17 results about "Automatic localization" patented technology

The invention relates to the technical field of metal material quality detection, and discloses a metal material surface defect detection method, device and equipment and a storage medium, and the method comprises the steps: obtaining a standard three-dimensional point cloud template and actual measurement point cloud data of the surface of a target metal material; preprocessing the actually measured point cloud data to obtain preprocessed actually measured point cloud data; performing space alignment on the preprocessed actually measured point cloud data and a standard three-dimensional point cloud template based on a registration algorithm to obtain a registration result; residual data are generated according to the registration result, and candidate defect areas are identified from the residual data; and performing clustering analysis on the candidate defect area to obtain defect information of the surface of the metal material. According to the invention, the detection stability of the metal material and the recognition precision of small defects can be improved, automatic positioning and noise filtering of deformation defects such as gutter formation and bone formation are realized, and the detection rate and the detection intelligent level are remarkably improved.

A method may involve: receiving direction of arrival (DOA) data corresponding to sound emitted by at least a first smart audio device of the audio environment that includes a first audio transmitter and a first audio receiver, the DOA data corresponding to sound received by at least a second smart audio device of the audio environment that includes a second audio transmitter and a second audio receiver, the DOA data corresponding to sound emitted by at least the second smart audio device and received by at least the first smart audio device; receiving one or more configuration parameters corresponding to the audio environment, to one or more audio devices, or both; and minimizing a cost function based at least in part on the DOA data and the configuration parameter(s), to estimate a position and an orientation of at least the first smart audio device and the second smart audio device.

This invention relates to an automatic localization method, computer device, and system for ulcer fragments in intestinal capsule endoscopy videos. It establishes an automatic ulcer fragment localization network based on initial temporal boundary specifications, combined with policy gradients and evaluation. The network is trained using query image-reference video pairs. The network is input into the trained network and outputs ulcer fragments in the reference video associated with the query image. A computer device is implemented based on this method. The system uses an input unit to input query image-reference video pairs, a localization unit to execute the method and locate the ulcer fragments, and an output unit to output the results. This invention uses an image of an ulcer lesion of interest from an intestinal capsule endoscopy as the query image and a long intestinal capsule endoscopy video as the reference video. It analyzes the video using reinforcement learning, refines the temporal boundary through sequential decisions using start and end markers, and accurately locates fragments related to the query image, thus completing the video relocalization task.

Method for investigating a semiconductor circuit (2) comprising several semiconductor components (4-6) on a front face (2) of a circuit carrier (3), comprising the steps: - Obtaining image data (7) depicting the semiconductor circuit (1) or a test object (8) produced by machining the circuit carrier (3) of the semiconductor circuit (1) from a rear side (9) opposite the front side (2), and - automatic identification of a function (10) of at least one semiconductor component (4-6) and / or at least one group (11) of semiconductor components (4-6) and / or automatic localization (12) of at least one functional block (13) of the semiconductor circuit (1) implementing a given function and / or at least one contact pad (14) of the circuit carrier (3) in the image data (7) by evaluating the image data (7) using an image processing algorithm (15).

The invention discloses a method and system for analyzing vehicle accident time and place based on EDR and T-BOX fusion. The method comprises the following steps: collecting EDR data and T-BOX data of a suspicious vehicle; performing multi-dimensional feature matching on the EDR data and the T-BOX data to realize time alignment of the EDR data and the T-BOX data; searching a time point corresponding to the collision event and spatial data corresponding to the time point in the T-BOX data, preliminarily judging whether the suspicious vehicle is a suspected hit-and-run vehicle, and if so, entering a final judgment step; and analyzing the collision point location of the collision event by using the EDR data and the T-BOX data, comparing the collision point location with the collision point location in the vehicle accident record, and if the collision point locations are consistent with the collision point location in the vehicle accident record, determining that the suspicious vehicle is a suspicious accident vehicle and reporting a conclusion. According to the method, the EDR data and the T-BOX data are subjected to feature matching, and linear interpolation and cubic spline interpolation algorithms are combined, so that high-precision space-time automatic positioning of the collision event is realized, and vehicle responsibility determination is assisted.

The present invention provides a method and system for automatic positioning of magnetic resonance imaging based on image registration, including: performing image registration on the three-dimensional magnetic resonance image of a to-be-imaged part with a plurality of pre-generated three-dimensional magnetic resonance template images respectively to obtain registration images and corresponding first registration parameters, and adding each registration image, the corresponding three-dimensional magnetic resonance template image and the registration parameters into a data set respectively; for each data set, calculating the similarity between the registration image and the three-dimensional magnetic resonance template image respectively, and processing according to each similarity and the first registration parameters in the corresponding data set to obtain a second registration parameter; processing according to the second registration parameter and a standard positioning parameter associated with the to-be-imaged part obtained in advance to obtain an automatic positioning parameter, which is used as the automatic positioning result of magnetic resonance imaging for the current magnetic resonance scan. The beneficial effect is to effectively improve the efficiency of the magnetic resonance imaging workflow and reduce the uncertainty brought by the operator's human factors.

