Abstract: The invention relates to a system for annotating car radar data, comprising: at least one radar arranged on a car for producing a radar image by means of radar measurement; at least one optical detection system arranged outside the car for producing a camera image; a segmentation unit, which is designed to subject a camera image produced by the optical detection system to semantic segmentation for forming a semantic grid in order to assign one of a plurality of object classes to the camera image pixel by pixel; a computing unit, which is designed to transfer the camera image and/or the radar image into a common coordinate system for co-registration; and an annotation unit, which is designed to carry out annotation of the radar image, in other words to allocate an object class to a radar target of the radar image, in such a way that the object class of the semantic grid of the co-registered camera image in which the radar target of the co-registered radar image is located is allocated to a particular radar tar

Abstract: To generate training data based on normal content and anomalous content generated from the normal content. A training data generation method for generating training data used for generating a learned model for determining whether there is an anomaly in an inspection target, the training data generation method including: receiving normal content regarding the inspection target and anomalous content generated from the normal content; and generating training data based on a set of the normal content and one or more pieces of the anomalous content.

Abstract: The provided is a personalized target selection method for a non-invasive neuromodulation technology, including: preprocessing functional magnetic resonance imaging (fMRI) data from MRI scan data of a current patient to acquire fMRI brain image feature data; inputting the fMRI brain image feature data into a pre-trained inter-subtype classification model to acquire a subtype label of the current patient and all feature voxels of the subtype label; preprocessing T1-weighted MRI data of structural magnetic resonance imaging (sMRI) data from the MRI scan data of the current patient to acquire a skull outline and a transformation matrix between the sMRI and fMRI data; performing coordinate transformation on the feature voxels, calculating a distance between each voxel on the skull outline and each feature voxel, marking response feature voxels, and counting a number of response feature voxels; and sorting the number of response feature voxels.

Abstract: Aspects of the present disclosure involve a system comprising a medium storing a program and method for machine-learning based selection of a representative video frame. The program and method provide for receiving a set of video frames; determining a first subset of frames by removing frames outside of an image quality threshold; determining a second subset by removing frames outside of an image stillness threshold; computing feature data for each frame in the second subset; providing, for each frame in the second subset, the feature data to a machine learning model (MLM), the MLM being configured to output a score for each frame in the second subset of frames based on the feature data, the MLM having been trained with a first set of images labeled based on aesthetics, and with a second set of images labeled based on image quality; and selecting a frame based on output scores.

Abstract: Disclosed herein are apparatuses, systems, methods, and computer-readable media relating to area selection in charged particle microscope (CPM) imaging. For example, in some embodiments, a CPM support apparatus may include: first logic to generate a first data set associated with an area of a specimen by processing data from a first imaging round of the area by a CPM; second logic to generate predicted parameters of the area; and third logic to determine whether a second imaging round of the area is to be performed by the CPM based on the predicted parameters of the area; wherein the first logic is to, in response to a determination by the third logic that a second imaging round of the area is to be performed, generate a second data set, including measured parameters, associated with the area by processing data from a second imaging round of the area by the CPM.

Abstract: Examples include authenticating a banknote having at least one printed area on a substrate thereof. An optoelectronic capturing device captures the at least one printed area on respective substrates of each of a plurality of copies of the same type of banknote to be authenticated and provides raw image data to a processor unit for visualizing the respective captured printed areas as an image on a display device connected to the processor unit. The processor unit partitions the respective image into a plurality of regions of interest (ROIs) and selectively provides different features for authentication of the certain type of banknote from the raw image data of each of the ROIs. Different selected features each form different classification models and authentication of a banknote to be presently authenticated is carried out using a plurality of classification models.

Abstract: A device may receive image data identifying images of a network device, and may receive environmental data, historical outage data, performance data, customer data, and historical weather data associated with the network device. The device may process the image data, with a first model, to identify objects of the network device and to generate classifications for the objects, and may process the objects, the classifications, and the environmental data, with a second model, to determine relationships between an environment of the network device and the objects. The device may process the objects, the classifications, the environmental data, the relationships, the historical outage data, the performance data, the customer data, and the historical weather data, with a third model, to predict a probability of damage to the network device or maintenance issues for the network device, and may perform actions based on the probability of damage and/or the maintenance issues.

Abstract: A refrigerator appliance may include a cabinet, a freezer drawer, a camera module, and a controller. The freezer drawer may include a drawer body and a freezer door coupled to the drawer body to move therewith and provide selective access to a freezer chamber. The controller may be operably coupled to the camera module. The controller may be configured to initiate an operation routine. The operation routine may include initiating an image capture sequence at the camera module to capture one or more two-dimensional images, identifying a first stored item based on the one or more two-dimensional images of the image capture sequence, determining an internal location of the first stored item within the freezer drawer based on the one or more two-dimensional images of the image capture sequence, and recording a descriptor of the first stored item and the internal location of the first stored item.

Abstract: Methods and systems are provided for determining a posture of a user of an Information Handling System (IHS). One or more cameras of the IHS are utilized to generate a two-dimensional image of the user as they operate the IHS. Landmarks that correspond to physical features of the user are identified through processing of the two-dimensional image generated using the cameras. The system then identifies, from a database comprising a plurality of differing wireframes, a subset of the wireframes that optimally match the physical feature landmarks of the user, each of the wireframes associated with an ergonomic level, and performs a regression analysis technique on the ergonomic level of each of the subset of wireframes to determine a posture score of the user.

