20
Appropriate correction is required.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1-5, 7-12, 14-19 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by CN110991321A (hereinafter Biao – of which a machine translation from Google Patents has been provided).
Regarding independent claim 1, Biao discloses a computer-implemented video feature extraction method (abstract, “The invention relates to a video pedestrian re-identification method based on label correction and weighted feature fusion, and belongs to the field of computer vision and biometric identification”), the method comprising:
obtaining a target video sequence that comprises a plurality of video frames (page 4, “The data preprocessing is to preprocess the original video shot by the camera, so that the subsequent steps can be conveniently carried out. ”);
performing video frame feature extraction on the target video sequence to obtain video frame features of each of the plurality of video frames (page 3, “ the method comprises the following steps of extracting pedestrian video fragments;” page 4, “Step two: convolutional neural network extraction of video frame features The main network used by the invention is a residual error network ResNet50 commonly used in the field of computer vision at present, the step length used in the last block by an original ResNet50 is 2, and in order to improve the resolution of the extracted image characteristics, the step length of the last block of ResNet50 is set to be 1, so that the loss of information can be reduced. ”);
performing feature weight calculation on each of the video frame features to obtain the feature weight of each of the video frame features (page 3, “The weight of each frame of image is calculated by utilizing the similarity between each image feature in the same video segment, the video features are obtained in a weighting fusion mode”);
wherein the feature weight of each of the video frame features is determined by the video frame features of all of the video frames in the target video sequence (page 3, “The weight of each frame of image is calculated by utilizing the similarity between each image feature in the same video segment, the video features are obtained in a weighting fusion mode;” page 4, “And calculating the similarity by using the video features obtained in the step three and video features extracted in advance from the candidate pedestrian library, selecting k pedestrian video clips with the maximum similarity as a final matching result;” page 4, “ For all video frames of a video sequence S ═ { I ═ I1,I2,I3,…,InDefine F ═ F1,f2,f3,…,fnAnd E, extracting the corresponding video frame characteristics in the step two. F is theniCorresponding weight αiThe calculation formula is as follows: αi＝λsi1+(1-λ)savg wherein s isi1Is fiAnd f1Similarity of (S)avgIs fiAnd fj(j ≠ i) is an average value of similarity degrees of (1, 2,3, …, n; j ≠ i), and λ is a weight coefficient.”); and
performing feature weighting on each of the video frame features according to the feature weight of each of the video frame features to obtain video features of the target video sequence (page 3, “The weight of each frame of image is calculated by utilizing the similarity between each image feature in the same video segment, the video features are obtained in a weighting fusion mode;” page 4, “The characteristics obtained in step two are each view And image features of the frequency frames are fused in a weighting mode to obtain video features, and the video features are used as final feature representation.”).
Regarding dependent claim 2, the rejection of claim 1 is incorporated herein. Additionally, Biao further discloses wherein performing feature weight calculation on each of the video frame features to obtain the feature weight of each of the video frame features comprises:
calculating a similarity of each of video frame features to obtain a feature similarity matrix (page 3, “The weight of each frame of image is calculated by utilizing the similarity between each image feature in the same video segment, the video features are obtained in a weighting fusion mode;” page 4, “And calculating the similarity by using the video features obtained in the step three and video features extracted in advance from the candidate pedestrian library, selecting k pedestrian video clips with the maximum similarity as a final matching result;” page 4, “ For all video frames of a video sequence S ═ { I ═ I1,I2,I3,…,InDefine F ═ F1,f2,f3,…,fnAnd E, extracting the corresponding video frame characteristics in the step two. F is theniCorresponding weight αiThe calculation formula is as follows: αi＝λsi1+(1-λ)savg wherein s isi1Is fiAnd f1Similarity of (S)avgIs fiAnd fj(j ≠ i) is an average value of similarity degrees of (1, 2,3, …, n; j ≠ i), and λ is a weight coefficient.”); and
performing feature weight calculation on each of the video frame features to obtain the feature weight of each of the video frame features according to the feature similarity matrix (page 5, “Meanwhile, in the weighted feature fusion stage, the feature weight is calculated according to the similarity of the features and other features of the same video sequence, so that the influence of noise on the final video features can be further reduced, and the robustness of pedestrian re-identification of the video is improved.”).