The present application relates to an abnormal heartbeat localization method based on multi-instance learning. The method considers the importance of abnormal heartbeat localization from a new perspective, adopts a weakly supervised multi-instance learning method, predicts the fine labels of heartbeats through the coarse labels of signal sequences, can capture abnormalities in long-term electrocardiogram signals, and realizes the automatic localization of abnormal heartbeats. The present application starts from signal sequences containing multiple heartbeats, determines the positions of abnormal heartbeats among numerous heartbeats, ensures the integrity and coherence of heartbeats, and provides important value for real-time early warning and auxiliary diagnosis.

The present invention discloses a centering and localization method for large-aperture spherical optical elements under the manipulation of a robotic arm. An automatic centering and localization device is adopted, which includes a sample stage, a robotic arm, a probe mounted on the robotic arm and equipped with a spectral confocal sensor and a camera, a data acquisition unit electrically connected to the spectral confocal sensor, a data analysis and processing unit electrically connected to the data acquisition unit, and a control unit for receiving the feedback from the data analysis and processing unit and controlling the movement of the robotic arm. For large-aperture spherical optical elements, automatic centering is achieved by collecting three points on a certain concentric circle on the sphere, and then automatic localization is achieved by collecting edge points. The present invention is simple and easy to implement, without the need to calibrate the sensor. It only requires a robotic arm to carry an optical precision probe for three-dimensional movement, reducing the mechanical design and assembly difficulty, and realizing non-contact, fast, and automatic centering and localization of optical elements, which is suitable for mass production and detection of large-aperture optical elements.

Implementations described herein relate to methods, systems, and computer-readable media to localize dynamic content. In some implementations, a computer-implemented method includes receiving visual content associated with a game from a first client locale, the visual content including text being represented at the first client locale by a first language, converting the text to generate translated text in at least a second language associated with a second client locale, and storing the translated text in a database in association with the visual content.

The present invention discloses a method and device for sleep apnea event localization based on a multi-scale convolutional neural network. The nasal and oral airflow, thoracic pressure, and abdominal pressure signals in sleep monitoring data are selected as the data basis, and a sleep apnea event automatic localization network model integrating multi-modal data is designed. The model mainly includes the following four parts: extracting multi-modal features from preprocessed time series data based on a feature extraction module; generating a prediction feature layer with multi-scale in both network depth and network width based on a multi-scale prediction feature layer generation module; adaptively adjusting the size and position of a preset box designed according to the receptive field based on a region generation module; and classifying based on the scale consistency features generated by candidate segments. The model of the present invention adopts an end-to-end training mode and can simultaneously realize the classification and localization of sleep apnea events.

In accordance with various embodiments, described herein are systems and methods for providing automated localization of software applications and graphical user interfaces. A software extension or add-in component operates both as a design tool, and as a runtime process, for purposes of localizing a software application or its graphical user interface, including the translation of user-visible strings displayable within graphical user interface elements. The translation manager can be used to automate the localization of a software application or workbook being developed, including during an extraction process, automatically identifying and associating user-visible strings with string keys. When the workbook is subsequently accessed and used at runtime, for example by a business user working within a particular region or language, the extension or add-in can use the string keys to automatically map prepared-translations to the graphical user interface elements, for use in localizing the software application.

A method may involve: receiving direction of arrival (DOA) data corresponding to sound emitted by at least a first smart audio device of the audio environment that includes a first audio transmitter and a first audio receiver, the DOA data corresponding to sound received by at least a second smart audio device of the audio environment that includes a second audio transmitter and a second audio receiver, the DOA data corresponding to sound emitted by at least the second smart audio device and received by at least the first smart audio device; receiving one or more configuration parameters corresponding to the audio environment, to one or more audio devices, or both; and minimizing a cost function based at least in part on the DOA data and the configuration parameter(s), to estimate a position and an orientation of at least the first smart audio device and the second smart audio device.

The invention discloses an AI-based multi-language front-end interface automatic localization method and system. The automatic localization method comprises the following steps: automatically loading and displaying a corresponding translation text according to language preference of a user; the language preference of the user is detected and recognized, and a translation version is automatically selected; automatically translating the application content by using machine learning and natural language processing technologies; adjusting the translation content according to the cultural background of the target language; the dynamic content is translated in real time; training the translation data based on a deep learning model; and multi-language resources are managed in a unified manner. And through an artificial intelligence technology, translation and localization of a multi-language front-end interface are automatically realized.

Embodiments included herein relate to a method, computer program product, and computing system for tire pressure monitoring. Embodiments of the present disclosure can include receiving amplitude and phase differences of a plurality of radio frequency (RF) signals between one or more TPMS sensors. Embodiments can also include comparing and monitoring the relative amplitude and phase differences of the plurality of RF signals between all of the TPMS sensors based on an automatic localization algorithm. Embodiments can also include distinguishing between a front of a vehicle and a back of the vehicle based on a statistical model. Embodiments can also include determining a rotational direction of all of the TPMS sensors on the vehicle based on information received from the statistical model in combination with data from sensor accelerometers.