Abstract: Disclosed is a facial recognition system/method, utilizing modules to perform the following routine: extracting a feature descriptor from a detected feature point of a detected face in an input image frame; and matching the extracted feature descriptor with at least one of a pre-stored facial image that is index-mapped, comprising at least a first and second round of matching, wherein the second round of matching only selects the index-mapped facial images that matched above a pre-defined threshold from the first round of matching. Optionally, the above described steps may be coupled to a Point-of-Recognition (POR) provisioning, enabling an on-demand gate-keeping and/or payment processing for an end-user at an event/venue entry or point-of-sale.

Abstract: A device is configured to be mounted to a planar mounting panel, including, for example, a wall or ceiling of a home or other building. The device includes a housing, a fastener, a dogleg tab and a friction inducing member. The housing is configured to be received in an aperture in the mounting panel and includes a housing aperture. The fastener is disposed in the housing aperture. The dogleg tab is operatively coupled to one end of the fastener. The dogleg tab is configured to be disposed in a retracted position and to be disposed in an engagement position, in which engagement position the dogleg tab is disposed to engage an inside surface of the mounting panel. The friction inducing member is fixedly attached to the housing adjacent the housing aperture and friction-fit to the fastener.

Abstract: An authentication system accesses an image of a face of a user. The face of the user is partially covered by a facial mask. The authentication system detects an area on the facial mask and generates a first identification of the user based on the area on the facial mask. The authentication system also detects an exposed area uncovered by the facial mask on the face of the user and generates a second identification of the user based on the exposed area. The authentication system compares the first identification of the user with the second identification of the user, and authenticates the user based on the comparison.

Abstract: An audio firewall system has a microphone that generates audio data. A speech-to-text engine converts the audio data to text data. The text data is parsed for a service wake word and corresponding content data. The service wake word identifies one of a local security system and a remote assistant server. A text-to-speech engine converts the service wake word and the corresponding content data to converted audio data. The converted audio data is provided to the remote assistant server. The content data is provided to the local security system. The audio firewall system receives a response from the remote assistant server or the local security system and outputs an audio signal corresponding to the response.

Abstract: A server accesses a security system profile of a first security system. The security system profile identifies a plurality of sensors connected to the first security system. The server identifies a second security system based on at least a first sensor of the plurality of sensors coupled to the first security system. The server then generates a notification sharing profile for the first security system based on the security system profile. The notification sharing profile indicates that the second security system corresponds to the first sensor. A first event triggered by the first sensor causes a first notification to the second security system.

Abstract: A seed camera disposed a first location is manually calibrated. A second camera, disposed at a second location, detects a physical marker based on predefined characteristics of the physical marker. The physical marker is located within an overlapping field of view between the seed camera and the second camera. The second camera is calibrated based on a combination of the physical location of the physical marker, the first location of the seed camera, the second location of the second camera, a first image of the physical marker generated with the seed camera, and a second image of the physical marker generated with the second camera.

Abstract: A method for dynamically partitioning a security system is described. A security system identifies sensors registered with the security system. The security system then identifies a first partition attribute of a first group of sensors of the sensors. The first partition attribute indicates a primary partition of the security system. The security system then identifies a second partition attribute of a second group of sensors of the sensors. The second partition attribute indicates a secondary partition of the security system. The security system forms a dynamic partition of the security system based on a combination of the first and second partition attributes.

Abstract: Human or object presence in or absence from a field-of-view of a camera can be achieved by analyzing camera data using a processor inside of or adjacent to the camera itself. In an example, a video signal processing system receives image data from one or more cameras and uses a processing circuit to determine whether a designated object is or is not present at a particular time, during a particular interval, or over a designated sequence of frames. In an example, the designated object can include one or more of a human being, a vehicle, or a parcel. In an example, results of the determination, such as including positive human or object identification, can be used as a trigger for operation of a barrier or access door.

Abstract: A license plate detection and recognition system receives training data comprising images of license plates. The system prepares ground truth data from the training data based predefined parameters. The system trains a first machine learning algorithm based on the ground truth data to generate a license plate detection model. The license plate detection model is configured to detect one or more regions in the images. The one or more regions contains a candidate for a license plate. The LPDR system generates a bounding box for each region. The LPDR system trains a second machine learning algorithm based on the ground truth data and the license plate detection model to generate a license plate recognition model. The license plate recognition model generates a sequence of alphanumeric characters with a level of recognition confidence for the sequence.

Abstract: A method for calibrating a device is described. The device accesses magnetometer data of a magnetometer sensor in the device, and accelerometer data of an accelerometer sensor in the device. The device determines a first position and a second position of the device based on the magnetometer data and the accelerometer data. The device determines a first magnetic vector based on the magnetometer data at the first position of the device, and a second magnetic vector based on the magnetometer data at the second position of the device. The device then assigns the first magnetic vector to the first position of the device, and the second magnetic vector to the second position of the device.