Regarding dependent claim 3, the rejection of claim 2 is incorporated herein. Additionally, Biao further discloses wherein calculating the similarity of each of video frame features to obtain the feature similarity matrix comprises:
performing a convolution operation on each of the video frame features to obtain a feature vector of each of the video frame features (page 4, “Step two: convolutional neural network extraction of video frame features;” page 4, “ The size of the input image is 256 × 128 × 3, the image characteristics of each pedestrian video frame are obtained after the processing of ResNet50, and the size of the output pedestrian video frame characteristics is 2048 × 1.”); and
calculating the similarity of each of video frame features to obtain the feature similarity matrix according to the feature vector of each of the video frame features (page 3, “The weight of each frame of image is calculated by utilizing the similarity between each image feature in the same video segment, the video features are obtained in a weighting fusion mode;” page 4, “And calculating the similarity by using the video features obtained in the step three and video features extracted in advance from the candidate pedestrian library, selecting k pedestrian video clips with the maximum similarity as a final matching result;” page 4, “ For all video frames of a video sequence S ═ { I ═ I1,I2,I3,…,InDefine F ═ F1,f2,f3,…,fnAnd E, extracting the corresponding video frame characteristics in the step two. F is theniCorresponding weight αiThe calculation formula is as follows: αi＝λsi1+(1-λ)savg wherein s isi1Is fiAnd f1Similarity of (S)avgIs fiAnd fj(j ≠ i) is an average value of similarity degrees of (1, 2,3, …, n; j ≠ i), and λ is a weight coefficient.”).
Regarding dependent claim 4, the rejection of claim 3 is incorporated herein. Additionally, Biao further discloses wherein the similarity is calculated according to the following equation:
KI=
PNG
media_image1.png
63
186
media_image1.png
Greyscale
, whereKi,1 represents the feature similarity between a i-th video frame feature F and a j-th video frame feature F, f(Fl) represents the feature vector of the video frame feature Fi, f (F) represents the feature vector of the video frame feature F,||*|| represents a norm of a vector * (page 5, “For two vectors in a given d-dimensional space, p ═ p (p)1,p2…,pd),q＝(q1,q2…,qd) The similarity of p and q is calculated as follows:
PNG
media_image2.png
131
654
media_image2.png
Greyscale
;” page 5, “s (p, q) represents the similarity of p to q; s (q, p) represents the similarity of q to p; the | p | and | q | are the modulo lengths of the vector p and the vector q, respectively.”).
Regarding dependent claim 5, the rejection of claim 4 is incorporated herein. Additionally, Biao further discloses wherein the feature weight is calculated according to the following equation:
si = 1/TKi,t, where si is the feature weight of the i-th video frame feature Fi,
PNG
media_image3.png
32
46
media_image3.png
Greyscale
is a t-th feature similarity in an i-th row in the feature similarity matrix, and T represents an amount of the video frames in the target video sequence (page 2, “Corresponding weight αiThe calculation formula is as follows: αi＝λsi1+(1-λ)savg;” this formula performs a weighting calculation, similar to that as claimed in that the feature wait is being calculated, based upon the similarity values; determining a weight based upon a total frame count is similar to determining an average across the weights).
Regarding dependent claim 7, the rejection of claim 1 is incorporated herein. Additionally, Biao further discloses wherein performing video frame feature extraction on the target video sequence to obtain video frame features of each of the plurality of video frame comprises:
performing video frame feature extraction on each of the video frames in the target video sequence to obtain the video frame features of each video frame using a preset video frame feature extraction network (page 3, “video pedestrian re-identification generally adopts a deep learning-based method, and the basic idea is to extract the features of each frame of image in a video segment;” page 4, “Step two: convolutional neural network extraction of video frame features;” page 4, “ The size of the input image is 256 × 128 × 3, the image characteristics of each pedestrian video frame are obtained after the processing of ResNet50, and the size of the output pedestrian video frame characteristics is 2048 × 1”);
wherein the video frame feature extraction network is a deep neural network for video frame feature extraction (page 4, “Step two: convolutional neural network extraction of video frame features;” page 4, “ The size of the input image is 256 × 128 × 3, the image characteristics of each pedestrian video frame are obtained after the processing of ResNet50, and the size of the output pedestrian video frame characteristics is 2048 × 1;” the CNN Is read as the deep neural network; page 5, “ A convolutional neural network: one class of feed-forward neural networks, which involves convolution operations, is one of the algorithms that represents deep learning.”).
