Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for false detection removal using adversarial masks. The method includes performing object detection on a first image that includes a first region using a detection model determining the detection model incorrectly classified the first region of the first image; generating an adversarial mask based on the first region of the first image and the detection model; obtaining a second image that includes the first region; generating a masked image based on the second image and the adversarial mask; and performing object detection on the masked image including the first region using the detection model.

Abstract: Methods, systems, an apparatus, including computer programs encoded on a storage device, for tracking human movement in video images. A method includes obtaining a first image of a scene captured by a camera; identifying a bounding box around a human detected in the first image; determining a scale amount that corresponds to a size of the bounding box; obtaining a second image of the scene captured by the camera after the first image was captured; and detecting the human in the second image based on both the first image scaled by the scale amount and the second image scaled by the scale amount. Detecting the human in the second image can include identifying a second scaled bounding box around the human detected in the second image scaled by the scale amount.

Abstract: Methods and systems, including computer programs encoded on a storage medium, are described for implementing item monitoring using a doorbell camera. A system generates an input video stream that has image frames corresponding to detection of activity at a property. Timing information is generated for the video stream and includes a timestamp for each image frame of the stream. Using the timing information, the system processes a pre-event image frame that precedes detection of the activity and a post-event image frame that coincides with detection of the activity. An image score is computed with respect to placement of a candidate item at the property in response to processing the pre-event and post-event image frames. The image score is used to determine that a first item was delivered to the property or that a second item was removed after being delivered to the property.

Abstract: A device for detecting and alleviating flooding and blocked storm sewers includes a manhole cover coupled to a float body. The device also includes a canister having a drain hole and a valve. The device also includes multiple guides that can catch onto part of a sewer. The device is configured such that when water flows into the canister, the manhole cover, float body, and guides rise and the valve is opened.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, are described for implementing a smart security fastener. The smart security fastener includes a body configured to be installed at a property; and a head that is supported by the body. The head has circuitry that includes: a micro-processor that generates control signals; and a radio device that is coupled to the micro-processor. The radio device is operable to: i) transmit data to a property monitoring system based on the control signals, where the data indicates an installation status of the smart security fastener; and ii) receive a command from the property monitoring system that indicates authorization to uninstall the smart security fastener. The circuitry also includes a power source that powers each of the micro-processor and the radio device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for tracking objects of interest using distance-based thresholding. One of the methods includes detecting an object depicted in an image captured by a camera, determining a predicted physical distance between the object and the camera, selecting, from a plurality of predetermined confidence thresholds, a confidence threshold for the predicted physical distance, each confidence threshold in the plurality of predetermined confidence thresholds for a different physical distance range, the confidence threshold having a physical distance range that includes the predicted physical distance, and determining, using the confidence threshold and a confidence score that indicates a likelihood that the object is an object of interest, that the object is likely an object of interest.

Abstract: Methods and systems for image-based abnormal event detection are disclosed. An example method includes obtaining a sequential set of images captured by a camera; generating a set of observed features for each of the images; generating a set of predicted features based on a portion of the sets of observed features that excludes the set of observed features for a last image in the sequential set of images; determining that a difference between the set of predicted features and the set of observed features for the last image in the sequential set of images satisfies abnormal event criteria; and in response to determining that the difference between the set of predicted features and the set of observed features for the last image in the sequential set of images satisfies abnormal event criteria, classifying the set of sequential images as showing an abnormal event.

Abstract: Methods, systems, and apparatus for removing precipitation from video are disclosed. A method includes generating, from a first set of images of a scene from a camera, a segmented background image model of the scene; obtaining a second set of images from the camera; identifying, in an image of the second set of images, a plurality of edges, determining that a first edge of the plurality of edges satisfies criteria for representing precipitation based at least in part on determining that the first edge (i) does not correspond to the background image model of the scene and (ii) extends into two or more contiguous segments of the scene; in response, classifying each of the contiguous segments as a precipitation segment; generating pixel data for each of the precipitation segments; and applying the pixel data to each precipitation segment in the image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for emphasizing a portion of audio data. In some implementations, a method may include determining that a first person is wearing a hearing aid, determining, from images captured by a camera, that a second person is speaking to the first person, determining an audio stream for an environment in which the first person is located, determining whether more than one sound stream is encoded in the audio stream, based on determining that more than one sound stream is encoded in audio data, identifying a portion of captured sounds that corresponds to the second person speaking to the first person, and providing, to the hearing aid, audio data that increases a volume of the portion of captured sounds relative to other portions of the captured sounds.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reducing a likelihood that a doorbell might be used. One of the methods includes determining that a visitor arrived at a premises; determining that the visitor used a computing device at a first time; determining that a user device of a person of the premises received a message at a second time; determining that the first time and the second time both satisfy a timing criteria; and in response to determining that the first time and the second time both satisfy the timing criteria, sending, to the user device, a notification that indicates that the visitor arrived at the premises.

