Abstract: An imaging system is provided comprising: a memory storing instructions which, when executed by processing circuitry, cause the processing circuitry to perform operations comprising: determining multiple image regions of interest (ROIs) within a camera image plane that correspond to one or more three-dimensional (3D) world object images; determining multiple radar ROIs that correspond to one or more 3D world objects; determining 3D world distances corresponding to the radar ROIs; determining multiple co-registered ROI pairs by co-registering individual image ROIs with individual radar ROIs corresponding to common 3D world objects; adjusting one or more parameters associated with the camera, based upon the co-registered ROI pairs.

Abstract: An imaging system is provided comprising: a memory storing instructions which, when executed by processing circuitry, cause the processing circuitry to perform operations comprising: determining multiple image regions of interest (ROIs) within a camera image plane that correspond to one or more three-dimensional (3D) world object images; determining multiple radar ROIs that correspond to one or more 3D world objects; determining 3D world distances corresponding to the radar ROIs; determining multiple co-registered ROI pairs by co-registering individual image ROIs with individual radar ROIs corresponding to common 3D world objects; adjusting one or more parameters associated with the camera, based upon the co-registered ROI pairs.

Abstract: This application describes techniques for providing computer vision for manual services. In some instances, a remote system may determine that a current time is within a threshold period of time of a scheduled service and, based on the determination, send a first message requesting image data to a camera apparatus located within an environment. After sending the first message, the remote system may receive image data associated with the environment from the camera apparatus and use the image to detect an object within the environment. The remote system can then send a second message to a device of a guest and a third message to a device of a user, where each of the second message and the third message indicates that the object is within the environment. In some instances, the object can include an animal while in some instances, the object can include a person.

Abstract: A sensor system comprising multiple sensor units non-collocated at a site; processing circuitry operatively coupled to memory is configured to perform operations comprising: producing sensor unit tracks, each sensor unit track comprising one or more object attributes including relative object location attributes and non-location attributes; for each sensor unit track, translating the one or more relative object location attributes of the sensor unit track, to one or more universal object location attributes; fusing sets of sensor unit tracks, based at least in part upon corresponding object attributes of the sets of sensor unit tracks, to produce unified site tracks that include the corresponding object attributes; and saving the unified site tracks in a non-transitory storage device.

Abstract: A method of classifying motion from video frames involves generating motion frames indicative of changes in pixel values between pairs of frames. The method also involves determining one-dimensional feature values based on the video frames or motion frames, such as the statistical values or linear transformation coefficients. Each one-dimensional feature value may be stored in a buffer, from which additional temporal feature values can be extracted indicative of the change of the one-dimensional feature values across a set of frames. A classifier may receive the one-dimensional feature values and the additional temporal feature values as inputs, and determine the class of motion present in the video frames. Some classes of motion, such as irrelevant motion, may be considered irrelevant to the execution of certain motion-triggered actions, such that the method may involve suppressing the performance of a motion-triggered action based on the determined class of motion.

Abstract: A system is provided that learns a radar scene's background and that filters radar tracks determined to be in the radar scene background; The system including processing circuitry configured with executable instructions to accesses radar tracks that include radar measurements; to use the measurements to determine a persistent radar object in a radar scene background; and to subsequently filter accessed radar tracks having locations within the radar scene background.

Abstract: An imaging system is provided comprising: a memory storing instructions which, when executed by processing circuitry, cause the processing circuitry to perform operations comprising: determining multiple image regions of interest (ROIs) within a camera image plane that correspond to one or more three-dimensional (3D) world object images; determining multiple radar ROIs that correspond to one or more 3D world objects; determining 3D world distances corresponding to the radar ROIs; determining multiple co-registered ROI pairs by co-registering individual image ROIs with individual radar ROIs corresponding to common 3D world objects; adjusting one or more parameters associated with the camera, based upon the co-registered ROI pairs.

Abstract: Techniques are generally described for object detection in image data. A first frame of image data associated with a first domain is received by a detector executing on at least one computing device. The detector generates a first feature data in the first domain. The first feature data is transformed from the first domain into a second feature data in a second domain. The detector may be effective to detect objects in the second domain. A location of an object in the first frame of image data is determined based at least in part on the second feature data.

Abstract: Systems and methods for smart device control using radar are disclosed. According to some aspects, a machine receives, using a millimeter-wave multiple antenna array, a radar signal. The machine preprocesses the radar signal to generate radar metadata. The machine determines, using a trained machine learning engine and based on at least the radar metadata, a moving entity and a movement type. The machine identifies, based on at least the determined moving entity and the determined movement type, a smart device and an action for the smart device to take in response to the movement type by the moving entity. The machine transmits, to the smart device, a control signal for the identified action.

Abstract: Techniques are generally described for suppressing video streaming based on trajectory information. First video data captured at a first time may be received from a first camera device. A determination may be made that the first video data includes image data representing a previously-identified human. A determination may be made that first trajectory data associates movement of the previously-identified human with the first camera device at the first time. A signal may be sent to a second camera device. The signal may be effective to suppress streaming of video captured by the second camera device during a second time following the first time.