Abstract: Disclosed by the present application are an image enhancement method and apparatus, a terminal device and a computer-readable storage medium.

Abstract: Disclosed are a hyperspectral imaging method and an apparatus thereof. A method of reconstructing a hyperspectral image includes receiving an image photographed through a diffractive optical element and reconstructing a hyperspectral image of the received image based on the received image and information about a point spread function for each wavelength of the diffractive optical element. The diffractive optical element may generate an anisotropic shape of the point spread function that varies with a spectrum.

Abstract: A depth estimation method and apparatus using a learning model are disclosed. A depth information estimation method may include identifying a plurality of image data, generating feature maps of the plurality of image data respectively, generating a cost volume using the feature maps, generating normalized cost volumes in different sizes by normalizing the cost volume, estimating disparity information from the normalized cost volumes, and generating depth information using the estimated disparity information.

Abstract: The invention relates to a method for producing variables of interest relating to human or animal hepatic tissue from a digital representation of a histological section. Such a method is intended to be implemented by a unit for processing a medical imaging system to automatically and quickly provide diagnosis assistance, in particular for NASH, to healthcare personnel. The variables of interest respectively describe a level of steatosis of the hepatic tissue, a level of fibrosis in the portal, central and perisinusoidal areas of the hepatic lobule and a level of inflammation of the hepatic tissue. A method according to the invention further provides for producing a multiparametric indicator in the form of graphical representations arranged to be displayed by an output human-machine interface of the medical imaging system.

Abstract: An electronic device for multimodal temporal-axis fusion artificial intelligence models is proposed. The electronic device comprises a storage unit, and a processor, wherein the processor may obtain a plurality of first visual features respectively corresponding to a plurality of different time points or time periods from a video, obtain a plurality of text features respectively corresponding to the plurality of time points or time periods from text, obtain a plurality of first local fusion features, respectively corresponding to the plurality of time points or time periods, from the plurality of first visual features and the plurality of text features by fusing the first visual features and the text features, which correspond to a same time point or time period, and obtain at least one global fusion feature from the plurality of first local fusion features.

Abstract: A system for processing images captured in a retail store is provided. The system may include a processor configured to: access a database storing a group of product models; receive an image depicting at least part of a store shelf having a plurality of products of a same type displayed thereon; analyze the image and determine a first candidate type of the products based on the group of product models and the image analysis; determine a first confidence level associated with the first candidate type; when the first confidence level is below a confidence threshold, determine a second candidate type of the products using contextual information; determine a second confidence level associated with the determined second candidate type of the plurality of products; and when the second confidence level is above the confidence threshold, initiate an action to update the group of product models stored in the database.

Abstract: There is provided a method for generating a 3D physical model of a patient specific anatomic feature from 2D medical images. The 2D medical images are uploaded by an end-user via a Web Application and sent to a server. The server processes the 2D medical images and automatically generates a 3D printable model of a patient specific anatomic feature from the 2D medical images using a segmentation technique. The 3D printable model is 3D printed as a 3D physical model such that it represents a 1:1 scale of the patient specific anatomic feature. The method includes the step of automatically identifying the patient specific anatomic feature.

Abstract: A user device may receive video associated with a patient, wherein the video depicts physiological activity involving the patient. The user device may receive profile information associated with the patient. The user device may obtain, from the video, image data using an image processing model. The user device may analyze the image data to generate a patient signature associated with the image data, wherein the patient signature is representative of the physiological activity. The user device may access a reference data structure that includes a plurality of reference signatures. The user device may identify that the patient signature is associated with a reference signature of the plurality of reference signatures, wherein the reference signature is associated with a health condition. The user device may perform an action associated with the health condition and the patient.

Abstract: A computer-implemented method for machine learning model operation can include, by one or more processors executing program instructions: providing a first training dataset comprising a plurality of images and associated object detection labels, providing a second training dataset comprising a plurality of images and associated classification labels, and providing a machine learning model comprising a model backbone, an object detection task head, and a classification task head. The method can further include training the machine learning model by training the object detection task head using the first training dataset and training the classification task head using the second training dataset. The method can further include deploying the trained machine learning model that includes the trained model backbone and the trained object detection task head but does not include the trained classification task head.

Abstract: The present disclosure provides a method and system for efficiently and securely managing human motion data. In one aspect, a human-motion-data-managing system first receives a sequence of video images including a first person. Next, for each image in the sequence of video images, the human-motion-data-managing system detects the first person in the video image; and subsequently extracts a skeleton figure of the detected first person from the image, wherein the skeleton figure is composed of a set of human keypoints. Next, human-motion-data-managing system combines a sequence of extracted skeleton figures of the detected first person from the sequence of video images to form a skeleton sequence of the detected first person which depicts a continuous motion of the first person. The human-motion-data-managing system subsequently transmits the skeleton sequence to a server in place of the actual images of the first person to preserve the privacy of the first person.

Abstract: A computational lithography process uses machine learning models. An aerial image produced by a lithographic mask is first calculated using a two-dimensional model of the lithographic mask. This first aerial image is applied to a first machine learning model, which infers a second aerial image. The first machine learning model was trained using a training set that includes aerial images calculated using a more accurate three-dimensional model of lithographic masks. The two-dimensional model is faster to compute than the three-dimensional model but it is less accurate. The first machine learning model mitigates this inaccuracy.