Abstract: A solution for monitoring an area includes using a region schema for the area. The region schema can include a set of prototypical tracks, each of which includes a start location, an end location, and a trajectory. The trajectory comprises an expected path an object will travel between the start location and the end location and can include variation information that defines an amount that an object can vary from the trajectory. The region schema can be generated by obtaining training object tracking data for the area for an initialization time period and evaluating the object tracking data to identify the set of prototypical tracks. While monitoring the area, monitored object tracking data is obtained for a monitored object in the area, and abnormal behavior of the monitored object is identified when the monitored object tracking data for the monitored object does not follow at least one of the set of prototypical tracks in the region schema.

Abstract: A system, method and program product for providing a video surveillance system that enhances object detection by utilizing feedback from a tracking system to an object detection system. A system is provided that includes: a moving object detection system for detecting moving objects in a video input; an object tracking system for tracking a detected moving object in successive time instants; and a tracker feedback system for feeding tracking information from the object tracking system to the moving object detection system to enhance object detection.

Abstract: A system for automatically acquiring high-resolution images by steering a pan-tilt-zoom camera at targets detected in a fixed camera view is provided. The system uses automatic or manual calibration between multiple cameras. Using automatic calibration, the homography between the cameras in a home position is estimated together with the effects of pan and tilt controls and the expected height of a person in the image. These calibrations are chained together to steer a slave camera. The manual calibration scheme steers a camera to the desired region of interest and calculates the pan, tile and zoom parameters accordingly.

Abstract: A method and system for real time processing of a sequence of video frames. A current frame in the sequence and at least one frame in the sequence occurring prior to the current frame is analyzed. Each frame includes a two-dimensional array of pixels. The sequence of video frames is received in synchronization with a recording of the video frames in real time. The analyzing includes performing a background subtraction on the at least one frame, which determines a background image and a static region mask associated with a static region consisting of a contiguous distribution of pixels in the current frame. The static region mask identifies each pixel in the static region upon the static region mask being superimposed on the current frame. The background image includes the array of pixels and a background model of the at least one frame and does not include any moving object.

Abstract: An occlusion detection system and method include a decomposer configured to decompose an image into a set of hierarchical parts. A hierarchy of classifiers is employed to detect features in the image and the hierarchical parts. A logical operation is configured to logically combine a classification result from at least two of the classifiers to detect an occlusion state of the image.

Abstract: An approach that allows for model based people counting is provided. In one embodiment, there is a generating tool configured to generate a set of person-shape models based on results of a cumulative training process; a detecting tool configured to detect persons in a camera field-of-view by using the set of person-shape models, and a counting tool configured to track detected persons upon crossing by the detected persons of a previously established virtual boundary.

Abstract: A system for automatically acquiring high-resolution images by steering a pan-tilt-zoom camera at targets detected in a fixed camera view is provided. The system uses automatic or manual calibration between multiple cameras. Using automatic calibration, the homography between the cameras in a home position is estimated together with the effects of pan and tilt controls and the expected height of a person in the image. These calibrations are chained together to steer a slave camera. The manual calibration scheme steers a camera to the desired region of interest and calculates the pan, tile and zoom parameters accordingly.

Abstract: A method for real time processing of a sequence of video frames. The video frames are received in synchronization with a recording of the video frames in real time for triggering an alert. The method is implemented by execution of program code on a processor of a computer system. Each frame includes a two-dimensional array of pixels and a frame-dependent color intensity at each pixel. An algorithm determines whether a static object in a current frame of the video frames is an abandoned object or a removed object. The determined status, the current frame time, the static region, and the static object are stored in a data storage medium of the computer system. An alarm is triggered in response to satisfaction of requirements that include a persistence requirement, a non-persistence duration requirement, and a persistence duration requirement.

Abstract: A solution for monitoring an area uses color histograms and size information (e.g., heights and widths) for blob(s) identified in an image of the area and model(s) for existing object track(s) for the area. Correspondence(s) between the blob(s) and the object track(s) are determined using the color histograms and size information. Information on an object track is updated based on the type of correspondence(s). The solution can process merges, splits and occlusions of foreground objects as well as temporal and spatial fragmentations.

Abstract: A person detection system includes a face detector configured to detect a face in an input video sequence, the face detector outputting a face keyframe to be stored if a face is detected; and a person detector configured to detect a person in the input video sequence if the face detector fails to detect a face, the person detector outputting a person keyframe to be stored, if a person is detected in the input video sequence.

