Abstract: An advertising system is disclosed. In one embodiment, the system includes an advertising station including a display and configured to provide advertising content to potential customers via the display and one or more cameras configured to capture images of the potential customers when proximate to the advertising station. The system may also include a data processing system to analyze the captured images to determine gaze directions and body pose directions for the potential customers, and to determine interest levels of the potential customers in the advertising content based on the determined gaze directions and body pose directions. Various other systems, methods, and articles of manufacture are also disclosed.

Abstract: According to some implementations of the present disclosure, computer-implemented methods and systems for generating media clips are disclosed. According to some implementations, the method includes receiving an original media stream, transcoding the original media stream into a transcoded media stream, and streaming the transcoded media stream to a user device. The method further includes creating a plurality of media segments that include content of the original media stream and receiving a request to create a media clip from the original media stream from a user device. The request indicates a clip start time and a clip end time defined with respect to the transcoded media stream. The method further includes identifying, from the plurality of media segments, one or more identified media segments corresponding to the clip start time and the clip end time and creating the media clip based on content included in the identified media segments.

Abstract: Systems and methods for generating a master video stream from at least two live video streams are provided in this disclosure. The systems include a combination component that combines the live video streams to generate the master video stream. In one aspect, the live video streams can be copies of the same recording that are multicast from different locations according to User Datagram Protocol. The live video streams suffer different errors, such as stream corruption or stream error, due to the transmission. The combination component eliminates the errors in the live video streams due to transmission and creates a substantially error-free master video stream.

Abstract: According to some implementations of the present disclosure, computer-implemented methods and systems for generating media clips are disclosed. According to some implementations, the method includes receiving an original media stream, transcoding the original media stream into a transcoded media stream, and streaming the transcoded media stream to a user device. The method further includes creating a plurality of media segments that include content of the original media stream and receiving a request to create a media clip from the original media stream from a user device. The request indicates a clip start time and a clip end time defined with respect to the transcoded media stream. The method further includes identifying, from the plurality of media segments, one or more identified media segments corresponding to the clip start time and the clip end time and creating the media clip based on content included in the identified media segments.

Abstract: A media sharing system receives a media stream from a broadcaster system. The media sharing system streams a transcoded version of the media stream to user devices that request the media stream broadcast. Additionally, as the media stream is received from the broadcaster system, the media sharing system generates media segments that include the content of the media stream. Based on programming information received for the media stream, the media sharing system creates a media clip for each program included in the media stream. The media sharing system uses content from the media segments to generate the media clips. Further, as a user is viewing a media stream broadcast to the user's device by the media sharing system, the user may request the creation of a media clip from the media stream. The system identifies media segments that include content of the desired media clip and creates the media clip.

Abstract: Systems and methods for generating a master video stream from at least two live video streams are provided in this disclosure. The systems include a combination component that combines the live video streams to generate the master video stream. In one aspect, the live video streams can be copies of the same recording that are multicast from different locations according to User Datagram Protocol. The live video streams suffer different errors, such as stream corruption or stream error, due to the transmission. The combination component eliminates the errors in the live video streams due to transmission and creates a substantially error-free master video stream.

Abstract: A system and method for processing multicast streams is disclosed. A router receives the multicast streams and communicates the streams via communication tunnels to a set of ingestion pipelines. Each communication tunnel can be terminated upon the ingestion pipeline receiving a multicast stream. The set of ingestion pipelines process and deliver the multicast streams across existing IP infrastructure for real time distribution.

Abstract: A video storyboard delivery system is disclosed. The system receives, from a playback client executed on a user device, a request for a video including one or more user device parameters. The system obtains a storyboard manifest including information defining a storyboard associated with the video, wherein the information includes a plurality of storyboard resolution levels. Using the one or more user device parameters, a selection is made of one of the plurality of storyboard resolution levels from the storyboard manifest. The storyboard at the selected resolution level is delivered to the playback client.

Abstract: Systems and methods for generating a master video stream from at least two live video streams are provided in this disclosure. The systems include a combination component that combines the live video streams to generate the master video stream. In one aspect, the live video streams can be copies of the same recording that are multicast from different locations according to User Datagram Protocol. The live video streams suffer different errors, such as stream corruption or stream error, due to the transmission. The combination component eliminates the errors in the live video streams due to transmission and creates a substantially error-free master video stream.

Abstract: An advertising system is disclosed. In one embodiment, the system includes an advertising station including a display and configured to provide advertising content to potential customers via the display and one or more cameras configured to capture images of the potential customers when proximate to the advertising station. The system may also include a data processing system to analyze the captured images to determine gaze directions and body pose directions for the potential customers, and to determine interest levels of the potential customers in the advertising content based on the determined gaze directions and body pose directions. Various other systems, methods, and articles of manufacture are also disclosed.

