Abstract: A method, apparatus and computer-readable storage medium are provided to define a storyline based on path probabilities for a plurality of paths through the frames of a video. Relative to a method and for a plurality of frames of a video, regions of a first frame and regions of a second, subsequent frame that have been viewed are identified. For each of at least one first-frame region of one or more regions of the first frame, the method determines a transition probability of transitioning from a respective first-frame region of the first frame to each of at least one second-frame region of a plurality of regions of the second frame. Based on the transition probabilities, the method determines a path probability for each of at least one of a plurality of paths through the frames of the video. The method additionally defines a storyline based on the path probabilities.

Abstract: A method, apparatus and computer-readable storage medium provide information regarding changes in viewing behavior between first and second frame of a video. In a method, a plurality of objects that are included within a respective frame are identified. The method determines a first number of views of each of at least one of the plurality of objects in the first frame. For the second frame subsequent to the first frame, the method determines a second number of views of each of at least one of the plurality of objects that are in the second frame and identifies a number of instances in which a respective viewer who viewed one object within the first frame changed to view a different object within the second frame. The method additionally causes information to be provided regarding changes in viewing behavior between the first and second frame of the video.

Abstract: A method, apparatus and computer-readable storage medium are provided to define a storyline based on path probabilities for a plurality of paths through the frames of a video. Relative to a method and for a plurality of frames of a video, regions of a first frame and regions of a second, subsequent frame that have been viewed are identified. tified. For each of at least one first-frame region of one or more regions of the first frame, the method determines a transition probability of transitioning from a respective first-frame frame region of the first frame to each of at least one second-frame region of a plurality of regions of the second frame. Based on the transition probabilities, the method determines a path probability for each of at least one of a plurality of paths through the frames of the video. The method additionally defines a storyline based on the path probabilities.

Abstract: A method, apparatus and computer-readable storage medium provide information regarding changes in viewing behavior between first and second frame of a video. In a method, a plurality of objects that are included within a respective frame are identified. The method determines a first number of views of each of at least one of the plurality of objects in the first frame. For the second frame subsequent to the first frame, the method determines a second number of views of each of at least one of the plurality of objects that are in the second frame and identifies a number of instances in which a respective viewer who viewed one object within the first frame changed to view a different object within the second frame. The method additionally causes information to be provided regarding changes in viewing behavior between the first and second frame of the video.

Abstract: Techniques for facilitating a video surveillance search of a person are provided. The techniques include maintaining a database of one or more attributes of one or more people captured on one or more video cameras, indexing the one or more attributes in the database extracted from the one or more video cameras, and pruning one or more images captured from the one or more video cameras using the one or more attributes and one or more items of qualifying information to facilitate a video surveillance search of a person.

Abstract: A method, apparatus and computer program product are provided to facilitate the review of at least portions of a panoramic image and to increase the likelihood that a viewer consumes at least those portions of the panoramic image that are considered to be both interesting and of aesthetic value. In the context of a method, one or more regions within a panoramic image are identified based upon a saliency of the one or more regions. The method also includes identifying candidate subimages that at least partially overlap with at least one of the regions identified within the panoramic image. The method further includes scoring the candidate subimages based upon predefined criteria and causing information for one or more of the candidate subimages to be provided based upon scores associated therewith.

Abstract: A method, apparatus and computer program product are provided to facilitate the review of at least portions of a panoramic image and to increase the likelihood that a viewer consumes at least those portions of the panoramic image that are considered to be both interesting and of aesthetic value. In the context of a method, one or more regions within a panoramic image are identified based upon a saliency of the one or more regions. The method also includes identifying candidate subimages that at least partially overlap with at least one of the regions identified within the panoramic image. The method further includes scoring the candidate subimages based upon predefined criteria and causing information for one or more of the candidate subimages to be provided based upon scores associated therewith.

Abstract: A method, apparatus and computer program product are provided to cause image content to be adjusted in a manner consistent with the corresponding viewing direction, such as the viewing direction of a user of a head-mounted display device. In regards to a method, one or more first anchor frames are determined within a multi-frame image, a user's viewing direction is determined relative to the multi-frame image and at least one second anchor frame is identified based on the user's viewing direction. The method also includes determining one or more tonal modification parameters of a frame in relation to the viewing direction based upon the one or more first anchor frames and the at least one second anchor frame. Further, the method generates a plurality of modified frames based on the one or more tonal modification parameters. A corresponding apparatus and computer program product are also provided.

Abstract: A method, apparatus and computer program product are provided to cause image content to be adjusted in a manner consistent with the corresponding viewing direction, such as the viewing direction of a user of a head-mounted display device. In regards to a method, one or more first anchor frames are determined within a multi-frame image, a user's viewing direction is determined relative to the multi-frame image and at least one second anchor frame is identified based on the user's viewing direction. The method also includes determining one or more tonal modification parameters of a frame in relation to the viewing direction based upon the one or more first anchor frames and the at least one second anchor frame. Further, the method generates a plurality of modified frames based on the one or more tonal modification parameters. A corresponding apparatus and computer program product are also provided.

Abstract: In a method, a first image of a subject is taken from a first viewpoint. The first image of the subject is composed of a first plurality of pixels. A second image of the subject is taken from a second viewpoint. The second image of the subject is composed of a second plurality of pixels. Pixels in the first plurality of pixels in the first image correspond to pixels in the second plurality of pixels in the second image. Corresponding pixels lie on first epipolar lines in the first image and on second epipolar lines in the second image. The first and second images are rectified to make the first and second epipolar lines parallel to one another and to place corresponding pixels in the first and second images on one of a plurality of pairs of common scanlines. For at least one pair of common scanlines, a corresponding pixel is found in the second image for each pixel in the first image such that a visual perception matching cost (VPMC) is minimized.

