Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using feature descriptors to track objects depicted in images. One of the methods includes receiving hue, saturation, value data for an image and data that indicates an object detected in the image, generating a feature descriptor that includes hue data and saturation data, determining, for each of two or more tracked objects that each have a historical feature descriptor that includes historical hue data and historical saturation data, a distance between (i) the respective historical feature descriptor and (ii) the feature descriptor, associating the feature descriptor for the object with a tracked object from the two or more tracked objects, and tracking the tracked object in one or more images from a video sequence using the feature descriptor and the historical feature descriptor.

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: 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 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, systems, and apparatus, including computer programs encoded on computer storage media, for real-motion prediction. One of the methods includes: providing, as an input to a machine learning model, image frames of a scene for which the image frames were captured over a period of time; obtaining, as an output from the machine learning model, a temporally aggregated optical flow signature that includes a two-dimensional (2D) motion vector for a plurality of locations in the image frames of the scene; detecting, using the temporally aggregated optical flow signature, a real-motion event by comparing a magnitude of each 2D motion vector with a threshold; and performing an action for the real-motion event in response to detecting the real-motion 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 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 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 estimating a robot pose. One of the methods includes the actions of obtaining two or more images captured at two or more locations on a property; detecting feature points at positions within two or more images including first feature points in the first image and second feature points in the second image; comparing the positions of the first feature points in the first image to positions of the second feature points in the second image; obtaining data indicating the two or more locations on the property; comparing the two or more locations; and generating depth data for the feature points for use by a robot navigating the property.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for obtaining a sample Light Detection and Ranging (LIDAR) profile generated by a drone; selecting a reference position based on the sample LIDAR profile; determining a LIDAR profile-based translation and rotation relative to a reference LIDAR profile of the reference position; determining an image-based translation and rotation relative to a reference image of the reference position; determining whether the LIDAR profile-based translation and rotation and the image-based translation and rotation satisfy a similarity threshold; and verifying, using a result of the determination, a predicted position of the drone.

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, 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 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 feature selection for object tracking. One of the methods includes: obtaining first feature points of an object in a first image of a scene captured by a camera; obtaining a second image of the scene captured by the camera after the first image was captured; determining whether a motion prediction of the object is available that indicates an area of the second image where the object is likely located; in response to determining that the motion prediction of the object is available, identifying, in the area of the second image where the object is likely located, second feature points that satisfy a similarity threshold for the first feature points in the first image; and detecting the object in the second image using the identified second feature points.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting packages delivering in the camera's blindspot. One of the methods includes detecting, using one or more images captured by a camera at a property, movement in an area of interest i) at the property, ii) that is included in a field of view of the camera and iii) was generated using historical data for packages delivered to the property; determining, using the detected movement in the area of interest, that a package was likely delivered; and in response to determining that the package was likely delivered, performing one or more automated actions for the package.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for exemplar generation and localization. In some implementations, a method includes obtaining sensor data from a robot traversing a route at a property; determining sampling rates along the route using the sensor data obtained from the robot; selecting images from the sensor data as exemplars for robot localization using the sampling rates along the route; determining that a second robot is in a localization phase at the property; and providing representations of the exemplars for robot localization to the second robot.

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.

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 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: Disclosed are methods, systems, and apparatus for adjusting areas of interest for motion detection in camera scenes. A method includes obtaining a map of false motion event detections using a first area of interest; identifying an overlap area between the map of false detections and the first area of interest; determining a second area of interest that includes portions of the first area of interest and excludes at least a part of the overlap area; obtaining a map of true motion event detections using the first area of interest; determining whether true detections using the second area of interest compared to true detections using the first area of interest satisfies performance criteria; and in response to determining that true detections using the second area of interest compared to true detections using the first area of interest satisfies performance criteria, providing the second area of interest for use in detecting events.