Abstract: A state assessment system, a diagnosis and treatment system and a method for operating the diagnosis and treatment system are disclosed. An oscillator model converts a physiological signal of a subject into a defined feature image. A classification model analyzes state information of the subject based on the feature image. An analysis model outputs a treatment suggestion for the subject based on the state information of the subject. An AR projection device projects acupoint positions of a human body onto the subject, for the subject to be treated based on the treatment suggestion.

Abstract: A system for identifying an aspect of interest on a vehicle that includes a local AI system that can analyze sensor data from an on-site sensor to make an attempt to identify the aspect of interest according to first criterion. The aspect of interest can be information printed on the vehicle and/or on a seal of the vehicle. If the local AI system is unable to identify and validate the information on the first effort, it can consult with a central/global AI system that can leverage its own database and other local systems at other locations for subsequent attempts at identifying and validating the aspects of interest.

Abstract: Systems and method to detect presence of buried landmines in a suspect area. A drone is outfitted with a ground penetrating radar, an infrared camera, and a metal detector mounted onto a leveling platform. The drone is flown over the suspect area while maintaining the leveling platform horizontal. Signals from the ground penetrating radar, an infrared camera, and a metal detector are converted into radargram, thermal image, and metal gram. Convolutional neural networks are applied to each of the into radargram, thermal image, and metal gram to detect anomalies.

Abstract: An example system includes a pose engine to determine a pose of a camera based on an environmental measurement. The system also includes a transform engine to determine a transform to apply to frames captured by the camera based on the pose of the camera. The system includes a correction engine to apply the transform to the frames captured by the camera in substantially real-time with capturing of the frames.

Abstract: A support system, a support method, and a support program in the form of a non-transitory computer readable medium are disclosed that support a medical action during an operation. The support system includes a data acquisition unit configured to acquire, during an operation, use state data on a use state of a medical device during the operation, and target lesion data on a target lesion of a patient during the operation, a learning unit configured to perform machine learning using the use state data and the target lesion data, and a presentation unit configured to present a recommended operation policy based on a result of the machine learning.

Abstract: An imaging system and method of providing localization data to a vehicle using the imaging system is disclosed. The method may comprise: capturing, from an electronic depth camera, one or more images, wherein the one or more images include at least a portion of the vehicle; and using a deep neural network and the one or more images, determining a multi-degree of freedom (MDF) pose of the vehicle, wherein an optical axis of the electronic depth camera is oriented along a Z-axis according to a Cartesian coordinate system (comprising an X-axis, a Y-axis, and the Z-axis), wherein the Z-axis is plumb with respect to Earth.

Abstract: In some examples, a system includes a memory configured to store a first image and a second image captured by one or more cameras mounted on one or more vehicles and store locations and orientations of the one or more cameras at times when the first and second images were captured. The system also includes processing circuitry configured to identify an existing landmark in the first and second images. The processing circuitry is also configured to determine a latitude, a longitude, and an altitude of the existing landmark based on the locations and orientations of the one or more cameras at the times when the images were captured. The processing circuitry is configured to create a file including the location of the existing landmark and pixel coordinates of the existing landmark in the first and second images.

Abstract: A technique for assessing development condition of a property is provided that determines development condition for an individual property or properties of interest using image or other sensor data from one or more unmanned aerial vehicles taken over the development process. A property condition output may be generated to indicate a condition of the property or properties.

Abstract: Systems and methods for detecting a waste receptacle, the system including a camera for capturing an image, a convolutional neural network, and processor. The convolutional neural network can be trained for identifying target waste receptacles. The processor can be mounted on the waste-collection vehicle and in communication with the camera and the convolutional neural network configured for using the convolutional neural network. The processor can be configured for using the convolutional neural network to generate an object candidate based on the image; using the convolutional neural network to determine whether the object candidate corresponds to a target waste receptacle; and selecting an action based on whether the object candidate is acceptable.

Abstract: An album creation application displays an image arrangement screen and an image selection screen, and image data selected by a user from among an image group is arranged in an image slot selected by the user on the image arrangement screen. Each of the image data, which is arranged in the respective image slots included in album data for which an order is confirmed, is analyzed so as to determine whether or not each of the image data is a target of high quality printing. Based on the analysis result, upsampling for increasing the resolution is selectively performed to the image data included in the album data. The album data is sent to an image printer.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for tracking objects in a store. One of the methods includes receiving, by one or more first computing devices, data captured by one or more sensors in the store; identifying, by the one or more first computing devices, a plurality of objects based on the received data, wherein the identified objects comprise one or more persons and one or more product items; extracting, by the one or more first computing devices, a plurality of features associated with each of the identified objects; generating, by the one or more first computing devices, a digest comprising information of the extracted features associated with the identified objects; and sending, by the one or more first computing devices, the digest to one or more second computing devices for processing.

