Abstract: Method of notifying a user of site abnormalities via an application configured to access an event server having a first sensor abnormality detector connected to a first sensor, for detecting first abnormal behavior of first sub-events sensed by the first sensor, the first abnormal behavior corresponding to a first abnormal behavior value, a second sensor abnormality detector connected to a second sensor, for detecting second abnormal behavior of second sub-events sensed by the second sensor of a type different from the first sensor, the second abnormal behavior corresponding to a second abnormal behavior value, a correlator for correlating the first and second abnormal behavior values and logging correlated values as a composite event, a data store, the application having a viewer configured to show, on the device, data associated with a plurality of composite events, the viewer further configured to display the plurality of composite events in a temporal order.

Abstract: A system and method for predictive abnormal behavior detection is disclosed. The system receives surveillance data such as video data and can create and update a plurality of prediction models. The system may also receive video data relating to a moving object and may generate a prediction of the future locations of the moving object based on the generated prediction models. The predicted motion may be scored by a scoring engine to determine if the predicted motion is unsafe or otherwise undesirable.

Abstract: A multi-perspective context sensitive behavior assessment system includes an adaptive behavior model builder establishing a real-time reference model that captures intention of motion behavior. It operates by modeling outputs of multiple user defined scoring functions with respect to multiple references of application specific target areas of interest. The target areas have criticality values representing a user's preference regarding the target areas with respect to one another. The outputs of the scoring functions are multiplied by the critically values to form high level sequences of representation that are communicated to the user.

Abstract: A method for determining a transformation matrix used to transform data from a first image of a space to a second image of the space is disclosed. The method comprises receiving image data from a video camera monitoring the space, wherein the video camera generates image data of an object moving through the space and determining spatio-temporal locations of the object with respect to a field of view of the camera from the image data. The method further comprises determining observed attributes of motion of the object in relation to the field of view of the camera based on the spatio-temporal locations of the object, the observed attributes including at least one of a velocity of the object with respect to the field of view of the camera and an acceleration of the object with respect to the field of view of the camera. The method also includes determining the transformation matrix based on the observed attributes of the motion of the object.

Abstract: A video surveillance system is disclosed. The system includes a model database storing a plurality of models and a vector database storing a plurality of vectors of recently observed trajectories. The system includes a model building module that builds a new motion model corresponding to the motion data of the current trajectory data structure. The system generates a current trajectory data structure having motion data and abnormality scores. The system also includes a database purging module configured to determine a subset of vectors that is most similar to the current trajectory data structure based on a measure of similarity between the subset of vectors and the current trajectory data structure. The database purging module is further configured to replace one of the motion models in the model database with the new motion model based on an amount of vectors in the subset vectors the recentness of the subset of vectors.

Abstract: A surveillance system implements an architecture and process to support real-time abnormal behavior assessment operations in a distributed scalable sensor network. An automated behavior model builder generates behavior models from sensor data. A plurality of abnormal behavior scoring engines operating concurrently to generate abnormal behavior assessment models by scoring the behavior models. An execution performance manager performs fast switching of behavior models for the abnormal behavior scoring engines. The execution performance manager performs detection of abnormal behavior score distribution characteristic deviation by comparing a current abnormal behavior assessment model to a pre-recorded abnormal behavior assessment model. The execution performance manager selects a pre-recorded behavior model for the abnormal behavior scoring engines when the deviation exceeds a predetermined threshold.

Abstract: The intelligent, automated surveillance system collects the interactions between the security personal and the surveillance system during the handling of an alarm. Each alarm is modeled as a “transaction” and each operation/action that a security personal executes modeled as an “event” within the transaction. The collected events within the transaction are in partial order. Furthermore, the system provides a scoring system for a security manager to evaluate the performance of the security guard. The score of the sequence of actions that the security guard performed manually and the system performed automatically for each set of dependent alarms are used to decide future sequence of operation. Security guards can overwrite the automatic sequencing of actions with manual sequence of operations.

Abstract: A surveillance system improves accuracy and robustness of abnormal behavior detection of a monitored object traversing a space includes a metadata processing module, a model building module, and a behavior assessment module. The metadata processing module generates trajectory information for a monitor object and determines attributes of the monitored object. The model building module at least one of generates and updates normal motion models based on at least one of the trajectory information, the attributes, and an abnormal behavior score. The behavior assessment module generates the abnormal behavior score based on one of a plurality of methods. A first one of the plurality of methods defines wrong direction behavior. A second one of the plurality of methods defines wandering/loitering behavior. A third one of the plurality of methods defines speeding behavior.

Abstract: A system and method for predictive abnormal behavior detection is disclosed. The system receives surveillance data such as video data and can create and update a plurality of prediction models. The system may also receive video data relating to a moving object and may generate a prediction of the future locations of the moving object based on the generated prediction models. The predicted motion may be scored by a scoring engine to determine if the predicted motion is unsafe or otherwise undesirable.

Abstract: A system and method for managing video storage on a video surveillance system is disclosed. The system calculates an importance score for a video segment based on a weighted average of multiple scores corresponding to the video event. The multiple scores include an event correlation score correlating a video event with a plurality of other video events, an abnormality score indicating the abnormality of the observed event, a user entered score, a score relating to the number of times a specific location was visited by a moving object, the amount of times a video has been retrieved, and a predicted future storage space. The importance score may be used to determine a video retention operation, such as retaining the video event, purging the video event, reducing the video quality of the event, or storing the video in mix-reality format.