Regarding independent claim 8, the rejection of claim 1 applies directly. Additionally, Biao further discloses A device for extracting video features (abstract, “The invention relates to a video pedestrian re-identification method based on label correction and weighted feature fusion, and belongs to the field of computer vision and biometric identification;” computer vision is read as including a computing device) comprising:
one or more processors (abstract, “The invention relates to a video pedestrian re-identification method based on label correction and weighted feature fusion, and belongs to the field of computer vision and biometric identification;” computer vision is read as including a computing device which is the processor); and
a memory coupled to the one or more processors, the memory storing programs that, when executed by the one or more processors (page 4, “Step two: convolutional neural network extraction of video frame features. The main network used by the invention is a residual error network ResNet50 commonly used in the field of computer vision at present, the step length used in the last block by an original ResNet50 is 2, and in order to improve the resolution of the extracted image characteristics, the step length of the last block of ResNet50 is set to be 1, so that the loss of information can be reduced;” in order to train and execute a CNN, there must be a memory to store the initial programming of the CNN, and then be able to be called from memory to utilize the network), cause performance of operations comprising:
obtaining a target video sequence that comprises a plurality of video frames (page 4, “The data preprocessing is to preprocess the original video shot by the camera, so that the subsequent steps can be conveniently carried out. ”);
performing video frame feature extraction on the target video sequence to obtain video frame features of each of the plurality of video frames (page 3, “ the method comprises the following steps of extracting pedestrian video fragments;” page 4, “Step two: convolutional neural network extraction of video frame features The main network used by the invention is a residual error network ResNet50 commonly used in the field of computer vision at present, the step length used in the last block by an original ResNet50 is 2, and in order to improve the resolution of the extracted image characteristics, the step length of the last block of ResNet50 is set to be 1, so that the loss of information can be reduced. ”);
performing feature weight calculation on each of the video frame features to obtain the feature weight of each of the video frame features (page 3, “The weight of each frame of image is calculated by utilizing the similarity between each image feature in the same video segment, the video features are obtained in a weighting fusion mode”);
wherein the feature weight of each of the video frame features is determined by the video frame features of all of the video frames in the target video sequence (page 3, “The weight of each frame of image is calculated by utilizing the similarity between each image feature in the same video segment, the video features are obtained in a weighting fusion mode;” page 4, “And calculating the similarity by using the video features obtained in the step three and video features extracted in advance from the candidate pedestrian library, selecting k pedestrian video clips with the maximum similarity as a final matching result;” page 4, “ For all video frames of a video sequence S ═ { I ═ I1,I2,I3,…,InDefine F ═ F1,f2,f3,…,fnAnd E, extracting the corresponding video frame characteristics in the step two. F is theniCorresponding weight αiThe calculation formula is as follows: αi＝λsi1+(1-λ)savg wherein s isi1Is fiAnd f1Similarity of (S)avgIs fiAnd fj(j ≠ i) is an average value of similarity degrees of (1, 2,3, …, n; j ≠ i), and λ is a weight coefficient.”); and
performing feature weighting on each of the video frame features according to the feature weight of each of the video frame features to obtain video features of the target video sequence (page 3, “The weight of each frame of image is calculated by utilizing the similarity between each image feature in the same video segment, the video features are obtained in a weighting fusion mode;” page 4, “The characteristics obtained in step two are each view And image features of the frequency frames are fused in a weighting mode to obtain video features, and the video features are used as final feature representation.”).
Regarding dependent claim 9, the rejection of claim 8 is incorporated herein. Additionally, Biao further discloses wherein performing feature weight calculation on each of the video frame features to obtain the feature weight of each of the video frame features comprises:
calculating a similarity of each of video frame features to obtain a feature similarity matrix (page 3, “The weight of each frame of image is calculated by utilizing the similarity between each image feature in the same video segment, the video features are obtained in a weighting fusion mode;” page 4, “And calculating the similarity by using the video features obtained in the step three and video features extracted in advance from the candidate pedestrian library, selecting k pedestrian video clips with the maximum similarity as a final matching result;” page 4, “ For all video frames of a video sequence S ═ { I ═ I1,I2,I3,…,InDefine F ═ F1,f2,f3,…,fnAnd E, extracting the corresponding video frame characteristics in the step two. F is theniCorresponding weight αiThe calculation formula is as follows: αi＝λsi1+(1-λ)savg wherein s isi1Is fiAnd f1Similarity of (S)avgIs fiAnd fj(j ≠ i) is an average value of similarity degrees of (1, 2,3, …, n; j ≠ i), and λ is a weight coefficient.”); and
performing feature weight calculation on each of the video frame features to obtain the feature weight of each of the video frame features according to the feature similarity matrix (page 5, “Meanwhile, in the weighted feature fusion stage, the feature weight is calculated according to the similarity of the features and other features of the same video sequence, so that the influence of noise on the final video features can be further reduced, and the robustness of pedestrian re-identification of the video is improved.”).
