Canon Kabushiki Kaisha

Amit Kumar Gupta

Ashley John Partis

David Kenji See

Quang Tuan Pham

Peter Jan Pakulski

Hiroshi Tojo

Getian Ye

Jeroen Vendrig

Xin Yu Liu

Jie Xu

Nagita Mehr Seresht

Qianlu Lin

A method of capturing an image of a scene. A current location of a plurality of objects in a frame of a video capturing the scene having one or more events of interest, is determined. For at least one of the events of interest, a time and a location for each of the plurality of objects associated with the event of interest is predicted based on the current location of the plurality of objects. A frame subset score is determined for each of a plurality of frame subsets in the frame, each of the plurality of frame subsets including one or more of the plurality of objects based on the predicted time and the predicted location for the event of interest. One of the determined plurality of frame subsets is selected based on the determined frame subset score. An image of the event of interest is captured using a camera, based on a camera orientation setting for the selected frame subset, where the captured image comprises the selected frame subset.

Method, system and apparatus for capturing an image

A system and method of generating a composite frame from a video capturing a plurality of persons. The method comprises determining a plurality of frames corresponding to occurrence of a predetermined event in the video; determining an importance score for each of the plurality of persons in the determined plurality of frames, the importance score determined based on a type of interaction detected between each of the plurality of persons with an activity object; and selecting one or more of the plurality of persons based on the determined importance score to generate a composite frame of the event including the selected one or more persons.

System and method of generating a composite frame

An apparatus for classifying an action in a video of a sports event including receiving a first video segment and a second video segment in the sports video, wherein the second video segment is the segment after next of the first video segment; receiving a predetermined play state of the first video segment and a different predetermined play state of the second video segment, locating a play object in one of a predetermined set of regions in a field of the sports event in the second segment; determining a role of a player interacting with the play object when the play object is located one of the predetermined set of regions in the second video segment; and classifying the action in the first video segment based on the located play object and the determined role.

Classify actions in video segments using play state information

A system and method for performing foreground/background separation on an input image. The method identifies a corresponding model visual element in a scene model associated with the input image, the model visual element being associated with a set of element models, each element model including a plurality of visual data sets. Select an element model from the set of element models, dependent upon a visual distance between the input visual element and a visual data set of the selected element model satisfying a predetermined criterion. The method classifies the input visual element as one of foreground and background, dependent upon the selected element model, and then updates each visual data set in the selected element model, dependent upon the input visual element and at least first and second different methods of updating a visual data set.

Method for video object detection

A method for classifying a visual element in a video frame as either foreground or background, the video frame being characterized using a scene model comprising a plurality of modes, the method comprising the steps of: determining a blob boundary characteristic for a blob comprising at least the visual element; identifying a mode matched to the visual element; classifying the visual element and the matched mode as foreground dependent upon a match mode boundary characteristic of the matched mode; and updating the scene model dependent upon the blob boundary characteristic and the matched mode boundary characteristic.

Video segmentation method

A method of determining stability of a camera comprises capturing an image with the camera and then (A) determining a magnitude of motion for each region of a current sub-division of the image. A step (B) then determines a number of the magnitudes of motion not larger than a magnitude threshold associated with the current sub-division, and where the determined number is greater than or equal to a region threshold associated with the number of regions in the current sub-division, (i) determining the camera to be stable, or otherwise (ii) dividing the current sub-division of the image into a further sub-division and repeating steps (A) and (B) upon the further sub-division.

Rapid shake detection using a cascade of quad-tree motion detectors

Disclosed is a method of classifying visual elements in a region of a video as either foreground or background. The method classifies each visual element in the region as either foreground or background using a first classifier, and expands spatially at least one of the visual elements classified as foreground to form a spatially expanded area. The method then classifies the visual elements in the spatially expanded area as either foreground or background using a second classifier that is more sensitive to foreground than the first classifier.

A method of updating a scene model for a foreground segmentation of an input image captured from a camera, is disclosed. One or more visual elements of the input image are determined. A spatial relationship between at least one of the visual elements and the scene model for a foreground segmentation of the input image is determined. The method updates the scene model for determining the foreground segmentation of the input image based on the determined spatial relationship.

Method, system and apparatus for updating a scene model

Disclosed are a method and apparatus for adjusting a set of luminance values associated with a set of visual elements in a current frame () of a video sequence for object detection (). The method determines (), for each of a plurality of scenarios (SO, SI, S2), a set of adjusted luminance values based on a corresponding luminance compensation value, and accumulates (), for each scenario, a set of brightness counts and darkness counts of the current frame based on the set of adjusted luminance values. A metric () is calculated for each scenario based on the set of brightness counts and darkness counts and one of scenarios is selected based on the calculated metric. The method then selects () the adjusted luminance value associated with the selected scenario as an adjusted set of luminance values associated with the current frame of the video sequence.

Method and system for luminance adjustment of images in an image sequence

Disclosed is a method of storing a scene model () used for foreground/background separation of a scene () captured by a camera (), the scene model comprising a plurality of visual element models () each associated with a set () of mode models (, . . . ), said method comprising determining () if a change in the scene satisfies a pre-determined threshold (MFGT), creating () a background image based on a plurality of the mode models classified as background, matching () an input image () captured by the camera and the background image by determining a similarity score, and updating the set of mode models if the similarity score satisfies a pre-determined similarity threshold by creating at least one mode model based on the received input image, said mode model being classified as background.

Method and system for robust scene modelling in an image sequence

Disclosed herein are a system and method for performing foreground/background separation on an input image. The method pre-classifies () an input visual element in the input image as one of a first element type and a second element type, dependent upon a predetermined characteristic. The method performs a first foreground/background separation () on the input visual element that has been pre-classified as the first element type, wherein the first foreground/background separation step is based on color data and brightness data of the input visual element. The method performs a second foreground/background separation () on the input visual element that has been pre-classified as the second element type, wherein the second foreground/background separation step is based on color data, brightness data, and texture of the input visual element.

Foreground background separation in a scene with unstable textures

Disclosed herein are a method, system, and computer program product for aligning an input video frame from a video sequence with a background model associated with said video sequence. The background model includes a plurality of model blocks (), each one of the plurality of model blocks () being associated with at least one mode (), wherein each mode () includes a plurality of frequency domain attributes. The method selects, for each one of the plurality of model blocks, a reference mode dependent upon a mode of the corresponding model block, generates a background reference image () comprising the plurality of selected reference blocks (), and then aligns the input frame with the background model (), based on the background reference image ().

Growing community of inventors

Epping, Australia

Amit Kumar Gupta