Abstract: A process classifies objects in a scene. The process receives a captured IR image of a scene taken by a 2-dimensional image sensor array of a camera system while one or more IR illuminators of the camera system are emitting IR light, thereby forming an IR intensity map of the scene with a respective intensity value determined for each pixel of the IR image. The process uses the IR intensity map to identify a plurality of pixels whose corresponding intensity values are within a predefined intensity range, and clusters the identified plurality of pixels into one or more regions that are substantially contiguous. The process determines that a first region of the one or more regions corresponds to a specific material based, at least in part, on the intensity values of the pixels in the first region. The process then stores information in the memory that identifies the first region.

Abstract: Systems and methods of a security system are provided, including detecting, by a sensor, a sound event, and selecting, by a processor coupled to the sensor, at least a portion of sound data captured by the sensor that corresponds to at least one sound feature of the detected sound event. The systems and methods include classifying the at least one sound feature into one or more sound categories, and determining, by a processor, based upon a database of home-specific sound data, whether the at least one sound feature is a human-generated sound. A notification can be transmitted to a computing device according to the sound event.

Abstract: This application discloses a method implemented by an electronic device to detect a signature event (e.g., a baby cry event) associated with an audio feature (e.g., baby sound). The electronic device obtains a classifier model from a remote server. The classifier model is determined according to predetermined capabilities of the electronic device and ambient sound characteristics of the electronic device, and distinguishes the audio feature from a plurality of alternative features and ambient noises. When the electronic device obtains audio data, it splits the audio data to a plurality of sound components each associated with a respective frequency or frequency band and including a series of time windows. The electronic device further extracts a feature vector from the sound components, classifies the extracted feature vector to obtain a probability value according to the classifier model, and detects the signature event based on the probability value.

Abstract: A camera system includes memory, a lens assembly arranged to direct light from a scene onto an image sensing element, an image sensing element configured to receive light from the scene via the lens assembly, at least one infrared illuminator configured to transmit infrared light, and a processor, coupled to the image sensing element and the illuminators. The processor is configured to operate the illuminators and the image sensing element in a first mode whereby infrared light transmitted by the illuminators and reflected from the scene is used to generate a two-dimensional image of the scene. The processor is also configured to operate the illuminators and the image sensing element in a second mode whereby infrared light transmitted by the illuminators and reflected from the scene is used to detect a first region, located within the scene, having a specific material.

Abstract: A camera system includes memory, a lens assembly to direct light from a scene onto an image sensing element, an image sensing element configured to receive light from the scene via the lens assembly, at least one infrared illuminator configured to transmit infrared light, and a processor, coupled to the image sensing element and the at least one infrared illuminator. The processor is configured to operate the illuminators and the image sensing element in a first mode whereby infrared light transmitted by the illuminators and reflected from the scene is used to generate a two-dimensional image of the scene. The processor is also configured to operate the illuminators and the image sensing element in a second mode whereby infrared light transmitted by the illuminators and reflected from the scene is used to identify a planar surface in the scene.

Abstract: A process reduces false positive security alerts. The process is performed at a computing device having one or more processors, and memory storing one or more programs configured for execution by the one or more processors. The process computes a depth map for a scene monitored by a video camera using a plurality of IR images captured by the video camera and uses the depth map to identify a first region within the scene having historically above average false positive detected motion events. In some instances, the first region is a ceiling, a window, or a television. The process monitors a video stream provided by the video camera to identify motion events, excluding the first region, and generates a motion alert when there is detected motion in the scene outside of the first region and the detected motion satisfies threshold criteria.

Abstract: A process identifies large planar surfaces in scenes. The process receives captured IR images of a scene taken by a 2-dimensional array of image sensors of a camera system. Each IR image is captured when a distinct subset of IR illuminators of the camera system is illuminated. The process constructs a depth map of a scene using IR images and uses the depth map to compute a binary depth edge map for the scene. The binary depth edge map identifies which points in the depth map comprise depth discontinuities. The process identifies contiguous components based on the binary depth edge map and determines that a first component of the contiguous components represents a large planar surface in the scene by: fitting a plane to points in the first component; determining the orientation of the plane; and determining that the plane fitting residual error is less than a predefined threshold.

Abstract: A process classifies objects in a scene. The process receives a captured IR image of a scene taken by a 2-dimensional image sensor array of a camera system while one or more IR illuminators of the camera system are emitting IR light, thereby forming an IR intensity map of the scene with a respective intensity value determined for each pixel of the IR image. The process uses the IR intensity map to identify a plurality of pixels whose corresponding intensity values are within a predefined intensity range, and clusters the identified plurality of pixels into one or more regions that are substantially contiguous. The process determines that a first region of the one or more regions corresponds to a specific material based, at least in part, on the intensity values of the pixels in the first region. The process then stores information in the memory that identifies the first region.

Abstract: A process estimates height and tilt of a camera having an image sensor array and IR illuminators. The process identifies multiple distinct subsets of the illuminators. For multiple heights and tilts, the process constructs dictionary entries that correspond to the camera having the height and tilt above a floor. Each entry includes light intensity values for pixels in images corresponding to activating each of the subsets of illuminators. For each of the subsets, the process receives an image of a scene captured while the subset is emitting light and the other illuminators are not. The process uses the captured images to identify a floor region corresponding to a floor in the scene. The process forms a vector including pixels from the captured images in the identified floor region and estimates the height and tilt of the camera by comparing the vector to the dictionary entries.