Abstract: A method, system and computer program product for detecting presence of an object in an image are disclosed. According to an embodiment, a method for detecting a presence of an object in an image comprises: receiving multiple training image samples; determining a set of adaptive features for each training image sample, the set of adaptive features matching the local structure of each training image sample; integrating the sets of adaptive features of the multiple training image samples to generate an adaptive feature pool; determining a general feature based on the adaptive feature pool; and examining the image using a classifier determined based on the general feature to detect the presence of the object.

Abstract: A method, system and computer program product for detecting presence of an object in an image are disclosed. According to an embodiment, a method for detecting a presence of an object in an image comprises: receiving multiple training image samples; determining a set of adaptive features for each training image sample, the set of adaptive features matching the local structure of each training image sample; integrating the sets of adaptive features of the multiple training image samples to generate an adaptive feature pool; determining a general feature based on the adaptive feature pool; and examining the image using a classifier determined based on the general feature to detect the presence of the object.

Abstract: An approach that detects objects crossing a virtual boundary line is provided. Specifically, an object detection tool provides this capability. The object detection tool comprises a boundary component configured to define a virtual boundary line in a video region of interest, and establish a set of ground patch regions surrounding the virtual boundary line. The object detection tool further comprises an extraction component configured to extract a set of attributes from each of the set of ground patch regions, and update a ground patch history model with the set of attributes from each of the set of ground patch regions. An analysis component is configured to analyze the ground patch history model to detect whether an object captured in at least one of the set of ground patch regions is crossing the virtual boundary line in the video region of interest.

Abstract: A method for processing a time-ordered sequence of video frames. The method is implemented by execution of program code on a processor of a computer system. Each frame includes a two-dimensional array of pixels and a frame-dependent color intensity at each pixel. A current frame and at least one frame occurring prior to the current frame in the sequence are analyzed via a background subtraction on the at least one frame to determine a background image and a static region mask associated with a static region. The background subtraction determines an existence of a static object relating to the static region. A status of the static object is determined, the status being either that the static object is an abandoned object or that the static object is a removed object. The determined status is stored in a data storage medium of the computer system.

Abstract: A system for automatically acquiring high-resolution images by steering a pan-tilt-zoom camera at targets detected in a fixed camera view is provided. The system uses automatic or manual calibration between multiple cameras. Using automatic calibration, the homography between the cameras in a home position is estimated together with the effects of pan and tilt controls and the expected height of a person in the image. These calibrations are chained together to steer a slave camera. The manual calibration scheme steers a camera to the desired region of interest and calculates the pan, tile and zoom parameters accordingly.

Abstract: An apparatus and method of identifying objects with salient motion in a scene and program product therefor. A region of change is identified within a scene. Optical flow is determined for the region of change. Pixels moving in a common direction are identified as seed pixels. Seed pixels are expanded to form pixel clusters. Temporal imaging results are fused to identify those objects with salient motion.

Abstract: An approach that allows for model based people counting is provided. In one embodiment, there is a generating tool configured to generate a set of person-shape models based on results of a cumulative training process; a detecting tool configured to detect persons in a camera field-of-view by using the set of person-shape models, and a counting tool configured to track detected persons upon crossing by the detected persons of a previously established virtual boundary.

Abstract: An approach that detects objects crossing a virtual boundary line is provided. Specifically, an object detection tool provides this capability. The object detection tool comprises a boundary component configured to define a virtual boundary line in a video region of interest, and establish a set of ground patch regions surrounding the virtual boundary line. The object detection tool further comprises an extraction component configured to extract a set of attributes from each of the set of ground patch regions, and update a ground patch history model with the set of attributes from each of the set of ground patch regions. An analysis component is configured to analyze the ground patch history model to detect whether an object captured in at least one of the set of ground patch regions is crossing the virtual boundary line in the video region of interest.

Abstract: An approach that indexes and searches according to a set of attributes of a person is provided. In one embodiment, there is an extensible indexing and search tool, including an extraction component configured to extract a set of attributes of a person monitored by a set of sensors in a zone of interest. An index component is configured to index each of the set of attributes of the person within an index of an extensible indexing and search tool. A search component is configured to enable a search of the index of the extensible indexing and search tool according to at least one of the set of attributes of the person.

Abstract: A system, method and program product for providing automated learning for a people counting system. A system is disclosed that includes a grid system for dividing a field of view (FOV) of a captured image data into a set of blocks; an object detection and tracking system for tracking a blob passing through the FOV; and a learning system that maintains person size parameters for each block and updates person size parameters for a selected block when a blob appears in the selected block.