Systems and methods for processing surveillance video streams using image classification and object detection are described. Video data from a video image sensor may be processed using an image classifier to determine whether an object type is present in a video frame. If the object type is present, the video frame and/or subsequent video frames may be processed using an object detector to provide additional object data, such as position information, for use in other video surveillance processes. In some examples, an event message may be generated and sent to a video surveillance application in response to selective object detection.

A system is provided and generally includes a server and an associate computing device. The server may receive location video data comprising at least one image from a camera directed to a location, such as a designated area of a parking lot. The server may detect one or more objects in the image, and determine a bounding box based on the detected objects. The server may also determine a confidence value corresponding to the bounding box. The confidence value may be determined based on an area of the image defined by the bounding box and a predefined class. The server may then generate an arrival message based on the determined confidence value, and transmit the arrival message to the associate computing device.

An analytical recognition system includes one or more video cameras configured to capture video and a video analytics module configured to perform real-time video processing and analyzation of the captured video and generate non-video data. The video analytic module includes one or more algorithms configured to identify an abnormal situation. Each abnormal situation alerts the video analytics module to automatically issue an alert and track one or more objects or individuals by utilizing the one or more video cameras. The abnormal situation is selected from the group consisting of action of a particular individual, non-action of a particular individual, a temporal event, and an externally generated event.

Methods, systems, apparatus, and computer programs, for tracking objects are disclosed. In one aspect, a method is disclosed that includes actions of obtaining an image, determining that a user of a first monitoring system has opted-in for object tracking by a second monitoring system that is remote from the first monitoring system, and based on a determination that the user of the first monitoring system has opted-in for object tracking: determining whether the obtained image satisfies a predetermined level of similarity to a stored tracking object image model stored on a first device of the first monitoring system, and based on a determination that the obtained image satisfies a predetermined level of similarity to the stored tracking object image model, generating a tracking update notification, and transmitting the tracking update notification to the second monitoring system that is remote from the first monitoring system.

A system receives a digital representation of a biometric for a person, uses the digital representation of the biometric to determine and/or otherwise retrieve identity information associated with the person, and uses the identity information to perform one or more actions related to the person's presence in one or more areas. For example, the system may estimate a path for the person and signal an agent electronic device based on the path. In another example, the system may determine a presence of a person within the area and/or transmit information to an agent electronic device regarding the determined presence. In still another example, the system may receive a request to communicate with the person and forward the communication to the person using the identity information.

A method for monitoring and securing a facility without employing a manned control center, according to which a server acquires surveillance data from each of a plurality of distributed surveillance devices deployed within or adjacent to a given security sensitive facility. Then the server receives an intrusion alert from a guard, or from one or more of the plurality of surveillance devices to initiate a triggering event, if the acquired surveillance data is indicative of activity that has been detected at an indicated location. A first guard is alerted and presented with a full situational awareness image to assess the severity of the detected activity and the triggering event is terminated if found by the first guard to be of a low severity, or an interception operation initiated by self-dispatching or dispatching one or more additional guards to a close by location that holds tactical advantage relative to the indicated location if the triggering event was found by the first guard to be of a high severity.

A method includes receiving a first time series of video frames depicting a first area of interest that includes a display area in a retail environment, and using classification by a convolutional neural network to detect instances of people picking up inventory items from the display area. The method also includes receiving a second time series of video frames depicting a second area of interest in the retail environment, and determining, based upon one or more portions of the second time series of video frames, that at least one inventory item picked up at the display area was not, or will not likely be, checked out. The method also includes causing one or more alert messages to be displayed, including causing an alert message to be displayed based on the determining.

A route display apparatus (10) according to the present disclosure includes: an acquisition unit (11) that acquires friend account information of a friend account that is connected online to an account of interest; a specification unit (12) that specifies a traffic site near an activity site of a friend user who uses the friend account based on the acquired friend account information; a calculation unit (13) that calculates an estimated movement route of a user of interest who uses the account of interest, the estimated movement route including the specified traffic site; and a display unit (14) that displays the calculated estimated movement route.

A method of selectively broadcasting a message to a client by a server without knowing the client's internet protocol (IP) address includes performing target recognition and tracking on one or more targets, including position of the one or more targets, extracting target-specific context parameters from the one or more recognized and tracked targets, encoding the target-specific context parameters into a header, thereby generating a context address for the one or more targets, appending the context address to a message for the one or more targets from a predetermined set of messages based on the position of the one or more targets, thereby generating one or more packets of information, and broadcasting the one or more packets wirelessly to one or more client mobile devices each associated with the one or more targets.

A person tracking support device includes a processor. The processor acquires identification information of a tracked person identified from a face image of a person imaged by a first camera, and a first time at which the tracked person is imaged by the first camera, and also acquires a second time at which the tracked person is imaged by a second camera positioned away from the first camera, predicts a time at which the tracked person reaches a specific area on the basis of an elapsed time from the first time to the second time and a distance from the first camera to the second camera, and notifies a mobile terminal device possessed by each of a plurality of observers of the identification information of the tracked person, the specific area, and the time predicted.