Abstract: A server accesses a security system profile of a first security system. The security system profile identifies a plurality of sensors connected to the first security system. The server identifies a second security system based on at least a first sensor of the plurality of sensors coupled to the first security system. The server then generates a notification sharing profile for the first security system based on the security system profile. The notification sharing profile indicates that the second security system corresponds to the first sensor. A first event triggered by the first sensor causes a first notification to the second security system.

Abstract: An authentication system accesses an image of a face of a user. The face of the user is partially covered by a facial mask. The authentication system detects an area on the facial mask and generates a first identification of the user based on the area on the facial mask. The authentication system also detects an exposed area uncovered by the facial mask on the face of the user and generates a second identification of the user based on the exposed area. The authentication system compares the first identification of the user with the second identification of the user, and authenticates the user based on the comparison.

Abstract: A water detection device (100) may have a water sensor on both a top and bottom of the device. A water sensor circuit (1004,1006,1100, 1101) may be configured to detect water by delivering a signal may be delivered to an electrical contact (1104, 1132), and the presence of water may be determined based upon detection of the signal at the other contact (1106, 1134). The water sensor circuit device (1101) may be configured with a comparator (1116) that uses hysteresis to provide sensitivity to the presence or absence of water. In a battery-powered water sensor, the water detection signal may be delivered as an alternating signal using, e.g., a signal modulator circuit (e.g., an oscillator circuit (1114) and gate (1120) optionally coupled to a wake-sleep controller (1112)) that is coupled to a battery (133), which may avoid oxidation or other forms of ionic corrosion. In some examples, a water detection signal may be recurrently delivered to the first contact (1132) to conserve battery power.

Abstract: The primary purpose of the present invention is to enable devices/machines/systems to perform an optimized video analytics on images and videos. The present invention focuses on detecting, tracking, and classifying objects in a scene. Here, the tracking is performed by comparing objects across at least two frames and then associating the objects based on a cost matrix. Some examples of the objects include, but are not limited to, persons, animals, vehicles, or any other articles or items.

Abstract: A device is configured to be mounted to a planar mounting panel, including, for example, a wall or ceiling of a home or other building. The device includes a housing, a fastener, a dogleg tab and a friction inducing member. The housing is configured to be received in an aperture in the mounting panel and includes a housing aperture. The fastener is disposed in the housing aperture. The dogleg tab is operatively coupled to one end of the fastener. The dogleg tab is configured to be disposed in a retracted position and to be disposed in an engagement position, in which engagement position the dogleg tab is disposed to engage an inside surface of the mounting panel. The friction inducing member is fixedly attached to the housing adjacent the housing aperture and friction-fit to the fastener.

Abstract: Driver and pedestrian safety can be aided by systems and methods to provide identification and classification of objects in a vehicle travel path. Information about classified objects can be shared with a human driver to inform the driver about potentially hazardous conditions, or the information can be interpreted automatically by an operating system of the vehicle. In an example, a camera coupled to a vehicle can receive images from an image sensor. A computer system can use machine learning and neural network-based processing to identify an object present in the images and determine whether the object is a pedestrian. In an example, the computer system can process information from a region of interest in the images that comprises less than an entire field of view in the images.

Abstract: A magnetometer sensor that detects tampering is described. The sensor samples magnetometer data and computes a set of vectors based on the magnetometer data. The sensor detects a tampering of the magnetic sensor based on determining that the set of vectors is outside the reference plane for the magnetometer sensor. The sensor generates a notification to a security system coupled to the magnetometer sensor. The notification indicating the tampering of the magnetometer sensor.

Abstract: An audio firewall system has a microphone that generates audio data. A speech-to-text engine converts the audio data to text data. The text data is parsed for a service wake word and corresponding content data. The service wake word identifies one of a local security system and a remote assistant server. A text-to-speech engine converts the service wake word and the corresponding content data to converted audio data. The converted audio data is provided to the remote assistant server. The content data is provided to the local security system. The audio firewall system receives a response from the remote assistant server or the local security system and outputs an audio signal corresponding to the response.

Abstract: A system for detecting license plates is described. The system receives raw data comprising images of license plates. A base version of a ground truth is prepared based on the raw data, using a generic license plate detection (LPD). The system prepares input data for training a deep learning network. The deep learning network is trained with the prepared input data. A newly trained generic (LPD) is formed using data generated by the existing generic (LPD).

Abstract: A license plate detection and recognition system receives training data comprising images of license plates. The system prepares ground truth data from the training data based predefined parameters. The system trains a first machine learning algorithm based on the ground truth data to generate a license plate detection model. The license plate detection model is configured to detect one or more regions in the images. The one or more regions contains a candidate for a license plate. The LPDR system generates a bounding box for each region. The LPDR system trains a second machine learning algorithm based on the ground truth data and the license plate detection model to generate a license plate recognition model. The license plate recognition model generates a sequence of alphanumeric characters with a level of recognition confidence for the sequence.