Abstract: The invention provides a system for detecting obstacle state and an operating method thereof, comprising an image capturing module, a semantic segmentation module, a feature extraction module, an object detection module, and a distance table calibration module. The invention is delivered a semantic segmentation information to a model for processing self-learning, and selected an output of an original image size, for a carrier of an attention mechanism.

Abstract: The invention relates to a system and method to control a workflow comprising at least one task to be performed by a person (P3), wherein information is provided about at least one certain object (20, 32, 36, 38) related to the at least one task of the workflow, eye data (24, 26) are captured of at least one eye of the person (P3), and in dependency of the eye data (24, 26) and the information about the at least one certain object (20, 32, 36, 38) it is checked whether at least one task condition consisting in whether the task had been performed and/or whether the task is allowed to be performed is fulfilled. The invention also relates to a system and method for providing a set of task-specific control parameters (CP).

Abstract: Provided are systems and methods for generating a score for any model which can be updated online, regardless of model type architecture and parameters, leveraging relations between regret and uncertainty.

Abstract: Apparatus and methods related to image processing are provided. A computing device can determine a first image area of an image, such as an image captured by a camera. The computing device can determine a warping mesh for the image with a first portion of the warping mesh associated with the first image area. The computing device can determine a cost function for the warping mesh by: determining first costs associated with the first portion of the warping mesh that include costs associated with face-related transformations of the first image area to correct geometric distortions. The computing device can determine an optimized mesh based on optimizing the cost function. The computing device can modify the first image area based on the optimized mesh.

Abstract: A method of registering sets of anatomical data for use during a medical procedure is provided herein. The method may include accessing a first set of model points of a patient anatomy of interest and intra-operatively acquiring a second set of model points by visualizing a portion of the anatomical surface in the patient with a vision probe. The method may further include extracting system information, including kinematic information from a robotic arm of a medical system and/or setup information, and generating an initial seed transformation based on the extracted system information. Thereafter, the method may include applying the initial seed transformation to the first set of model points and generating a first registration between the first set of model points and the second set of model points to permit model and actual information to be viewed and used together by an operator.

Abstract: A medical image diagnostic apparatus of embodiments includes an acquisition unit and a processing unit. The acquisition unit acquires physical characteristics data of an examination subject and information about an imaging target portion. The processing unit is configured to output bed position information about the examination subject according to the acquired physical characteristics data and the information about the imaging target portion by inputting the physical characteristics data and the information about the imaging target portion acquired by the acquisition unit to a trained model which is configured to output bed position information on the basis of physical characteristics data and information about a imaging target portion.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed for text extraction from a receipt image. An example apparatus for clustering vertices, the apparatus comprises machine-readable memory, instructions, and processor circuitry to execute the machine-readable instructions to calculate a centroid corresponding to coordinates, calculate distances for respective ones of the coordinates relative to the centroid, calculate differences between the distances, determine whether ones of the differences satisfy a set of thresholds, in response to determining that ones of the differences satisfy the set of thresholds, calculate bearing angles for ones of the coordinates, determine an efficiency metric associated with respective ones of the bearing angles, sort each of the bearing angles based on the associated efficiency metric, and form coordinate clusters based on the sorted bearing angles.

Abstract: A system for determining the position and orientation of a landing area relative to an approaching vehicle is disclosed. The landing area has a plurality of target items disposed proximate to the landing area at known locations. The system includes a sensor on which is formed images of target items that are within a Field of View (FOV) of the sensor, a processor configured to receive the positions of the target items on the sensor, and a memory coupled to the processor. The memory stores the locations of the target items relative to the landing area and instructions that, when loaded into the processor and executed, cause the processor to determine a position and an orientation of the landing area relative to the vehicle based in part on the information received from the sensor and the locations of the target items.

Abstract: The disclosure describes techniques for interacting with visitors at a visitor interaction system. A method includes obtaining video data captured by the visitor interaction system, identifying an approach of a person, and analyzing the video data to determine an identity of the person. The method includes automatically and without user intervention determining that the person belongs to a visitor groups of a plurality of visitor groups. Each of the visitor groups corresponds to a response model that includes a plurality of response actions. At least one of the response actions includes an autonomous response action. The method includes identifying a response model corresponding to the visitor groups and initiating an autonomous response action associated with the response model. Initiating the autonomous response action including presenting a message to the person, monitoring a response to the message, and sending a report message to the user via a client device.

Abstract: Described is a system for pattern recognition and graph extraction. The system operates by obtaining data from a quantum dot device having gate defined semiconductor quantum dots. An image with pixel-level coordinates is then generated from the data. Ground truth graph annotations are received of the image. A deep network processes the image and pixel-level coordinates to generate a predicted graph. The predicted graph is compared to the graph annotations to generate a loss, which allows the deep network to be optimized by updating parameters in the deep network based on the loss. The image with pixel-level coordinates is then used to generate an optimized predicted graph, which allows for identifying operational voltages to apply to the quantum dot device.

Abstract: A system and method for determining a location of a client device is described herein. In particular, a client device receives images captured by a camera at the client device. The client device identifies features in the images. The features may be line junctions, lines, curves, or any other features found in images. The client device retrieves a 3D map of the environment from the map database and compares the identified features to the 3D map of the environment, which includes map features such as map line junctions, map lines, map curves, and the like. The client device identifies a correspondence between the features identified from the images and the map features and determines a location of the client device in the real world based on the correspondence. The client device may display visual data representing a location in a virtual world corresponding to the location in the real world.