Regarding dependent claim 10, the rejection of claim 9 is incorporated herein. Additionally, Biao further discloses wherein calculating the similarity of each of video frame features to obtain the feature similarity matrix comprises:
performing a convolution operation on each of the video frame features to obtain a feature vector of each of the video frame features (page 4, “Step two: convolutional neural network extraction of video frame features;” page 4, “ The size of the input image is 256 × 128 × 3, the image characteristics of each pedestrian video frame are obtained after the processing of ResNet50, and the size of the output pedestrian video frame characteristics is 2048 × 1.”); and
calculating the similarity of each of video frame features to obtain the feature similarity matrix according to the feature vector of each of the video frame features (page 3, “The weight of each frame of image is calculated by utilizing the similarity between each image feature in the same video segment, the video features are obtained in a weighting fusion mode;” page 4, “And calculating the similarity by using the video features obtained in the step three and video features extracted in advance from the candidate pedestrian library, selecting k pedestrian video clips with the maximum similarity as a final matching result;” page 4, “ For all video frames of a video sequence S ═ { I ═ I1,I2,I3,…,InDefine F ═ F1,f2,f3,…,fnAnd E, extracting the corresponding video frame characteristics in the step two. F is theniCorresponding weight αiThe calculation formula is as follows: αi＝λsi1+(1-λ)savg wherein s isi1Is fiAnd f1Similarity of (S)avgIs fiAnd fj(j ≠ i) is an average value of similarity degrees of (1, 2,3, …, n; j ≠ i), and λ is a weight coefficient.”).
Regarding dependent claim 11, the rejection of claim 10 is incorporated herein. Additionally, Biao further discloses wherein the similarity is calculated according to the following equation:
KI=
PNG
media_image1.png
63
186
media_image1.png
Greyscale
, whereKi,1 represents the feature similarity between a i-th video frame feature F and a j-th video frame feature F, f(Fl) represents the feature vector of the video frame feature Fi, f (F) represents the feature vector of the video frame feature F,||*|| represents a norm of a vector * (page 5, “For two vectors in a given d-dimensional space, p ═ p (p)1,p2…,pd),q＝(q1,q2…,qd) The similarity of p and q is calculated as follows:
PNG
media_image2.png
131
654
media_image2.png
Greyscale
;” page 5, “s (p, q) represents the similarity of p to q; s (q, p) represents the similarity of q to p; the | p | and | q | are the modulo lengths of the vector p and the vector q, respectively.”).
Regarding dependent claim 12, the rejection of claim 11 is incorporated herein. Additionally, Biao further discloses wherein the feature weight is calculated according to the following equation:
si = 1/TKi,t, where si is the feature weight of the i-th video frame feature Fi,
PNG
media_image3.png
32
46
media_image3.png
Greyscale
is a t-th feature similarity in an i-th row in the feature similarity matrix, and T represents an amount of the video frames in the target video sequence (page 2, “Corresponding weight αiThe calculation formula is as follows: αi＝λsi1+(1-λ)savg;” this formula performs a weighting calculation, similar to that as claimed in that the feature wait is being calculated, based upon the similarity values; determining a weight based upon a total frame count is similar to determining an average across the weights).
