Gopro, Inc.

Brian G Schunck

David A Newman

Scott Patrick Campbell

Desmond Chik

Daniel Tse

Jonathan Wills

Systems and method of generating video summaries are presented herein. Information defining a video may be obtained. The video may include a set of frame images. Parameter values for parameters of individual frame images of the video may be determined. Interest weights for the frame images may be determined. An interest curve for the video that characterizes the video by interest weights as a function of progress through the set of frame images may be generated. One or more curve attributes of the interest curve may be identified and one or more interest curve values of the interest curve that correspond to individual curve attributes may be determined. Interest curve values of the interest curve may be compared to threshold curve values. A subset of frame images of the video to include within a video summary of the video may be identified based on the comparison.

Systems and methods for generating a video summary

Systems and methods are disclosed that capture and compress frames of pixel data. In an implementation, an image sensor chip is configured to convert light into pixel data and generate compressed pixel data at a variable compression rate including applying a transform to pixel data associated with a pixel category from a plurality of pixel categories. The variable compression rate is within an available bandwidth of an output bus configured to output the compressed pixel data.

On-chip image sensor data compression

A system and method disposed to enable encoding, decoding and manipulation of digital video with substantially less processing load than would otherwise required. In particular, one disclosed method is directed to generating a compressed video data structure that is selectively decodable to a plurality of resolutions including the full resolution of the uncompressed stream. The desired number of data components and the content of the data components that make up the compressed video data, which determine the available video resolutions, are variable based upon the processing carried out and the resources available to decode and process the data components. During decoding, efficiency is substantially improved because only the data components necessary to generate a desired resolution are decoded. In variations, both temporal and spatial decoding are utilized to reduce frame rates, and hence, further reduce processor load. The system and method are particularly useful for real-time video editing applications.

Encoding and decoding selectively retrievable representations of video content

Systems and methods are disclosed that capture and compress frames of pixel data. In an implementation, an image sensor chip converts light into pixel data and generates transform data by applying a transform to a portion of the pixel data associated with a pixel category from a plurality of pixel categories and generates compressed pixel data at a variable compression rate by compressing the transform data. The variable compression rate is within an available bandwidth of an output bus that outputs the compressed pixel data.

A system and method disposed to enable encoding, decoding and manipulation of digital video with substantially less processing load than would otherwise be required. In particular, one disclosed method is directed to generating a compressed video data structure that is selectively decodable to a plurality of resolutions including the full resolution of the uncompressed stream. The desired number of data components and the content of the data components that make up the compressed video data, which determine the available video resolutions, are variable based upon the processing carried out and the resources available to decode and process the data components. During decoding, efficiency is substantially improved because only the data components necessary to generate a desired resolution are decoded. In variations, both temporal and spatial decoding are utilized to reduce frame rates, and hence, further reduce processor load. The system and method are particularly useful for real-time video editing applications.

Video and corresponding metadata is accessed. Events of interest within the video are identified based on the corresponding metadata, and best scenes are identified based on the identified events of interest. A video summary can be generated including one or more of the identified best scenes. The video summary can be generated using a video summary template with slots corresponding to video clips selected from among sets of candidate video clips. Best scenes can also be identified by receiving an indication of an event of interest within video from a user during the capture of the video. Metadata patterns representing activities identified within video clips can be identified within other videos, which can subsequently be associated with the identified activities.

Generating video summaries for a video using video summary templates

An image sensor compresses image data prior to transmitting the image data to a DSP. The image sensor captures light representing an image, for instance via a camera's aperture. A focal plane array converts the captured light into pixel data. The pixel data is sorted into categories, and is compressed in parallel by a compression engine. The compressed pixel data is then sent to a DSP, which may be located off-chip. The DSP then decompresses the compressed pixel data, performs image signal processing operations on the compressed pixel data, and then compresses the processed pixel data into a digital image format. The image sensor may buffer the pixel data for one or more images to accommodate for slowdown by the compression engine. The pixel data may be sorted by row and column of a pixel array. Alternatively, the pixel data may be sorted by color from a Bayer color filter.

Growing community of inventors

San Diego, CA, United States of America

Brian G Schunck