Abstract: A system includes an intraoral scanner and a computing device operatively connected to the intraoral scanner. The intraoral scanner generates three-dimensional scan data of a tooth and further generates color data of the tooth under multi-chromatic light. The computing device receives the three-dimensional scan data and the color data of the tooth during a first mode of operation. The computing device invokes a second mode of operation, and presents, in a graphical user interface (GUI), an image of the tooth. The computing device further presents, in the GUI, data indicating a plurality of color zones of the tooth and further indicating, for at least one color zone of the plurality of color zones, that insufficient color data has been received, wherein each color zone indicates a separate region of the tooth that is expected to have approximately uniform color.

Abstract: A method for enhancing a wide angle image to improve the perspectives and the visual appeal thereof wide-angle images uses custom adaptive dewarping. The method is based on the scene image content of recognized objects in the image, the position of these objects in the image, the depth of these objects in the scene with respect to other objects and the general context of the image.

Abstract: Disclosed herein are systems and methods of calibrating a microscope or an imaging system prior to acquiring image data of a sample. In some embodiments, a method is disclosed including the steps of (a) running a power output calibration module to calibrate an imaging apparatus for repeatability; (b) running an image intensity calibration module to calibrate the imaging apparatus for reproducibility and to mitigate differences in detection efficiency between channels; (c) collecting image data from a microscope or imaging system; (d) optionally running an unmixing module to unmix the collected image data into individual image channel images; and (e) optionally running a contrast agent intensity correction module to calibrate for differences in brightness between different contrast agents.

Abstract: Soundfield signals such as e.g. Ambisonics carry a representation of a desired sound field. The Ambisonics format is based on spherical harmonic decomposition of the soundfield, and Higher Order Ambisonics (HOA) uses spherical harmonics of at least 2nd order. However, commonly used loudspeaker setups are irregular and lead to problems in decoder design. A method for improved decoding an audio soundfield representation for audio playback comprises calculating a panning function (W) using a geometrical method based on the positions of a plurality of loudspeakers and a plurality of source directions, calculating a mode matrix (?) from the loudspeaker positions, calculating a pseudo-inverse mode matrix (?+) and decoding the audio soundfield representation. The decoding is based on a decode matrix (D) that is obtained from the panning function (W) and the pseudo-inverse mode matrix (?+).

Abstract: Techniques described herein may involve audio settings based on an environment. An example implementation may involve a playback device playing back first audio content and during playback of at least a portion of the first audio content, detecting, via the at least one microphone, an audio signal. At least a portion of the detected audio signal may include a reflection of the first audio content played back by the playback device. The playback device may determine an equalization setting based on at least the determined one or more reflection characteristics and apply the determined equalization setting during playback of second audio content.

Abstract: A method for optimizing a knee arthroplasty surgical procedure includes receiving pre-operative data comprising (i) anatomical measurements of the patient, (ii) soft tissue measurements of the patient's anatomy, and (iii) implant parameters identifying an implant to be used in the knee arthroplasty surgical procedure. An equation set is selected from a plurality of pre-generated equation sets based on the pre-operative data. During the knee arthroplasty surgical procedure, patient-specific kinetic and kinematic response values are generated and displayed using an optimization process. The optimization process includes collecting intraoperative data from one or more surgical tools of a computer-assisted surgical system, and using the intraoperative data and the pre-operative data to solve the equation set, thereby yielding the patient-specific kinetic and kinematic response values. A visualization is then provided of the patient-specific kinetic and kinematic response values on the displays.

Abstract: Systems and methods for electromagnetic (EM) distortion detection and compensation are disclosed. In one aspect, the system includes an instrument, the system configured to: determine a reference position of the distal end of the instrument at a first time based on EM location data, determine that the distal end of the instrument at a second time is static, and determine that the EM location data at the second time is indicative of a position of the distal end of the instrument having changed from the reference position by greater than a threshold distance. The system is further configured to: determine a current offset based on the distance between the position at the second time and the reference position at the first time, and determine a compensated position of the distal end of the instrument based on the EM location data and the current offset.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and utilizing scale-diverse segmentation neural networks to analyze digital images at different scales and identify different target objects portrayed in the digital images. For example, in one or more embodiments, the disclosed systems analyze a digital image and corresponding user indicators (e.g., foreground indicators, background indicators, edge indicators, boundary region indicators, and/or voice indicators) at different scales utilizing a scale-diverse segmentation neural network. In particular, the disclosed systems can utilize the scale-diverse segmentation neural network to generate a plurality of semantically meaningful object segmentation outputs. Furthermore, the disclosed systems can provide the plurality of object segmentation outputs for display and selection to improve the efficiency and accuracy of identifying target objects and modifying the digital image.

Abstract: Methods for visualizing treatment outcomes are provided. In some embodiments, a method includes obtaining a first 2D image of a patient's teeth from a mobile device, and obtaining an arch model representing an outcome for the patient's teeth after orthodontic treatment. The method can include matching the patient's teeth in the first 2D image to corresponding teeth in the arch model, using a parametric model. The method can also include determining a target position for the patient's teeth, based on a position of the matched corresponding teeth in the arch model. The method can further include generating a second 2D image depicting the patient's teeth in the target position.