Canon Kabushiki Kaisha

Jarrad Michael Springett

David Grant McLeish

Jeroen Vendrig

Peter Jan Pakulski

Qiang Liu

Disclosed is a method (), in relation to a current video frame () comprising a visual element () associated with a location in a scene captured in the frame (), said visual element () being associated with a plurality of mode models (), said method matching () one of said plurality of mode models () to the visual element (), said method comprising, for each said mode model (), the steps of determining () a visual support value depending upon visual similarity between the visual element () and the mode model (), determining () a spatial support value depending upon similarity of temporal characteristics of the mode models () associated with the visual element and mode models () of one or more other visual elements (); and identifying () a matching one of said plurality of mode models () depending upon the visual support value and the spatial support value.

Spatio-activity based mode matching

Disclosed herein are a method and system for classifying a detected region of change of a video frame as one of an abandoned object event and an object removal event, wherein a plurality of boundary blocks define a boundary of said region of change. For each one of a set of said boundary blocks (), the method determines a predicted edge characteristic () and an observed edge characteristic () for said boundary block. The method then determines an individual block score () for said boundary block, based on said predicted edge characteristic () for said boundary block and said observed edge characteristic () for said boundary block. Once all of the set of boundary blocks have been processed, the method determines a global score () for said region of change, based on said individual block scores of said boundary blocks. The method then classifies the region of change () as an abandoned object event or an object removal event, based on how the overall score relates to a threshold.

Detection of abandoned and vanished objects

Disclosed is a methodof processing a video stream, the method comprising the steps of determininga representative age measure from a model for a visual element from the video stream, determininga representative activity count measure from the model, establishing a functional relationship between the representative activity count measure and the representative age measure, comparingthe functional relationship to a threshold value, and determiningif the visual element is stationary, based on the result of the comparing step.

Growing community of inventors

Cambridge, United Kingdom

Jarrad Michael Springett