Abstract: A first image frame is gathered. The first image frame, a first white balance value, and a first exposure value are stored. Information is sensed from an inertial sensor. A second image frame and intermediate image frames are gathered. A distance traversed by a camera is determined. In response to one or more of: the distance exceeding a predetermined threshold, or a new white balance value significantly differing from a previous white balance value, or a new exposure value significantly differing from a previous exposure value, a second white balance value and a second exposure value are determined for the second image frame. A smoothed white balance value and a smoothed exposure value are determined for the intermediate image frames.

Abstract: In response to a query of discernable facial attributes, the locations of distinct and different facial regions are estimated from face image data, each relevant to different attributes. Different features are extracted from the estimated facial regions from database facial images, which are ranked in base layer rankings as a function of relevance of extracted features to attributes relevant to the estimated regions, and in second-layer rankings as a function of combinations of the base layer rankings and relevance of the extracted features to common ones of the attributes relevant to the estimated regions. The images are ranked in relevance to the query as a function of the second-layer rankings.

Abstract: In response to a query of discernable facial attributes, the locations of distinct and different facial regions are estimated from face image data, each relevant to different attributes. Different features are extracted from the estimated facial regions from database facial images, which are ranked in base layer rankings as a function of relevance of extracted features to attributes relevant to the estimated regions, and in second-layer rankings as a function of combinations of the base layer rankings and relevance of the extracted features to common ones of the attributes relevant to the estimated regions. The images are ranked in relevance to the query as a function of the second-layer rankings.

Abstract: Techniques for tracking an individual across two or more cameras are provided. The techniques include detecting an image of one or more individuals in each of two or more cameras, tracking each of the one or more individuals in a field of view in each of the two or more cameras, applying a set of one or more attribute detectors to each of the one or more individuals being tracked by the two or more cameras, and using the set of one or more attribute detectors to match an individual tracked in one of the two or more cameras with an individual tracked in one or more other cameras of the two or more cameras.

Abstract: In response to a query of discernable facial attributes, the locations of distinct and different facial regions are estimated from face image data, each relevant to different attributes. Different features are extracted from the estimated facial regions from database facial images, which are ranked in base layer rankings as a function of relevance of extracted features to attributes relevant to the estimated regions, and in second-layer rankings as a function of combinations of the base layer rankings and relevance of the extracted features to common ones of the attributes relevant to the estimated regions. The images are ranked in relevance to the query as a function of the second-layer rankings.

Abstract: A first image frame is gathered. The first image frame, a first white balance value, and a first exposure value are stored. Information is sensed from an inertial sensor. A second image frame and intermediate image frames are gathered. A distance traversed by a camera is determined. In response to one or more of: the distance exceeding a predetermined threshold, or a new white balance value significantly differing from a previous white balance value, or a new exposure value significantly differing from a previous exposure value, a second white balance value and a second exposure value are determined for the second image frame. A smoothed white balance value and a smoothed exposure value are determined for the intermediate image frames.

Abstract: In a method, a first image of a subject is taken from a first viewpoint. The first image of the subject is composed of a first plurality of pixels. A second image of the subject is taken from a second viewpoint. The second image of the subject is composed of a second plurality of pixels. Pixels in the first plurality of pixels in the first image correspond to pixels in the second plurality of pixels in the second image. Corresponding pixels lie on first epipolar lines in the first image and on second epipolar lines in the second image. The first and second images are rectified to make the first and second epipolar lines parallel to one another and to place corresponding pixels in the first and second images on one of a plurality of pairs of common scanlines. For at least one pair of common scanlines, a corresponding pixel is found in the second image for each pixel in the first image such that a visual perception matching cost (VPMC) is minimized.

Abstract: Systems and apparatus for white balance correction. A reference object appearing in a captured scene image is identified and a color transform is computed, based on known color balance information for the reference object. The color transform is based on a difference between color information for the reference object taken under known illumination and the apparent color balance of the reference object as it appears in the captured image. The color transform is applied to the captured image and a corrected image is created, based on applying the color transform to every pixel in the captured image.

Abstract: In response to a query of discernable facial attributes, the locations of distinct and different facial regions are estimated from face image data, each relevant to different attributes. Different features are extracted from the estimated facial regions from database facial images, which are ranked in base layer rankings as a function of relevance of extracted features to attributes relevant to the estimated regions, and in second-layer rankings as a function of combinations of the base layer rankings and relevance of the extracted features to common ones of the attributes relevant to the estimated regions. The images are ranked in relevance to the query as a function of the second-layer rankings.

Abstract: In response to a query of discernable facial attributes, the locations of distinct and different facial regions are estimated from face image data, each relevant to different attributes. Different features are extracted from the estimated facial regions from database facial images, which are ranked in base layer rankings by matching feature vectors to a base layer ranking sequence as a function of edge weights. Second-layer rankings define second-layer attribute vectors as combinations of the base-layer feature vectors and associated base layer parameter vectors for common attributes, which are matched to a second-layer ranking sequence as a function of edge weights. The images are thus ranked for relevance to the query as a function of the second-layer rankings.