Abstract: A method and system for codec of visual feature data is provided. First protocol format visual feature data generated by an intelligent front end and a certificate identity used to uniquely identify a corresponding first protocol format are received. The first protocol format visual feature data is converted to a same type of second protocol format visual feature data according to the certificate identity. The second protocol format visual feature data is received and parsed according to the second protocol format to obtain original visual feature data that are generated by the intelligent front end and contained in the first protocol format visual feature data.

Abstract: Disclosed are a compression method and system for the frequent transmission of a deep neural network. The deep neural network compression is extended to the field of transmission, and the potential redundancy among deep neural network models is utilized for compressing, so that the overhead of the deep neural network under frequency transmission is reduced. The advantages of the present invention are that: in the present invention, the redundancy among multiple models of the deep neural network on the frequency transmission is combined, knowledge information among deep neural networks is utilized for compressing, and the size and the bandwidth of the required transmission are reduced. The deep neural network can be better transmitted under the same bandwidth limitation; meanwhile, the deep neural network is allowed to be performed targeted compression at a front end, rather than being restored partially after being performed targeted compression.

Abstract: A method and system for codec of visual feature data is provided. First protocol format visual feature data generated by an intelligent front end and a certificate identity used to uniquely identify a corresponding first protocol format are received. The first protocol format visual feature data is converted to a same type of second protocol format visual feature data according to the certificate identity. The second protocol format visual feature data is received and parsed according to the second protocol format to obtain original visual feature data that are generated by the intelligent front end and contained in the first protocol format visual feature data.

Abstract: The present invention provides a method and a device for detecting interest points in an image. The method includes: acquiring an original input image; performing down-sampling processing on the original input image, so as to obtain a plurality of sampling images with different resolutions; dividing each sampling image into a plurality of small image blocks; performing filtering processing on the plurality of small image blocks in each sampling image in sequence by using Laplacian-of-Gaussian filters, so as to obtain filtered images of the plurality of small image blocks in each sampling image; and acquiring interest points in an image in filtered images of the plurality of small image blocks in each sampling image. The present invention is used for solving the problems of more memory consumption and a low detection speed in the prior art.

Abstract: A method for compressing a local feature descriptor includes that: at least one local feature descriptor of a target image is selected; and multi-stage vector quantization is carried out on the selected at least one local feature descriptor according to a pre-set code book, and the local feature descriptor is quantized as a feature code stream, wherein the feature code stream includes serial numbers of code words obtained by means of the multi-stage vector quantization. A device for compressing a local feature descriptor and a storage medium are also provided.

Abstract: The present invention provides a method and a device for detecting interest points in an image. The method includes: acquiring an original input image; performing down-sampling processing on the original input image, so as to obtain a plurality of sampling images with different resolutions; dividing each sampling image into a plurality of small image blocks; performing filtering processing on the plurality of small image blocks in each sampling image in sequence by using Laplacian-of-Gaussian filters, so as to obtain filtered images of the plurality of small image blocks in each sampling image; and acquiring interest points in an image in filtered images of the plurality of small image blocks in each sampling image. The present invention is used for solving the problems of more memory consumption and a low detection speed in the prior art.

Abstract: A method of annotating footage that includes a structured text broadcast stream, a video stream and an audio stream, the method includes the steps of: extracting directly or indirectly one or more keywords and/or features from at least said structured text broadcast streams, temporally annotating said footage with said keywords and/or features analysing temporally adjacent annotated keywords and/or features to determine information about one or more events within said footage. Also provided are: a data store for storing video footage, a method of generation of a personalised video summary, a system for annotating footage and a system for generation of a personalised video summary.

Abstract: A method and system for generating replays of an event for broadcast video. The method comprises the steps of receiving a video feed, automatically detecting said event from said camera video feed, generating a replay video of said event, and generating broadcast video incorporating said replay. Optionally, the replay video is automatically generated. Optionally, the replay is automatically incorporated into said broadcast video.