Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for generating a placement of a camera. In some implementations, maintaining monitoring information of a property; generating a virtual model of a property; determining an initial placement location for a virtual camera in the virtual model; obtaining image data generated in the virtual model from the virtual camera placed at the initial placement location; analyzing the image data; determining, using the analysis of the image data, whether to identify an updated placement location; and providing the placement location for a physical camera at the property to a device using a result of the determination whether to identify the updated placement location.

Abstract: A computer-implemented method includes obtaining an image of an area of a property from an augmented reality device, identifying the area of the property based on the image obtained from the augmented reality device, determining that the area of the property corresponds to an event at the property or a configuration of a monitoring system of the property, and providing, in response to determining that the area of the property corresponds to the event or the configuration, information that represents the event or the configuration and that is configured to be displayed on the augmented reality device.

Abstract: Methods, systems, and apparatus for ground plane filtering of video events are disclosed. A method includes obtaining a first set of images of a scene from a camera; determining a ground plane from the first set of images of the scene; obtaining a second set of images of the scene after the first set of images of the scene is obtained; determining that movement shown by a group of pixels in the second set of images of the scene satisfies motion criteria; determining that the ground plane corresponds with at least a portion of the group of pixels; and in response to determining that movement shown by the group of pixels in the second set of images of the scene satisfies motion criteria, and that the ground plane corresponds with at least a portion of the group of pixels, classifying the group of pixels as showing ground plane based motion.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for robot navigation. One of the methods includes obtaining one or more images of an area from a robot; detecting two or more lines within the one or more images; identifying at least two of the two or more lines as vanishing lines; determining, using the vanishing lines, a correction maneuver; and controlling the robot to implement the correction maneuver.

Abstract: Methods, systems, and apparatus for camera detection of human activity with co-occurrence are disclosed. A method includes detecting a person in an image captured by a camera; in response to detecting the person in the image, determining optical flow in portions of a first set of images; determining that particular portions of the first set of images satisfy optical flow criteria; in response to determining that the particular portions of the first set of images satisfy optical flow criteria, classifying the particular portions of the first set of images as indicative of human activity; receiving a second set of images captured by the camera after the first set of images; and determining that the second set of images likely shows human activity based on analyzing portions of the second set of images that correspond to the particular portions of the first set of images classified as indicative of human activity.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for fast user enrollment for facial recognition using face clustering. A property monitoring system may reduce user input requirements by automatically performing face clustering, and requesting a user identify face images by cluster. Presenting clusters of faces to a user may allow the user to more quickly indicate multiple face images are of a user, and allow the property monitoring system to prioritize which clusters of faces are to be reviewed by the user. Accordingly, the property monitoring system may reduce processing and requests for user input by clustering faces.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selectively obfuscating audio. One of the methods includes detecting, by a security system for a premises, that a person who was within a threshold area for the premises was likely uttering a sound; determining, using data from one or more sensors, a likelihood that the person was communicating with the security system at the premises; determining whether the likelihood satisfies a threshold likelihood and that the person's voice should not be obfuscated; and in response to determining whether the likelihood satisfies the threshold likelihood and that the person's voice should not be obfuscated, selectively obfuscating the person's voice or maintaining, in memory, an audio signal i) that encodes the person's voice and ii) was captured by a microphone that was physically located at the premises.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predictive video conference actions. One of the methods includes accessing, for a video conference in progress in an area of a property, data indicating activity at the property; predicting, using the data indicating activity at the property, that a video conference interruption is likely to occur; and in response to determining that a video conference interruption is likely to occur, performing one or more actions to reduce a likelihood that the video conference interruption will be presented during the video conference.

