Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for monitoring air quality with multiple sensing devices. The methods, systems, and apparatus include actions of: obtaining first sensor data from a sensor that is not an air quality sensor, determining that the first sensor data satisfy a first air quality criterion, in response to determining that the first sensor data satisfy the first air quality criterion, obtaining second sensor data from an air quality sensor, determining that the second sensor data satisfy a second air quality criterion, and based on a determination that the second sensor data satisfy the second air quality criterion, activating an air quality device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for machine learning for home understanding and notification. In one aspect, a method includes obtaining reference videos from a camera within a premises of a home, determining, from the reference videos, timing of actions in a routine that a particular person performs before leaving the home, determining from a sample video from the camera within the home that the particular person appears to be out of sync in performing a particular action based on the timing of actions in the routine determined from the reference videos, and in response, providing a notification to the particular person.

Abstract: Systems and techniques are described for monitoring energy use habits of consumers. In some implementations, a method includes obtaining temperature data from a monitored property. An energy model of the monitored property is generated based on the obtained temperature data. The current temperature data is obtained from the monitored property. The current temperature data is provided to the generated energy model to generate a duty-cycle for turning an HVAC system of the monitored property off an on during the on-peak hours. The HVAC system of the monitored property is instructed to cycle off and on during the on-peak hours based on the generated duty-cycle.

Abstract: Systems and techniques are provided for charging devices at a property using battery-charging drones. In some implementations, a monitoring system is configured to monitor a property and includes a battery-powered sensor configured to generate sensor data. The system includes a drone that is configured to navigate the property and charge the battery-powered sensor. A monitor control unit is configured to obtain a battery level from the battery-powered sensor and compare the battery level to a battery level threshold. Based on the comparison, the monitor control unit determines that the battery level does not satisfy the threshold. Based on the determination, the monitor control unit generates and transmits an instruction to a drone for the drone to navigate to the battery-powered sensor and charge a battery of the battery-powered sensor. The monitor control unit receives data from the drone that indicates whether the drone charged the battery of the sensor.

Abstract: Techniques are described for tracking intruders of a monitored property by the unique identifying characteristics or “digital fingerprints” of electronic devices carried by the intruders. A system detects an alarm event at a monitored property based on output from at least one sensor located at the monitored property. In response to detecting the alarm event at the monitored property, the system initiates a process to gather electronic identifiers for mobile electronic devices located within the monitored property at a time corresponding to the detected alarm event. The system determines electronic identifiers for the mobile electronic devices located within the monitored property at a time corresponding to the detected alarm event. The system stores in electronic storage, information indicating the determined electronic identifiers for the mobile electronic devices located within the monitored property at a time corresponding to the detected alarm event.

Abstract: Techniques are described for configuring a monitoring system to assist users during a detected emergency condition at a property. In some implementations, sensor data from one or more sensors that are located at the property are obtained by a monitoring system that is configured to monitor the property. A determination that there is an emergency condition at the property is made by the monitoring system based on the sensor data, determining. A location of a person inside the property is determined by the monitoring system based on the sensor data. A first path to the person and a second path to guide the person away from the emergency condition are determined by the monitoring system. The first path to the person and the second path to guide the person away from the emergency condition are navigated by a computing device of the monitoring system.

Abstract: A security system can perform a systematic test to generate a visualization of the security camera coverage for an area. The test can be performed using a network of security cameras, a central system, and a mapping entity. The mapping entity may hold or be attached to a sign with a pattern. The mapping entity can move the sign from one location to another throughout a zone to be mapped. At each location, the mapping entity may send a message with the coordinate of its current position and optionally the pattern it is carrying to the central system.

Abstract: In some implementations, systems and techniques are described to automatically unlock a front door of a property in response to detecting an alarm signal indicating an emergency at or near a property. Data indicating occurrence of an emergency condition at a property is initially obtained. A lock configuration for an electronic lock of the property is determined. An unlock instruction is generated for the electronic lock based on the determined lock configuration for the electronic lock. The unlock instruction is transmitted to the electronic lock such that, when the unlock instruction is received by the electronic lock, the electronic lock is unlocked according to the unlock instruction.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a storage device, for using a drone to monitor a community. The drone may include a processor and a storage device storing instructions that, when executed by the processor, cause the one or more processors to perform operations. The operations may include receiving an instruction to deploy based on a determination, by a community monitoring system that an event was detected at a property of the community, navigating towards the property along an initial navigation path, obtaining local monitoring system data from a local monitoring system of a property of the community, generating based on the local monitoring system data a navigational model that identifies a location of each of one or more surveillance objectives, determining an adjusted navigation path to a location of a surveillance objective of the one or more surveillance objectives, and navigating along the adjusted navigation path.

