Canon Kabushiki Kaisha

Andrew John Shellshear

Craig Matthew Brown

David Grant McLeish

Laurence Crew

Rebecca Jayne Gorton

A method for tracking objects across a number of image frames includes tracking objects in the frames based on appearance models of each foreground region corresponding to each of the objects and determining if a plurality of the tracked objects overlap. Where a plurality of the tracked objects overlap, the method creates compensated appearance models for each of the plurality of overlapping objects by attenuating common appearance features among the corresponding appearance models; and tracks the plurality of overlapping objects based on the created compensated appearance models.

Method for improving tracking in crowded situations using rival compensation

A method for tracking an object across a number of image frames comprises identifying a region containing the object in a first image frame to be stored as an exemplar view of the object. An appearance model (modified Exemplar View histogram is created based on the region in the first image frame and a background region in a second image frame, and the method determines at least one of a location and size of a predicted region for tracking the object in the second image frame using the appearance model. The method corrects at least one of the determined location and size of the predicted region in the second image frame in accordance with at least one of the location and size of the region in the first image frame corresponding to the exemplar view of the object.

Method for improving tracking using dynamic background compensation with centroid compensation

Disclosed herein are a method, system, and computer program product for displaying on a display device () a track summary () of an object in a scene of a video sequence. The method includes the steps of: determining a plurality of detected track elements of the object in the scene of the video sequence; receiving a selection criterion; identifying at least one characteristic of interest of the object, based on the selection criterion; selecting a track element from the plurality of detected track elements, said selected track element corresponding to the at least one identified characteristic of interest; determining a parameter of the selected track elements depending on the at least one characteristic of interest; and displaying the track summary derived from said detected track elements, based on the determined parameter.

Summary view of video objects sharing common attributes

A method, system, and computer program product for classifying a behavior of a detected object in a video frame, wherein the video frame includes a plurality of blocks and the detected object is associated with a subset of the plurality of blocks. The method includes the step of associating a behavior model with each of the plurality of blocks, wherein each behavior model includes a set of behavior modes each having a set of parameters. The method further includes the steps, for each block in the video frame associated with the detected object, of: (i) determining a set of behavior statistics associated with the detected object, based on the detected object and the set of parameters; and (ii) comparing the determined set of behavior statistics with the set of parameters of each behavior mode in the set of behavior modes associated with that block to determine an abnormality score. The method also includes the step of classifying the behavior of the detected object based on the abnormality scores associated with the subset of the plurality of blocks associated with the detected object.

Detection of abnormal behaviour in video objects

A method of displaying items from a collection of items including a first item is provided. The method determines a first sort order of the collection, and at least one alternate sort order of the collection. At least items adjacent to the first item in the first sort order, and in the alternate sort order, are then compared. The method then displays a portion of the items associated with the first item in each of the first sort order and in the alternate sort order based on the comparison.

Method for navigating large image sets using sort orders

A system for recording audio and video comprises at least one video camera device (), each camera device comprising a subsystem for capturing () at least video data, a storage device () upon which at least the video data is stored, a wireless interface () for communicating with at least one further recording device (), an internal clock() for recording at least a time at which the video data was recorded, and a connecting port () enabling connection to a remote-control device (eg.). The system also has at least one of the further recording devices (), each comprising a microphone () for capturing audio information and a storage device upon which corresponding audio data is recorded, a wireless interface () for communicating with the video camera device, an internal clock () for recording at least a time at which the audio data was recorded, and a connection port () enabling connection to the video camera device.

Video camera and remote recording system

A method () of displaying one or more data attributes, is disclosed. The displayed data attributes is associated with one or more portions of data. The method () dynamically compiles a list of one or more data attribute types according to an analysis of the one or more portions of data and associated data attributes. The one or more data attributes are then displayed.

Metadata driven user interface

A method () of displaying a plurality of images is disclosed. The method () displays the images in a stack arrangement. The stack may be a perspective stack and a non-perspective stack. Another method () of displaying a plurality of images is also disclosed. The method () displays the images in a stack following any arbitrary path. The methods () and () are particularly advantageous for displaying a collection of images of irregular sizes and aspect ratios. The methods () and () maintain the regular geometric layout of a stack of images and also ensure that the size of the minimum visible area of each image in the stack remains the same irrespective of the aspect ratio of a particular image.

Growing community of inventors

North Ryde, Australia

Andrew John Shellshear