Regarding dependent claim 14, the rejection of claim 8 is incorporated herein. Additionally, Biao further discloses wherein performing video frame feature extraction on the target video sequence to obtain video frame features of each of the plurality of video frame comprises:
performing video frame feature extraction on each of the video frames in the target video sequence to obtain the video frame features of each video frame using a preset video frame feature extraction network (page 3, “video pedestrian re-identification generally adopts a deep learning-based method, and the basic idea is to extract the features of each frame of image in a video segment;” page 4, “Step two: convolutional neural network extraction of video frame features;” page 4, “ The size of the input image is 256 × 128 × 3, the image characteristics of each pedestrian video frame are obtained after the processing of ResNet50, and the size of the output pedestrian video frame characteristics is 2048 × 1”);
wherein the video frame feature extraction network is a deep neural network for video frame feature extraction (page 4, “Step two: convolutional neural network extraction of video frame features;” page 4, “ The size of the input image is 256 × 128 × 3, the image characteristics of each pedestrian video frame are obtained after the processing of ResNet50, and the size of the output pedestrian video frame characteristics is 2048 × 1;” the CNN Is read as the deep neural network; page 5, “ A convolutional neural network: one class of feed-forward neural networks, which involves convolution operations, is one of the algorithms that represents deep learning.”).
Regarding independent claim 15, the rejection of claim 1 applies directly. Additionally, Biao further discloses A non-transitory computer-readable storage medium storing instructions that, when executed by at least one processor of a device, cause the at least one processor to perform a method (abstract, “The invention relates to a video pedestrian re-identification method based on label correction and weighted feature fusion, and belongs to the field of computer vision and biometric identification;” computer vision is read as including a computing device which is the processor; page 4, “Step two: convolutional neural network extraction of video frame features. The main network used by the invention is a residual error network ResNet50 commonly used in the field of computer vision at present, the step length used in the last block by an original ResNet50 is 2, and in order to improve the resolution of the extracted image characteristics, the step length of the last block of ResNet50 is set to be 1, so that the loss of information can be reduced;” in order to train and execute a CNN, there must be a memory to store the initial programming of the CNN, and then be able to be called from memory to utilize the network), the method comprising:
obtaining a target video sequence that comprises a plurality of video frames (page 4, “The data preprocessing is to preprocess the original video shot by the camera, so that the subsequent steps can be conveniently carried out. ”);
performing video frame feature extraction on the target video sequence to obtain video frame features of each of the plurality of video frames (page 3, “ the method comprises the following steps of extracting pedestrian video fragments;” page 4, “Step two: convolutional neural network extraction of video frame features The main network used by the invention is a residual error network ResNet50 commonly used in the field of computer vision at present, the step length used in the last block by an original ResNet50 is 2, and in order to improve the resolution of the extracted image characteristics, the step length of the last block of ResNet50 is set to be 1, so that the loss of information can be reduced. ”);
performing feature weight calculation on each of the video frame features to obtain the feature weight of each of the video frame features (page 3, “The weight of each frame of image is calculated by utilizing the similarity between each image feature in the same video segment, the video features are obtained in a weighting fusion mode”);
wherein the feature weight of each of the video frame features is determined by the video frame features of all of the video frames in the target video sequence (page 3, “The weight of each frame of image is calculated by utilizing the similarity between each image feature in the same video segment, the video features are obtained in a weighting fusion mode;” page 4, “And calculating the similarity by using the video features obtained in the step three and video features extracted in advance from the candidate pedestrian library, selecting k pedestrian video clips with the maximum similarity as a final matching result;” page 4, “ For all video frames of a video sequence S ═ { I ═ I1,I2,I3,…,InDefine F ═ F1,f2,f3,…,fnAnd E, extracting the corresponding video frame characteristics in the step two. F is theniCorresponding weight αiThe calculation formula is as follows: αi＝λsi1+(1-λ)savg wherein s isi1Is fiAnd f1Similarity of (S)avgIs fiAnd fj(j ≠ i) is an average value of similarity degrees of (1, 2,3, …, n; j ≠ i), and λ is a weight coefficient.”); and
performing feature weighting on each of the video frame features according to the feature weight of each of the video frame features to obtain video features of the target video sequence (page 3, “The weight of each frame of image is calculated by utilizing the similarity between each image feature in the same video segment, the video features are obtained in a weighting fusion mode;” page 4, “The characteristics obtained in step two are each view And image features of the frequency frames are fused in a weighting mode to obtain video features, and the video features are used as final feature representation.”).