Abstract: Systems, devices, and methods for monitoring a person's sleep are described. Thermal images of a person sleeping can be captured using an infrared camera and processed to determine the body temperature of the person. A particular sleep stage and its duration can be determined using the body temperature. In addition, the data obtained from monitoring the person can be used to determine if the person is suffering from one or more sleep disorders or other health problems. In this manner, a person's sleep quantity and quality can be determined in a non-invasive, efficient, and comfortable manner.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for object detection. One of the methods includes determining, using first sensor data, a detection result on whether to trigger an event alerting a presence of an object in a target area by executing one or more models; determining, using second sensor data, a ground truth for the event that indicates whether an object is present in the target area; determining a difference value by comparing the detection result and the ground truth; adjusting at least one parameter of the one or more models in response to determining that the difference value does not satisfy the one or more threshold criteria; and determining a new detection result on whether to trigger a second event by executing the one or more models with adjusted parameters using new first sensor data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for spatial motion attention for intelligent video analytics. One of the methods includes: obtaining an input image of a region; generating a motion image that characterizes a difference between a value of a pixel at the pixel location in the input image and a value of a pixel at the pixel location in the reference image; generating a feature map using the input image; generating, using the motion image and the feature map, a motion enhanced feature map that has, for one or more pixels that likely indicate movement, a first value that a) indicates that the corresponding pixel in the motion enhanced feature map likely indicates movement and b) is different from a second value for a corresponding pixel in the feature map; and analyzing the motion enhanced feature map.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for monitoring extended reality spaces. One of the methods includes determining, for a first extended reality environment generated by a first device, first data defining a first three-dimensional space at a property for the first environment; determining, for a second extended reality environment generated by a second device, second data defining a second three-dimensional space at the property for the second environment; determining whether the first space at least partially overlaps with the second space; in response to determining that the first space at least partially overlaps with the second space, determining that the first space has a higher priority than the second space; in response to determining that the first space has the higher priority than the second space, providing, to the second device, a command to adjust an experience for the second extended reality environment.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for providing targeted notifications. One of the methods includes determining a likely identity of a visitor who arrived at a property that is associated with two or more people, selecting, from the two or more people, a target person using the likely identity of the visitor, and sending, to a device of the target person, a notification that indicates that the visitor arrived at the property.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving multiple images from a camera, each image of the multiple images representative of a detection of an object within the image. For each image of the multiple images the methods include: determining a set of detected objects within the image, each object defined by a respective bounding box, and determining, from the set of detected objects within the image and ground truth labels, a false detection of a first object. The methods further include determining that a target object threshold is met based on a number of false detections of the first object in the multiple images, generating, based on the number of false detections for the first object meeting the target object threshold, an adversarial mask for the first object, and providing, to the camera, the adversarial mask.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for motorized structure integration with augmented and virtual reality. One of the methods includes determining one or more physical objects for use with an extended reality environment; generating, for a physical object from the one or more physical objects, data for a representation of the physical object for use in the extended reality environment; providing, to a user device, at least some of the data for the representation of the physical object to cause the user device to present at least a portion of the representation in the extended reality environment; determining to change a presentation of the representation in the extended reality environment; and in response to determining to change the presentation of the representation, controlling a physical position of the physical object using the change to the presentation of the representation in the extended reality environment.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for consolidation of alerts using a similarity criterion. One of the methods includes: receiving, from a sensor at a property for which a first action in a sequence of actions was detected by a second sensor at the property, data that identifies a second action at the property; determining whether the second action satisfies a similarity criterion for an action in the sequence of actions that define an event at the property; and in response to determining that the second action satisfies the similarity criterion for the action in the sequence of actions that define the event at the property, performing an event operation for the event at the property.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for objection classification. One of the methods includes: obtaining a first set of images of objects that have a likelihood of being at a property that satisfies a likelihood threshold; generating, for each object, a binary classifier from a set of images of the respective object; determining, using at least one of the binary classifiers, that an image of an unknown object was classified as an object from the objects; in response to determining, using the binary classifiers, that the image of the unknown object was classified as an object from the objects, selecting a second set of images of unknown objects that does not include the image; and generating a multiclass classifier for use classifying objects using i) the first set as respective classes and ii) the second set that does not include the image.

Abstract: Methods and systems, including computer-readable media, are described for monitoring presence or absence of an object at a property using local region matching. A system generates images while monitoring an area of the property and, based on the images, detects an object in a region of interest in the area. For each of the images: the system iteratively computes interest points for the object using photometric augmentation applied to the image before each iteration of computing the interest points. A digital representation of the region and the object is generated based on interest points that repeat across the images after each application of the photometric augmentation. Based on the digital representation, a set of anchor points are determined from the interest points that repeat across images. Using the set of anchor points, the system detects an absence or a continued presence of the object in the area of the property.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using dual descriptor data. One of the methods includes: detecting, using a first set of descriptor features included in dual descriptor data, a first representation within first image data collected by a camera; determining a change to an imaging modality of the camera; detecting, using a second set of features included in the dual descriptor data, a second representation within second image data collected by the camera; classifying the first representation and the second representation as associated with a same object using the dual descriptor data; and in response to classifying the first representation and the second representation as associated with the same object using the dual descriptor data, transmitting operational instructions to one or more appliances connected to the system.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for monitoring events using a Virtual Inductive Loop system. In some implementations, image data is obtained from cameras. A region depicted in the obtained image data is identified, the region comprising lines spaced by a distance that satisfies a distance threshold. For each line included in the region: an object depicted crossing the line is determined whether to satisfy a height criteria indicating that the line is activated. In response to determining that an object depicted crossing the line satisfies the height criteria, an event is determined to have likely occurred using data indicating (i) which lines of the lines were activated and (ii) an order in which each of the lines were activated. In response to determining that an event likely occurred, actions are performed using at least some of the data.