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 a computer storage medium, are described for implementing intelligent seating for wellness monitoring. A system obtains data from a first sensor integrated in an intelligent seating apparatus at a property. The first data indicates a potential abnormal condition of a person at the property. The system determines that the person has an abnormal condition based on the first data corresponding to the person having used the seating apparatus. Based on the abnormal condition, the system provides an indication to a client device of the person to prompt the person to adjust their use of the seating apparatus. The system also obtains visual indications of the abnormal condition, determines the type of abnormal condition afflicting the person, and determines a wellness command with instructions for alleviating the abnormal condition. The wellness command is provided for display on the client device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for tracking moving objects depicted in multiple images. One of the methods includes determining, for an image captured by a camera, a first bounding box that represents a first moving object depicted in the image, determining that the first bounding box and a second bounding box overlap in an overlap area, determining that the first moving object represented by the first bounding box was farther from the camera that captured the image than a second moving object represented by the second bounding box, generating a mask for the first bounding box based on the overlap area, and determining, using data from the image that is associated with the mask, that the first moving object matches an appearance of another moving object depicted in another image captured by the camera.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for integrating a monitoring system with one or more air quality sensors. The method includes obtaining a request that includes an indication of an appearance of an object, selecting a first set of images in an initial modality based on the indication of the appearance of the object, determining an additional set of images in a different modality based on mappings between the first set of images and the additional set of images; and providing the first set of images and the additional set of images in response to the request.

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 collecting activity data from one or more devices in a home network, generating a graph-based knowledge base including two or more nodes based on the activity data, where each node is an object, person, or routine and wherein each link is a relationship between two nodes, generating, based on the graph-based knowledge base, one or more rules, determining, based in part on the activity data, an occurrence of a particular rule of the one or more rules, generating a notification responsive to the particular rule, presenting the notification to a user, receiving, user feedback responsive to the notification, where the user feedback includes a natural language label for the particular rule, and updating the particular rule based on the user feedback.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an event detector. The methods, systems, and apparatus include actions of obtaining frames of a video, determining whether an object of interest is detected within the frames, determining whether motion is detected within the frames, determining whether the frames correspond to motion by an object of interest, generating a training set that includes labeled inter-frame differences based on whether the frames correspond to motion by an object of interest, and training an event detector using the training set.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for finding lost objects. In some implementations, a video frame is displayed. An input drawing a shape around an area of the video frame is received. A second video frame is displayed. An indication of the shape in the second video frame is displayed. An input to adjust the shape such that the shape is drawn around a second area is received.

Abstract: Methods, systems, an apparatus, including computer programs encoded on a storage device, for training an image classifier. A method includes receiving an image that includes a depiction of an object; generating a set of poorly localized bounding boxes; and generating a set of accurately localized bounding boxes. The method includes training, at a first learning rate and using the poorly localized bounding boxes, an object classifier to classify the object; and training, at a second learning rate that is lower than the first learning rate, and using the accurately localized bounding boxes, the object classifier to classify the object. The method includes receiving a second image that includes a depiction of an object; and providing, to the trained object classifier, the second image. The method includes receiving an indication that the object classifier classified the object in the second image; and performing one or more actions.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for managing virtual surveillance windows for video surveillance. The methods, systems, and apparatus include actions of obtaining an original video, generating a downscaled video from the original video, detecting a first event at a location from the downscaled video using a first classifier, generating a windowed video from the original video based on the location, detecting a second event from the windowed video, and performing an action in response to detecting the second event.

Abstract: Methods, systems, an apparatus, including computer programs encoded on a storage device, for tracking human movement in video images. A method includes obtaining a first image of a scene captured by a camera; identifying a bounding box around a human detected in the first image; determining a scale amount that corresponds to a size of the bounding box; obtaining a second image of the scene captured by the camera after the first image was captured; and detecting the human in the second image based on both the first image scaled by the scale amount and the second image scaled by the scale amount. Detecting the human in the second image can include identifying a second scaled bounding box around the human detected in the second image scaled by the scale amount.