Regarding dependent claim 16, the rejection of claim 15 is incorporated herein. Additionally, Biao further discloses wherein performing feature weight calculation on each of the video frame features to obtain the feature weight of each of the video frame features comprises:
calculating a similarity of each of video frame features to obtain a feature similarity matrix (page 3, “The weight of each frame of image is calculated by utilizing the similarity between each image feature in the same video segment, the video features are obtained in a weighting fusion mode;” page 4, “And calculating the similarity by using the video features obtained in the step three and video features extracted in advance from the candidate pedestrian library, selecting k pedestrian video clips with the maximum similarity as a final matching result;” page 4, “ For all video frames of a video sequence S ═ { I ═ I1,I2,I3,…,InDefine F ═ F1,f2,f3,…,fnAnd E, extracting the corresponding video frame characteristics in the step two. F is theniCorresponding weight αiThe calculation formula is as follows: αi＝λsi1+(1-λ)savg wherein s isi1Is fiAnd f1Similarity of (S)avgIs fiAnd fj(j ≠ i) is an average value of similarity degrees of (1, 2,3, …, n; j ≠ i), and λ is a weight coefficient.”); and
performing feature weight calculation on each of the video frame features to obtain the feature weight of each of the video frame features according to the feature similarity matrix (page 5, “Meanwhile, in the weighted feature fusion stage, the feature weight is calculated according to the similarity of the features and other features of the same video sequence, so that the influence of noise on the final video features can be further reduced, and the robustness of pedestrian re-identification of the video is improved.”).
Regarding dependent claim 17, the rejection of claim 16 is incorporated herein. Additionally, Biao further discloses wherein calculating the similarity of each of video frame features to obtain the feature similarity matrix comprises:
performing a convolution operation on each of the video frame features to obtain a feature vector of each of the video frame features (page 4, “Step two: convolutional neural network extraction of video frame features;” page 4, “ The size of the input image is 256 × 128 × 3, the image characteristics of each pedestrian video frame are obtained after the processing of ResNet50, and the size of the output pedestrian video frame characteristics is 2048 × 1.”); and
calculating the similarity of each of video frame features to obtain the feature similarity matrix according to the feature vector of each of the video frame features (page 3, “The weight of each frame of image is calculated by utilizing the similarity between each image feature in the same video segment, the video features are obtained in a weighting fusion mode;” page 4, “And calculating the similarity by using the video features obtained in the step three and video features extracted in advance from the candidate pedestrian library, selecting k pedestrian video clips with the maximum similarity as a final matching result;” page 4, “ For all video frames of a video sequence S ═ { I ═ I1,I2,I3,…,InDefine F ═ F1,f2,f3,…,fnAnd E, extracting the corresponding video frame characteristics in the step two. F is theniCorresponding weight αiThe calculation formula is as follows: αi＝λsi1+(1-λ)savg wherein s isi1Is fiAnd f1Similarity of (S)avgIs fiAnd fj(j ≠ i) is an average value of similarity degrees of (1, 2,3, …, n; j ≠ i), and λ is a weight coefficient.”).
Regarding dependent claim 18, the rejection of claim 17 is incorporated herein. Additionally, Biao further discloses wherein the similarity is calculated according to the following equation:
KI=
PNG
media_image1.png
63
186
media_image1.png
Greyscale
, whereKi,1 represents the feature similarity between a i-th video frame feature F and a j-th video frame feature F, f(Fl) represents the feature vector of the video frame feature Fi, f (F) represents the feature vector of the video frame feature F,||*|| represents a norm of a vector * (page 5, “For two vectors in a given d-dimensional space, p ═ p (p)1,p2…,pd),q＝(q1,q2…,qd) The similarity of p and q is calculated as follows:
PNG
media_image2.png
131
654
media_image2.png
Greyscale
;” page 5, “s (p, q) represents the similarity of p to q; s (q, p) represents the similarity of q to p; the | p | and | q | are the modulo lengths of the vector p and the vector q, respectively.”).
Regarding dependent claim 19, the rejection of claim 18 is incorporated herein. Additionally, Biao further discloses wherein the feature weight is calculated according to the following equation:
si = 1/TKi,t, where si is the feature weight of the i-th video frame feature Fi,
PNG
media_image3.png
32
46
media_image3.png
Greyscale
is a t-th feature similarity in an i-th row in the feature similarity matrix, and T represents an amount of the video frames in the target video sequence (page 2, “Corresponding weight αiThe calculation formula is as follows: αi＝λsi1+(1-λ)savg;” this formula performs a weighting calculation, similar to that as claimed in that the feature wait is being calculated, based upon the similarity values; determining a weight based upon a total frame count is similar to determining an average across the weights).