Abstract: A method is described that determines that a replacement node device has been connected to a mesh network, the replacement node device corresponding to an original node that has been removed from the mesh network. In response to determining that the replacement node device has been connected to the mesh network, network topology data is accessed that specifies one or more data routing configurations that are each associated with a node device included in the mesh network. From among the one or more data routing configurations specified by the network topology data, a particular data routing configuration is identified that is associated with the original node device that has been removed from the mesh network. Data that specifies the particular data routing configuration that is associated with the original node device that has been removed from the mesh network is provided to the replacement node device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for adjusting of video analytics rules for camera movement. The methods, systems, and apparatus include actions of obtaining a rule that specifies a first set of coordinates applied to a first set of images from a camera, determining an amount and direction of movement of the camera after the rule was obtained, determining, based on the amount and direction of movement of the camera, a second set of coordinates applied to a second set of images captured after the camera moved.

Abstract: A system and method provide for the immediate transmission of a potential alarm to a remote alarm signal escrow site and from the escrow site to a host station in the event where a control panel or an alarm signaling device is tampered with or destroyed by a disablement tactic, e.g., a “crash and smash intrusion.” A system and method may also send an alarm signal during such an attack by using predictive analysis of real-time events.

Abstract: A circuit for direct current (DC) offset estimation comprises a quantile value circuit and a signal processor. The quantile value circuit determines a plurality of quantile values of an input signal and includes a plurality of quantile filters. Each quantile filter includes a comparator, a level shifter, a monotonic transfer function component, and a latched integrator. The comparator compares the input signal and a quantile value. The level shifter shifts the output of the comparator. The monotonic transfer function component determines the magnitude of the shifted signal and provide a transfer function signal. The latched integrator suppresses transient characteristics of the transfer function signal and provide the quantile value. The signal processor is configured to calculate a weighted average of the quantile values to yield a DC offset estimate.

Abstract: Systems and techniques are described for pet monitoring during unattended delivery. In some implementations, a monitoring system monitors a property includes sensors located throughout the property and generates sensor data. A monitor control unit receives a first indication that a resident of the property will be receiving a delivery during a delivery time. Based on the sensor data and during the delivery time, the monitor control unit determines that a pet, that resides at the property, has been restrained. The monitor control unit provides, to a delivery person, a second indication that the pet at the property has been restrained.

Abstract: A computer implemented method includes receiving one or more user set preferences for detecting a hub alarm condition and one or more actions to perform in response to detecting a hub alarm condition, receiving, from the output of the security panel, data indicating that a traditional alarm condition occurred, based on receiving data indicating a traditional alarm condition occurred at the monitored property, receiving sensor data from at least one wireless sensor in a vicinity of a hardwired sensor associated with the traditional alarm condition, determining, based on the sensor data received from at least one wireless sensor in a vicinity of the hardwired sensor associated the traditional alarm condition, that the sensor data satisfies a condition, and in response to determining that the sensor data satisfies a condition, performing an action.

Abstract: Techniques are described for assisted creation of video rules via scene analysis. In some implementations, a scene is obtained, a shape of an element in a ground plane shown in the images of the scene is identified, user input that defines a shape of a region of interest used in a video rule is obtained, that the shape of the region satisfies a reshape criteria based on the shape of the element in the ground plane shown in the images of the scene is determined, and a reshaped region based on the shape of the element in the ground plane shown in the images of the scene is determined.

Abstract: Methods, systems, and apparatus a drone for installing sensors. A method includes determining to emulate a view of a camera at a particular location with a drone, deploying the drone to the particular location, obtaining an image captured by a drone, and emulating the view of the camera with the image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for enhanced property access with video analytics. In some implementations, images of a first area captured by a camera are obtained. A number of persons in the first area is determined from the images. Data indicating one or more unique identifications is received. A number of persons who are authorized to access a second area are determined. Access is provided to the second area.

Abstract: A monitoring system that is configured to monitor a property includes a connected scale device that is configured to receive a package, determine a weight of the package, and after determining the weight of the package, arm the connected scale device, and a monitoring control unit that is configured to receive, from the connected scale device, data indicating that the connected scale device received the package and the connected scale device is armed, and based on receiving the data indicating that the connected scale device received the package and the connected scale device is armed, communicate, to a user device of a resident of the property, a notification indicating that the connected scale device received the package.

Abstract: Techniques are described for using sensor data derived from a monitoring system to drive personalized content. Sensor data captured by a monitoring system may be used to determine attributes of users of the monitoring system and/or attributes of a property monitored by the monitoring system. The determined attributes may be used to select content to present to users of the monitoring system. Content presentation may be made through the monitoring system and may be triggered based on events detected by the monitoring system.