Abstract: Predetermined information for determining whether an input screen on which a user inputs an evaluation of a program is to be displayed is received from a server. If the received predetermined information indicates that the input screen is to be displayed, the input screen is displayed on a display included in an information processing apparatus.

Abstract: The disclosure presents novel methods to conduct aerial surveying, inspection and measurements with higher accuracy in a fast and easy way, comprising: (1) flying a drone with an accelerometer, gyro, and camera sensors over a target object; (2) capturing a first aerial image at a first position; (3) capturing a second aerial image at a second position, wherein the second position has a horizontal and vertical displacement from the first position; (4) calculating the displacements between the first and second location using a sensor fusion estimation algorithm from the position sensors' data; (5) solving for the pixel depth information of the aerial images by using a single-camera stereophotogrammetry algorithm with the relative altitude and horizontal distance; (6) deriving the ground sample distance (GSD) of each pixel from the calculated depth information; (7) using the image pixel GSD values to compute any geometric properties of the target objects.

Abstract: A feature mapping computer system configured to (i) receive a first localized image including a first photo and a first location; (ii) receive a second localized image including a second photo and a second location; (iii) identify a roadway feature depicted in both the first and second photos; (iv) generate, using a photogrammetry module, a point cloud based upon the first and second photos and first and second locations; (v) generate a localized point cloud by assigning a location to the point cloud based upon at least one of the first and second locations; and (vi) generate an enhanced base map that includes a roadway feature by embedding an indication of the identified roadway feature onto the localized point cloud.

Abstract: Various implementations disclosed herein include devices, systems, and methods that involve federated learning techniques that utilize locally-determined ground truth data that may be used in addition to, or in the alternative to, user-provided ground truth data. Some implementations provide an improved federated learning technique that creates ground truth data on the user device using a second prediction technique that differs from a first prediction technique/model that is being trained. The second prediction technique may be better but may be less suited for real time, general use than the first prediction technique.

Abstract: A set of images of a three-dimensional (3D) inspection object collected by a drone during execution of a first flight path may be received, along with telemetry data from the drone. A tagged set of images may be stored, with each tagged image being stored together with a corresponding drone position at a corresponding time that the tagged image was captured, as obtained from the telemetry data. A mapping of the set of tagged images to corresponding portions of a 3D model of the 3D inspection object may be executed, based on the telemetry data. Based on the mapping, at least one portion of the 3D inspection object omitted from the set of tagged images may be identified. A second flight path may be generated for the drone that specifies a position of the drone to capture an image of the at least one omitted portion of the 3D inspection object.

Abstract: A robotic arm control system including a medical instrument to be inserted into a body-part, a force sensor to detect force applied by the instrument to the body-part, a robotic arm attached to the instrument, a first position sensor to track an instrument position of the instrument in the body-part, a second position sensor to track a body position of the body-part, and a controller to compute, responsively to the instrument position and the body position, a location of the instrument relative to the body-part, compare the detected force applied by the instrument to a permitted force level for application to an anatomical feature at the computed location and send a control command to, or cut power of, the robotic arm to loosen a rigidity of at least one robotic joint in response to the detected force applied by the instrument being greater than the permitted force level.

Abstract: Systems and methods for providing assistance to a surgeon during an implant surgery are disclosed. A method includes defining areas of interest in diagnostic data of a patient and defining a screw bone type based on the surgeon's input. Post defining the areas of interest, salient points are determined for the areas of interest. Successively, an XZ angle, an XY angle, and a position entry point for a screw are determined based on the salient points of the areas of interest. Successively, a maximum screw diameter and a length of the screw are determined based on the salient points. Thereafter, the screw is identified and suggested to the surgeon for usage during the implant surgery.

Abstract: A system may automatically create training datasets for training a segmentation model to recognize features such as lanes on a road. The system may receive sensor data representative of a portion of an environment and map data from a map data store including existing map data for the portion of the environment that includes features present in that portion of the environment. The system may project or overlay the features onto the sensor data to create training datasets for training the segmentation model, which may be a neural network. The training datasets may be communicated to the segmentation model to train the segmentation model to segment data associated with similar features present in different sensor data. The trained segmentation model may be used to update the map data store, and may be used to segment sensor data obtained from other portions of the environment, such as portions not previously mapped.

Abstract: The subject matter includes systems, methods, and prosthetic devices for joint reconstruction surgery. A computer-assisted intraoperating planning method can include accessing a first medical image providing a first view of a joint within a surgical site as well as receiving selection of a first component of a modular prosthetic device implanted in the first bone of the joint. The method continues by displaying a graphical representation of the first component of the modular prosthetic device overlaid on the first medical image, and updating a graphical representation of the first component based on receiving positioning inputs representative of an implant location of the first component relative to landmarks on the first bone visible within the first medical image. The method concludes by presenting a selection interface enabling visualization of additional components of the modular prosthetic device virtually connected to the first component and overlaid on the first medical image.