Method and system for detecting the occurrence of an interaction event via trajectory-based analysis
AssigneeConduent Business Services, LLC
InventorsRobert P. Loce, Wencheng Wu, Edgar A. Bernal, Michael C. Mongeon, Daniel S. Hann
Life of this patent
Estimating the term…
Abstract
Disclosed is a method and system for detecting an interaction event between two or more objects in a surveillance area, via the application of heuristics to trajectory representations of the static or dynamic movements associated with the objects. According to an exemplary embodiment, trajectory interaction features (TIFs) are extracted from the trajectory representations and heuristics are applied to the TIFs to determine if an interaction event has occurred, such as a potential illegal drug deal involving two or more pedestrians.
Claims21
The computer-implemented method for automatically detecting the interaction of two or more people according to claim 2, further comprising:
- e) collecting evidence of the detected interaction events in step d), the evidence including one or more of the number of occurrences of the detected interaction event, the number of occurrences of the detected interaction event associated with each of the two or more people detected within the first and second common temporal sequence of video frames, a time duration and start/end time associated with each detected interaction event, a calculated probability of the occurrence of the interaction event, and an indication of static or dynamic movement associated with each of the two or more people detected within the first and second common temporal sequence of video frames.
The computer implemented method for automatically detecting the interaction event of two or more people according to claim 1, wherein the interaction event is an illegal drug deal between two or more people.
The computer-implemented method for automatically detecting the interaction event of two or more people according to claim 1, wherein the TIFs include one or more of a position, a velocity and a relative distance associated with the two or more people within the first common temporal sequence of video frames.
A video system for automatically detecting an occurrence of an interaction event of two or more people concurrently present in a surveilled area comprising:
- a video camera with an associated FOV (field-of-view) directed towards the surveilled area;
- and
- a video processing system operatively connected to the video camera, the video processing system configured to:
- a) acquire a video stream from the video camera, the video stream including a temporal sequence of video frames including the surveilled area within the FOV associated with the video camera;
- b) detect and track two or more people within a first common temporal sequence of video frames included in the video stream, and generate a trajectory of each person tracked within the first common temporal sequence of video frames;
- c) process the trajectories of the tracked people to extract one or more trajectory interaction features (TIFs) associated with the trajectories of the two or more people tracked within the first common temporal sequence of video frames;
- and
- d) apply predefined heuristics to the extracted TIFs to detect an interaction event has occurred between at least two people of the two or more people tracked within the first common temporal sequence of video frames.
A video system for automatically detecting an occurrence of an interaction event of two or more objects concurrently present in a surveilled area, the interaction event associated with an illegal drug deal between the two or more objects, comprising:
- a video camera with an associated FOV (field-of-view) directed towards the surveilled area;
- and
- a video processing system operatively connected to the video camera, the video processing system configured to:
- a) acquire a video stream from the video camera, the video stream including a temporal sequence of video frames including all or part of the surveilled area within all or part of the FOV associated with the video camera;
- b) detect and track two or more objects within a first common temporal sequence of video frames included in the video stream, and generate a trajectory of each object tracked within the first common temporal sequence of video frames;
- c) process the trajectories of the tracked objects to extract one or more trajectory interaction features (TIFs) associated with the trajectories of the two or more objects tracked within the first common temporal sequence of video frames, the TIFs including one or more of a position, a velocity and a relative distance associated with the two or more objects within the first common temporal sequence of video frames;
- and
- d) apply predefined heuristics to the extracted TIFs to detect an interaction event has occurred between at least two objects of the two or more objects tracked within the first common temporal sequence of video frames, the predefined heuristics including a velocity threshold and a proximity threshold associated with the two or more objects tracked within the first common temporal sequence of video frames,
- wherein steps b)-d) are repeated for a second common temporal sequence of video frames, distinct from the first common temporal sequence of video frames, to determine if the interaction event has occurred between at least two objects of the two or more objects tracked within the second common temporal sequence of video frames.
Dependencies are inferred from the claim text.