Abstract: A system and method for the use of sensors and processors of existing, distributed systems, operating individually or in cooperation with other systems, networks or cloud-based services to enhance the detection and classification of sound events in an environment (e.g., a home), while having low computational complexity. The system and method provides functions where the most relevant features that help in discriminating sounds are extracted from an audio signal and then classified depending on whether the extracted features correspond to a sound event that should result in a communication to a user. Threshold values and other variables can be determined by training on audio signals of known sounds in defined environments, and implemented to distinguish human and pet sounds from other sounds, and compensate for variations in the magnitude of the audio signal, different sizes and reverberation characteristics of the environment, and variations in microphone responses.

Abstract: A particular smart hazard detector may itself function as a guide during a process of installation of the same at an installation location. Additionally, the installation location of the particular smart hazard detector may play a central role in how various settings of the smart hazard detector are defined and adjusted over time.

Abstract: Systems and methods for exchanging a data stream of information that varies over time using a message format. The message format includes a version field that indicates a version of a structure of the message format. The message format also includes one or more resources fields that each identifies a resource to be imported into the data stream exchanging the data stream. Moreover, the message format includes one or more records that represent time-variant data samples being exchanged in the message. Furthermore, the message format includes one or more descriptor fields, wherein each descriptor field corresponds to at least one respective record of the one or more records and contains metadata describing data contained within the at least one record.

Abstract: A method and system for optically detecting a user. A sequence of patterns of radiation reflected from an object in a room may be captured by a device. The patterns of radiation may be infrared radiation emitted from the device. A sequence of variations between the captured sequence of patterns of radiation and the emitted sequence of patterns of radiation may be determined and object characteristics of an object may be determined based upon the sequence of variations. The object characteristics may be a sequence of dimensions of the object and a sequence of locations of the object. The method may determine the first is a user based upon the determined object characteristics and a room profile. The room profile may include a plurality of object characteristics of one or more objects in the room.

Abstract: Systems and techniques are provided for dynamic volume adjustment. A signal including a detected distance to a person may be received from a proximity sensor of a smart home environment. A volume adjustment for a speaker of the smart home environment may be generated based on the detected distance to the person and a sound level associated with the detected distance to the person. The volume of the speaker may be adjusted based on the volume adjustment. A signal from a sensor of the smart home environment indicating that the sensor has been tripped may be received. The proximity sensor may be triggered based on the received signal indicating the sensor has been tripped to detect a distance to the person to generate the detected distance. An alarm may be sounded through the speaker.

Abstract: A system and method for automatic path light control based on a detected size and classification of motion around the device using passive infrared (PIR) sensor technologies and distributed classification algorithms, and on detected light levels in and around the path area using ambient light sensor (ALS) technologies. By using such sensor data, the path light does not need to be maintained at a fixed value, which may be inadequate or inefficient at times, nor require constant user adjustments. Implementations of the disclosed subject matter enable automatic path light control that can be dynamic and automatically adjusted to fit the environment, the current user characteristics and the current user movements through the environment.

Abstract: Hazard detection systems and methods according to embodiments described herein are operative to enable a user to interface with the hazard detection system by performing a touchless gesture. The touchless gesture can be performed in a vicinity of the hazard detection system without requiring physical access to the hazard detection system. This enables the user to interact with the hazard detection system even if it is out of reach. The hazard detection system can detect gestures and perform an appropriate action responsive to the detected gesture. In one embodiment, the hazard detection system can silence its audible alarm or pre-emptively turn off its audible alarm in response to a detected gesture. Gestures can be detected by processing sensor data to determine whether periodic shapes are detected.

Abstract: Systems and methods for exchanging a data stream of information that varies over time using a message format. The message format includes a version field that indicates a version of a structure of the message format. The message format also includes one or more resources fields that each identifies a resource to be imported into the data stream exchanging the data stream. Moreover, the message format includes one or more records that represent time-variant data samples being exchanged in the message. Furthermore, the message format includes one or more descriptor fields, wherein each descriptor field corresponds to at least one respective record of the one or more records and contains metadata describing data contained within the at least one record.

Abstract: A web page or group of pages can be automatically generated based on images selected by a user. The images are analyzed for color and groups of colors for the page background and image framing are determined. Images are analyzed to determine the shapes of the images and the images are placed within appropriate shapes on a page on the web. Click-through rate can be estimated for images and this click-through rate used during the web page generation. Important sections are evaluated in the images and cropping may occur for the images on a page. Text and video can be part of the web page. Software applications can be accessed from the web page as well. The online web pages can be tailored for presentation on a mobile device.

Abstract: Systems and techniques are provided for blocked sensor detection and notification. A signal may be received from a sensor. The sensor may be determined to be producing anomalous output based on checking the signal from the sensor against a signal from a second sensor on the same sensor device as the sensor, checking the signal from the sensor against signals from sensors on additional sensor devices, and checking the signal from the sensor against a slow temporal model for the sensor. In response to the determination that the sensor is producing anomalous output, a notification may be generated indicating the sensor is producing anomalous output, and a confidence level in the sensor may be degraded.

Abstract: A method for adaptively adjusting a threshold used to detect the presence of a living being may include receiving a first set of sensor measurements acquired by a passive infrared (PIR) sensor during a time period when the living being is not expected to be present in a space monitored by the PIR sensor. Here, the sensor measurements may depend on one or more noise sensitivity characteristics of the PIR sensor. The method may include adjusting a threshold that may indicate a presence of the living being based on the first set of sensor measurements. The method may then receive a second set of sensor measurements acquired by the PIR sensor and detect the presence of the living being when at least one of the second set of sensor measurements exceeds the threshold.