Abstract: A computer-implemented method includes receiving data including a plurality of objects. The data includes, for each of the plurality of objects, an activity, a location, a time period of interest, and a notify/suppress indicator associated with each of the plurality of objects. The method also includes receiving an indication of a specific object of the plurality of objects, receiving a video stream, and detecting, for the specific object, occurrence of the activity in the location during the time period of interest. The method further includes determining that the notify/suppress indicator is associated with notification and generating a notification related to the occurrence of the activity in the location during the time period of interest.

Abstract: Techniques are generally described for scene change detection. A first and second histogram representing frames of a video may be received. A Euclidean distance between the first and second histogram may be determined. A third histogram of a third frame may be received. Values of the third histogram may be compared to corresponding values of a background model of the environment. A fourth frame and a fifth frame of image data of the video may be received. A flow value between a first block of pixels of the fourth frame and a corresponding second block of pixels of the fifth frame may be determined. The flow value may be determined based on a motion vector and a sum of absolute differences between the first and second block. A portion of the video may be streamed to a remote computing device if the flow value exceeds a threshold value.

Abstract: Systems and techniques are generally described for pattern recognition in video data. In some examples, a first set of pixels representing a first person in the first video data may be determined. First feature representation data of the first set of pixels may be generated. The first feature representation data may be determined to correspond to second feature representation data stored in memory. An identity of the first person associated with the second feature representation data may be determined. A first action associated with the first person may be determined. A notification may be sent to a computing device accessible by the first person. The notification may include a reminder for the first person to engage in the first action.

Abstract: This application describes techniques for providing computer vision for manual services. In some instances, a remote system may determine that a current time is within a threshold period of time of a scheduled service and, based on the determination, send a first message requesting image data to a camera apparatus located within an environment. After sending the first message, the remote system may receive image data associated with the environment from the camera apparatus and use the image to detect an object within the environment. The remote system can then send a second message to a device of a guest and a third message to a device of a user, where each of the second message and the third message indicates that the object is within the environment. In some instances, the object can include an animal while in some instances, the object can include a person.

Abstract: A computer-implemented method includes receiving an image frame of image data associated with a camera. The method also includes receiving a human presence heatmap for the image frame, receiving a motion heatmap for the image frame, and receiving an image metric heatmap for the image frame. The method further includes receiving a combined heatmap as a combination of the human presence heatmap, the motion heatmap, and the image metric heatmap and setting auto-exposure parameters for the camera based on the combined heatmap.

Abstract: Systems, methods, and computer-readable media are disclosed for determining a depth or reflectance of objects. Example methods may include causing, by a camera device, infrared illumination within a field of view of the camera device, wherein the field of view is at least partially illuminated at a first illuminance value, detecting a human face present in the field of view, determining, using the first illuminance value, a depth value of a portion of the human face, determining, using the depth value, a user account associated with a user having the human face, and causing presentation of information associated with the user at the camera device based at least in part on the user account.

Abstract: This application describes techniques for providing computer vision-based surveillance of in-home services. In some instances, a remote system may authenticate a guest at an environment using data that the remote system receives from a camera apparatus. To authenticate the guest, the remote system can determine that an identification of the guest matches an identification of a worker associated with a scheduled service at the environment. When the scheduled service includes an in-home delivery, the remote system can further determine that a package in possession of the guest matches an item for the scheduled in-home delivery. In some instances, after the guest enters the environment, the remote system can further monitor the environment to ensure that the guest stays within a designated location of the environment. The remote system can further send a message to an electronic device when the guest is outside of the designated location.

Abstract: A system configured to improve human presence detection and/or localization by generating aggregate confidence values. The system may aggregate confidence values corresponding to overlapping regions of interest. The system may perform human presence detection by comparing the aggregate confidence values to a universal threshold, with aggregate confidence values above the universal threshold indicating that human presence is detected. The system may use the aggregate confidence values to generate a heatmap, may identify a strongest cluster of pixels in the heatmap and determine a bounding box surrounding the strongest cluster. To distinguish the strongest cluster from a second strongest cluster of pixels, the system may apply a Gaussian kernel with varying threshold values. The system may store the threshold value at which the strongest cluster separates from the second strongest cluster and may use the threshold value to generate the bounding box.

Abstract: Systems, methods, and computer-readable media are disclosed for determining a depth or reflectance of objects. Example methods may include illuminating a scene within a field of view of a device at a first illuminance value, detecting a reflected illuminance value, and determining a first reflectance value for a first object in the scene. Example methods may include identifying the first object, determining an orientation of the first object, and determining an estimated distance between the device and the first object based at least in part on the first illuminance value, the reflected illuminance value, and the first reflectance value.

Abstract: A system configured to improve human presence detection and/or localization by generating aggregate confidence values. The system may aggregate confidence values corresponding to overlapping regions of interest. The system may perform human presence detection by comparing the aggregate confidence values to a universal threshold, with aggregate confidence values above the universal threshold indicating that human presence is detected. The system may use the aggregate confidence values to generate a heatmap, may identify a strongest cluster of pixels in the heatmap and determine a bounding box surrounding the strongest cluster. To reduce false positive detections, the system may track the false positive detections as heatmap base data and may remove the heatmap base data from the heatmap. Thus, pixel intensity values corresponding to the false positive detections may be reduced to improve an accuracy of the human presence detection.