Abstract: Aspects of the disclosure provide a method for crowd segmentation that can globally optimize crowd segmentation of an input image based on local information of the input image. The method can include receiving an input image of a site, initializing a plurality of hypothesis based on the input image, dividing the input image into a plurality of patches, calculating an affinity measure of one or more patches to a hypothesis based on a partial response of the patches to a whole body classifier of the hypothesis that includes a combination of weak classifiers, and optimizing assignments of the plurality of patches to the plurality of hypothesis based on the affinity measures of the plurality of patches to the plurality of hypothesis.

Abstract: A system, method and program product for camera-based discovery of social networks. The computer implemented method for identifying individuals and associating tracks with individuals in camera-generated images from a face capture camera(s) and a tracking camera(s), wherein the computer implemented method includes: receiving images of an individual from the face capture camera(s) on a computer; receiving images of a track(s) of an individual from the tracking camera(s) on a computer; automatically determining with the computer the track(s) from the images from the tracking camera(s); and associating with the computer the track(s) with the individual(s) and a unique identifier. The present invention has been described in terms of specific embodiment(s), and it is recognized that equivalents, alternatives, and modifications, aside from those expressly stated, are possible and within the scope of the appending claims.

Abstract: A method and system for distributed tracking of multiple targets is disclosed. Multiple targets to be tracked by a plurality of trackers are detected in a frame. The motion state variable of each of the plurality of trackers is calculated in the E-step of a variational Expectation-Maximization algorithm. Further, the data association variable of each of the plurality of trackers is calculated in the M-step of the algorithm. Depending on the motion state variable and the data association variable, the multiple targets are tracked.

Abstract: An imaging detection system includes at least one location detection device configured to determine coordinates of a target, at least one detector configured to detect events from a source associated with the target, and a processor coupled in communication with the at least one location detection device and the at least one detector. The processor is configured to receive the coordinates from the at least one location detection device and the events from the at least one detector, translate the events using the coordinates acquired from the at least one location detection device to compensate for a relative motion between the source and the at least one detector, and output a processed data set having the events translated based on the coordinates.

Abstract: A system and method for monitoring an entity within an area is disclosed. The method includes specifying at least one criterion associated with an event of interest. The at least one criterion is specified visually on a display screen. At least one entity to be monitored is identified, and a movement of the at least one entity is captured visually on the display screen. The captured movement of the entity comprises at least one attribute associated with the at least one entity.

Abstract: Embodiments of the invention include a system and a method for determining whether a person is carrying concealed contraband, such as an improvised explosives device or other weapon. The system includes a people tracking video subsystem, a people tracking decisioning subsystem, a concealed contraband detection aiming subsystem, and a concealed contraband detection decisioning subsystem.

Abstract: A system, method and program product for camera-based discovery of social networks. The computer implemented method for identifying individuals and associating tracks with individuals in camera-generated images from a face capture camera(s) and a tracking camera(s), wherein the computer implemented method includes: receiving images of an individual from the face capture camera(s) on a computer; receiving images of a track(s) of an individual from the tracking camera(s) on a computer; automatically determining with the computer the track(s) from the images from the tracking camera(s); and associating with the computer the track(s) with the individual(s) and a unique identifier. The present invention has been described in terms of specific embodiment(s), and it is recognized that equivalents, alternatives, and modifications, aside from those expressly stated, are possible and within the scope of the appending claims.

Abstract: A method for re-identifying an image is provided. The method comprises obtaining a plurality of images and generating a correspondence map between the plurality of images. The method further comprises defining a plurality of region signatures for one or more regions comprising the plurality of images and comparing the plurality of images based on the correspondence map and the plurality of region signatures to perform image re-identification.

Abstract: Aspects of the disclosure provide a method for crowd segmentation that can globally optimize crowd segmentation of an input image based on local information of the input image. The method can include receiving an input image of a site, initializing a plurality of hypothesis based on the input image, dividing the input image into a plurality of patches, calculating an affinity measure of one or more patches to a hypothesis based on a partial response of the patches to a whole body classifier of the hypothesis that includes a combination of weak classifiers, and optimizing assignments of the plurality of patches to the plurality of hypothesis based on the affinity measures of the plurality of patches to the plurality of hypothesis.

Abstract: A gaze estimation method and system, the method including capturing a video sequence of images with an image capturing system, designating at least one landmark in a head portion of the captured video sequence, fitting a virtual model of the head portion to the actual head portion in the captured video sequence, and determining the gaze estimation.