Method and apparatus for processing video stream
AssigneeAlibaba Group Holding Limited
InventorsXin Guo, Yuan Cheng, Chen Jiang
Life of this patent
Estimating the term…
Abstract
A video stream captured for an object is obtained. Features of S image frames in the video stream are extracted, and S N-dimensional feature vectors are generated. The S N-dimensional feature vectors are arranged in a chronological order corresponding to the order in which the image frames occur in the video stream to generate a feature matrix, wherein the feature matrix has N rows and at least S columns. The feature matrix is processed by using a pre-trained convolutional neural network, to obtain a processing result for the object captured in the video stream.
Claims20
A computer-implemented method for processing a video stream, comprising:
- obtaining a video stream captured for an object;
- extracting features of S image frames in the video stream, and generating S N-dimensional feature vectors;
- arranging the S N-dimensional feature vectors in a chronological order corresponding to the order in which the image frames occur in the video stream to generate a feature matrix, wherein the feature matrix has N rows and at least S columns;
- and
- processing the feature matrix by using a pre-trained convolutional neural network, to obtain a processing result for the object captured in the video stream.
A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:
- obtaining a video stream captured for an object;
- extracting features of S image frames in the video stream, and generating S N-dimensional feature vectors;
- arranging the S N-dimensional feature vectors in a chronological order corresponding to the order in which the image frames occur in the video stream to generate a feature matrix, wherein the feature matrix has N rows and at least S columns;
- and
- processing the feature matrix by using a pre-trained convolutional neural network, to obtain a processing result for the object captured in the video stream.
A computer-implemented system, comprising:
- one or more computers;
- and
- one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform one or more operations comprising:
- obtaining a video stream captured for an object;
- extracting features of S image frames in the video stream, and generating S N-dimensional feature vectors;
- arranging the S N-dimensional feature vectors in a chronological order corresponding to the order in which the image frames occur in the video stream to generate a feature matrix, wherein the feature matrix has N rows and at least S columns;
- and
- processing the feature matrix by using a pre-trained convolutional neural network, to obtain a processing result for the object captured in the video stream.
Dependencies are inferred from the claim text.