Abstract: A transaction monitoring system is provided for monitoring transactions in a variety of transaction locations such a retail locations or gambling or other locations. The transaction monitoring system uses a multi-modal sensor an comprises a system controller that uses multi-modal sensor data to detect abnormal activity. The transaction monitoring system may capture and/or use image data and depth data. The transaction monitoring system may be used to detect theft or fraud for example by determining when there is an unscanned item, an occluded item, an incorrectly scanned item, unmatched plurality or incorrect capital exchange. To this end, the transaction monitoring system may also receive transaction input such as barcode data, or capital exchange data. Also provided is a transaction monitoring method and a system controller for a transaction monitoring system.

Abstract: Provided is novel technology for secure security data transmission and more particularly for registering network-enabled security devices such as IP cameras to a security server over a public network such as to a cloud-based security service. An enrolment server is provided that is logged into using a computing device to request and receive an activation code for the security device. The activation code is then provided to the security device, e.g. directly by the computing device. The Security device authenticates itself based on the activation code and in one example provides a public key that will be used to verify its registration. Data transmissions by the device are secured in part on the basis of its registration.

Abstract: Systems and methods are disclosed for locating a retroreflective object in a digital image and/or identifying a feature of the retroreflective object in the digital image. In certain environmental conditions, e.g. on a sunny day, or when the retroreflective material is damaged or soiled, it may be more challenging to locate the retroreflective object in the digital image and/or to identify a feature of the object in the digital image. The systems and methods disclosed herein may be particularly suited for object location and/or feature identification in situations in which there is a strong source of ambient light (e.g. on a sunny day) and/or when the retroreflective material on the object is damaged or soiled.

Abstract: A computer-implemented method, comprising: obtaining motion indicators for a plurality of samples of a video stream; obtaining an anomaly state for each of a plurality of time windows of the video stream, each of the time windows spanning a subset of the samples, by (i) obtaining estimated statistical parameters for the given time window based on measured statistical parameters characterizing the motion indicators for the samples in at least one time window of the video stream that precedes the given time window and (ii) determining the anomaly state for the given time window based on the plurality of motion indicators obtained for the samples in the given time window and the estimated statistical parameters; and processing the video stream based on the anomaly state for various ones of the time windows.

Abstract: A system to perform processing operations of input (video) streams, including is disclosed. The system consists of an input module, a stream type detection engine, a plurality of processing resources a resource monitoring engine, an attribution module, a dispatching module, and various other optional interface modules.

Abstract: A method and system for viral identification of evacuees are provided. The method is recursive and involves bringing an emergency warden and a midstream evacuee in close proximity with one another to enable a handheld computing device belonging to one of the two to read information from the other, enabling the handheld computing device to read the information, having the handheld computing device read the information to enable an identification of the midstream evacuee, providing the identifier of the midstream evacuee to a central mustering server, whereby the midstream evacuee is enabled to act as an emergency warden, and performing the method with the midstream evacuee acting as an emergency warden with respect to another evacuee before the central mustering server. The method provides the advantage of virally identifying evacuees within the confines of a muster point in an efficient and reliable manner.

Abstract: A security video monitoring client system and method of presenting feeds within the same are disclosed. Out-of-process renderer components executing outside the client program provide an important performance advantage, particularly as to the number of video feeds to decode and/or render that can be decoded. This external thread execution strategy likewise facilitates fault isolation, shielding the client from undesired effects arising from the termination, restarting, and/or any other action to be taken as a result of anomalous operation of any one or more out-of-process renderer components.

Abstract: A network sanitization technology for enforcing a network edge and enforcing particular communication functions for untrusted dedicated-function devices such as IP cameras. An untrusted network device is isolated from a network by a network sanitization system such that it cannot communicate with the network. Communications from the untrusted device are intercepted by the system and only allowed communications are used. Allowed communications are used to create new communications according to an allowed framework. Sanitization device may be in small two-port package with visual indicia indicating the untrusted device and the network side. The device may use and provide PoE to device. Abstract is not to be considered limiting.

Abstract: Provided is a visual vehicle speed estimation system based on camera output and calibration for such a vehicle speed estimation system. The calibration allows use of the system where the absolute camera position is unknown. Calibration determines an absolute-position-independent relationship between an image space placement and a physical space position relative to the camera. The calibration is done on the basis of camera output using vehicle features of known dimensions and some assumed physical constraints related thereto to provide a conversion relationship between image coordinates and physical space coordinates in a physical space defined in relation to the camera. This relationship is then used to estimate vehicle speeds based only on the visual information provided by the camera. Abstract is not to be interpreted as limiting.

Abstract: In-service upgrade of software can be achieved efficiently when software modules pass data using message or data queues. The use of data queues facilitates the transition from a software module's old behavior to a new behavior without risking a deadlock or dropped module call. Upgradeable objects connect to process objects that maintain the queues and their state data, and upgrade objects connect to the process objects of their predecessors.