Video surveillance system that detects predefined behaviors based on predetermined patterns of movement through zones
First Claim
1. A method for use in a video surveillance system, the method comprisinggenerating at least one hypothesis comprising a set of hypothesized trajectories of objects identified, based on their appearance, as being in a particular object class and hypothesized to have been moving through an area under surveillance at a particular time, said system capturing an image of said area under surveillance, said image of said area under surveillance including at least two zones within said area under surveillance,utilizing said hypothesis to analyze said area under surveillance to determine whether at least one predefined alert condition has occurred within the area under surveillance, said at least one alert condition includinga predetermined pattern of movement of at least a first one of said objects between at least two of said zones, said predetermined pattern of movement including that a) said first object was in a first one of said zones within said area being analyzed, and b) said first object thereafter moved from said first one of said zones within said area being analyzed to a second one of said zones within said area being analyzed, andat least one time criterion defining a time relationship between the presence of a) said first object in at least one of said first and second zones within said area being analyzed and b) at least a second one of said objects in that same one of said first and second zones.
16 Assignments
0 Petitions
Accused Products
Abstract
A video surveillance system uses rule-based reasoning and multiple-hypothesis scoring to detect predefined behaviors based on movement through zone patterns. Trajectory hypothesis spawning allows for trajectory splitting and/or merging and includes local pruning to managed hypothesis growth. Hypotheses are scored based on a number of criteria, illustratively including at least one non-spatial parameter. Connection probabilities computed during the hypothesis spawning process are based on a number of criteria, illustratively including object size. Object detection and probability scoring is illustratively based on object class.
-
Citations
25 Claims
-
1. A method for use in a video surveillance system, the method comprising
generating at least one hypothesis comprising a set of hypothesized trajectories of objects identified, based on their appearance, as being in a particular object class and hypothesized to have been moving through an area under surveillance at a particular time, said system capturing an image of said area under surveillance, said image of said area under surveillance including at least two zones within said area under surveillance, utilizing said hypothesis to analyze said area under surveillance to determine whether at least one predefined alert condition has occurred within the area under surveillance, said at least one alert condition including a predetermined pattern of movement of at least a first one of said objects between at least two of said zones, said predetermined pattern of movement including that a) said first object was in a first one of said zones within said area being analyzed, and b) said first object thereafter moved from said first one of said zones within said area being analyzed to a second one of said zones within said area being analyzed, andat least one time criterion defining a time relationship between the presence of a) said first object in at least one of said first and second zones within said area being analyzed and b) at least a second one of said objects in that same one of said first and second zones.
-
14. A method for use in a video surveillance system, the method comprising
generating at least one hypothesis comprising a set of hypothesized trajectories of objects identified, based on their appearance, as being in a particular object class and hypothesized to have been moving through an area under surveillance at a particular time, said area under surveillance being divided into at least two zones, utilizing said at least one of said hypotheses to determine whether at least one predefined alert condition has occurred within the area under surveillance, said at least one alert condition including a predetermined pattern of movement of at least one of said objects relative to at least one of said zones, said predetermined pattern of movement including that a) said object was in a first one of said zones within said area under surveillance, and b) said object thereafter moved from said first one of said zones within said area under surveillance to a second one of said zones within said area under surveillance, andat least one time criterion, said at least one time criterion being that said object was in said second zone within said area under surveillance for more than a predetermined period of time.
Specification