Abstract: A surveillance system generally includes a data capture module that collects sensor data. A scoring engine module receives the sensor data and computes at least one of an abnormality score and a normalcy score based on the sensor data, at least one dynamically loaded learned data model, and a learned scoring method. A decision making module receives the at least one of the abnormality score and the normalcy score and generates an alert message based on the at least one of the abnormality score and the normalcy score and a learned decision making method to produce progressive behavior and threat detection.

Abstract: A multi-perspective context sensitive behavior assessment system includes an adaptive behavior model builder establishing a real-time reference model that captures intention of motion behavior. It operates by modeling outputs of multiple user defined scoring functions with respect to multiple references of application specific target areas of interest. The target areas have criticality values representing a user's preference regarding the target areas with respect to one another. The outputs of the scoring functions are multiplied by the critically values to form high level sequences of representation that are communicated to the user.

Abstract: A resource manager transforms the MPEG7 descriptors into an active and composite storage, processing, and presentation component in a storage area network (e.g. iSCSI). The active component can enable fast search and retrival operation directly on the logical disk blocks which maps well with the multimedia video stream and images data. It can also support content addressable search on the video and image files and play the media blocks directly. In addition, it enables a dynamic configuration of a media processing function after it is loaded in an execution environment. The data block is moved from the iSCSI interface directly into processing modules and presentation modules via decoder, buffer, and constraint control units.

Abstract: A metadata database adaptor for use with a surveillance and/or sensor system is capable of adapting metadata messages of varying formats according to needs of metadata databases. In other aspects, a metadata data model template can allow a user to define a data definition that is used to map user defined data with the metadata data model template to form XML data schema. Template mapping knowledge can then be applied for fast XML data schema to non-XML database schema generation without translation processing. In yet other aspects, an application domain template can allow a user to define a query definition that can then be processed with a mapping of the application domain template to translate Xpath, Xquery, or others to a database query.

Abstract: An associative vector storage system has an encoding engine that takes input vectors, and generates transformed coefficients for a tunable number of iterations. Each iteration performs a complete transformation to obtain coefficients, thus performing a process of iterative transformations. The encoding engine selects a subset of coefficients from the coefficients generated by the process of iterative transformations to form an approximation vector with reduced dimension. A data store stores the approximation vectors with a corresponding set of meta data containing information about how the approximation vectors are generated. The meta data includes one or more of the number of iterations, a projection map, quantization, and statistical information associated with each approximation vector. A search engine uses a comparator module to perform similarity search between the approximation vectors and a query vector in a transformed domain.

Abstract: A surveillance system implements an architecture and process to support real-time abnormal behavior assessment operations in a distributed scalable sensor network. An automated behavior model builder generates behavior models from sensor data. A plurality of abnormal behavior scoring engines operating concurrently to generate abnormal behavior assessment models by scoring the behavior models. An execution performance manager performs fast switching of behavior models for the abnormal behavior scoring engines. The execution performance manager performs detection of abnormal behavior score distribution characteristic deviation by comparing a current abnormal behavior assessment model to a pre-recorded abnormal behavior assessment model. The execution performance manager selects a pre-recorded behavior model for the abnormal behavior scoring engines when the deviation exceeds a predetermined threshold.

Abstract: A meta data management system for use with a surveillance system includes a user interface that allows users to define rules to manage meta data from distributed devices. An application programming interface provides an application access to system data and control information. A mechanism allows the application to transparently and seamlessly integrate with different types of databases by transparently allocating and searching the data that are physically distributed at different devices.

Abstract: A resource manager allocates operation requests to security network devices according to device characteristics. The devices collect and/or manage data from an environment. The devices may include a camera, a multimedia recorder, an analyzer, and a meta-data server. One or more users submit operation requests to a controller. The controller allocates the network devices to the operation requests according to the device characteristics. The device characteristics include availability of the device, media flow data of the device, location of the device, and capabilities of the device.

Abstract: A peer-to-peer camera sensor network is defined using intelligent cameras that employ iSCSI initiators and iSCSI targets to read and write data and to send control commands directly across the network as iSCSI blocks. Because data transfer rides on top of the internet protocol, cameras can be directly attached to the internet without requiring attachment to a host computer. Image data represented as video frames are mapped onto iSCSI data blocks and are shared among the cameras directly to form an efficient virtual block level video image frame storage that can be directly manipulated by multiple cameras without data replications. Transport of multiple streams, associated with scalable or multilevel MPEG encoding scheme for instance, are automatically sequenced and realigned as the iSCSI data blocks are time-aligned.

Abstract: The surveillance visualization system extracts information from plural cameras to generate a graphical representation of a scene, with stationary entities such as buildings and trees represented by graphical model and with moving entities such as cars and people represented by separate dynamic objects that can be coded to selectively reveal or block the identity of the entity for privacy protection. A power lens tool allows users to specify and retrieve results of data mining operations applied to a metadata store linked with objects in the scene. A distributed model is presented where a grid or matrix is used to define data mining conditions and to present the results in a variety of different formats. The system supports use by multiple persons who can share metadata and data mining queries with one another.