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 6, 13 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Biao as applied to claims 5, 12 and 19 respectively above, and further in view of Official Notice.
Regarding dependent claim 6, the rejection of claim 5 is incorporated herein. Additionally, Biao fails to explicitly disclose wherein the feature weighting is performed according to the following equation:
PNG
media_image4.png
75
210
media_image4.png
Greyscale
where F represents the video features of the target video sequence, Fi represents the i-th video frame feature, and st is the feature weight of the video frame feature Fi.
However, as noted above, Biao discloses the determination of the weights as related to the features themselves in the abstract, “the feature weight is calculated by using the similarity between the feature and other features of the same video sequence, and the video features after weighted fusion can be reduced. ” Claim 6 is read as determining the feature weighting on a feature level, as opposed to the frame level. Further, mathematically, if a weight has been determined for an entity, and one wants to determine the overall contribution of that feature in itself, it follows that one would multiply the entity by the value. For example, said differently, to understand the contribution of a feature based on a weight, multiplication would confirm that value; further determining the value of the feature in that frame one would need to determine the count of frames, and divide the contribution by the total frames. The examiner takes official notice that it would have been obvious to a person having ordinary skill in the art before the effective filing date to modify the function of Biao in order to ensure an accurate count for the feature weighting on a single frame level is determined.
Regarding dependent claim 13, the rejection of claim 12 is incorporated herein. Additionally, Biao fails to explicitly disclose wherein the feature weighting is performed according to the following equation:
PNG
media_image4.png
75
210
media_image4.png
Greyscale
where F represents the video features of the target video sequence, Fi represents the i-th video frame feature, and st is the feature weight of the video frame feature Fi.
However, as noted above, Biao discloses the determination of the weights as related to the features themselves in the abstract, “the feature weight is calculated by using the similarity between the feature and other features of the same video sequence, and the video features after weighted fusion can be reduced. ” Claim 6 is read as determining the feature weighting on a feature level, as opposed to the frame level. Further, mathematically, if a weight has been determined for an entity, and one wants to determine the overall contribution of that feature in itself, it follows that one would multiply the entity by the value. For example, said differently, to understand the contribution of a feature based on a weight, multiplication would confirm that value; further determining the value of the feature in that frame one would need to determine the count of frames, and divide the contribution by the total frames. The examiner takes official notice that it would have been obvious to a person having ordinary skill in the art before the effective filing date to modify the function of Biao in order to ensure an accurate count for the feature weighting on a single frame level is determined.
Regarding dependent claim 20, the rejection of claim 19 is incorporated herein. Additionally, Biao fails to explicitly disclose wherein the feature weighting is performed according to the following equation:
PNG
media_image4.png
75
210
media_image4.png
Greyscale
where F represents the video features of the target video sequence, Fi represents the i-th video frame feature, and st is the feature weight of the video frame feature Fi.
However, as noted above, Biao discloses the determination of the weights as related to the features themselves in the abstract, “the feature weight is calculated by using the similarity between the feature and other features of the same video sequence, and the video features after weighted fusion can be reduced. ” Claim 6 is read as determining the feature weighting on a feature level, as opposed to the frame level. Further, mathematically, if a weight has been determined for an entity, and one wants to determine the overall contribution of that feature in itself, it follows that one would multiply the entity by the value. For example, said differently, to understand the contribution of a feature based on a weight, multiplication would confirm that value; further determining the value of the feature in that frame one would need to determine the count of frames, and divide the contribution by the total frames. The examiner takes official notice that it would have been obvious to a person having ordinary skill in the art before the effective filing date to modify the function of Biao in order to ensure an accurate count for the feature weighting on a single frame level is determined.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
U.S. Patent No. 11,967,151 to Li et al. discloses, “Embodiments of this application disclose a video classification method performed by a computer device and belong to the field of computer vision (CV) technologies (abstract).”
U.S. Patent No. 10,956,748 to Tang et al. discloses, “A video classification method is provided for a computer device (abstract).”
Contact
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Courtney J. Nelson whose telephone number is (571)272-3956. The examiner can normally be reached Monday - Friday 8:00 - 4:00.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, John Villecco can be reached at 571-272-7319. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/COURTNEY JOAN NELSON/Primary Examiner, Art Unit 2661