Abstract: CNN-based methods for cross-view image geo-localization rely on polar transform and fail to model global correlation. A pure transformer-based approach (TransGeo) is described to address these limitations from a different perspective. TransGeo takes full advantage of the strengths of the transformer related to global information modeling and explicit position information encoding. The claimed invention further leverages transformer input's flexibility and discloses an attention-guided non-uniform cropping method so that uninformative image patches are removed with a negligible drop in performance to reduce computation cost. The saved computation can be reallocated to increase resolution only for informative patches, resulting in performance improvement with no additional computation cost. This “attend and zoom-in” strategy is highly similar to human behavior when observing images.

Abstract: Systems and methods for extracting features from screen images for performing a task mining task are provided. A screen image depicting a user interface of a computing system is received. The screen image is preprocessed to generate a preprocessed screen image and processing results. Image features are extracted from the preprocessed screen image using a first machine learning based network. Text features and control element features are extracted from the processing results using a second machine learning based network. The text features and the control element features are encoded using a third machine learning based network to generate representative features of the screen image. A task is performed on the screen image based on one or more of the image features, the text features, the control element features, or the representative features. Results of the task are output.

Abstract: A class boundary detection apparatus (2000) acquires target time-series data (10). The class boundary detection apparatus (2000) extracts a plurality of pieces of extracted time-series data from the target time-series data (10), and calculates a similarity between each piece of extracted time-series data and reference time-series data (30). The reference time-series data (30) is time-series data representing a class boundary, and has a head portion of time-series data belonging to a subsequent class indicated by the class boundary after a tail portion of time-series data belonging to a preceding class indicated by the class boundary. The class boundary detection apparatus (2000) detects a class boundary represented by the reference time-series data (30) from extracted time-series data having the calculated similarity equal to or more than a threshold.

Abstract: A defect detection method includes: obtaining an average grayscale value of an image; constructing a mapping table, where elements of the mapping table include a mapped value corresponding to each grayscale value within a grayscale value range of the image, a mapped value corresponding to a grayscale value greater than or equal to a reference value is a first value, a mapped value corresponding to a grayscale value less than the reference value is a second value, and the reference value is an absolute value of a difference between the average grayscale value and a preset grayscale value; searching for a mapped value corresponding to a grayscale value of each pixel in the image from the mapping table; segmenting the image to obtain a suspicious defect sub-image based on the mapped value corresponding to the grayscale value of each pixel; and inputting the suspicious defect sub-image into a machine learning model.

Abstract: A video processing method and apparatus are provided. The video processing method includes: extracting at least two types of modal information from a received target video; extracting, based on a preset feature extraction model, at least two modal features corresponding to the at least two types of modal information; and fusing the at least two modal features to obtain a target feature of the target video.

Abstract: A computerized method for augmenting digital medical images, including an apparatus and methods utilizing a machine-learning approach for generating an augmented medical image containing features within the boundaries of the source image that are missing from or distorted in the source image.

Abstract: Disclosed herein are computer-implemented method, system, and non-transitory computer-readable device aspects for orchestrated multi-agent medical imaging analysis. The disclosed system receives medical imaging data, performs standardized preprocessing, and applies one or more machine-learning inference models to generate intermediate diagnostic outputs. An orchestration agent dynamically selects and invokes specialized downstream agents, including explainability, segmentation, clinical-context fusion, risk scoring, and bias detection agents, based on workflow rules, confidence thresholds, and shared-state memory conditions. The system then generates a structured clinical output comprising diagnostic measurements, visual overlays, narrative explanations, and risk assessments. The multi-agent architecture eliminates fragmented diagnostic pipelines and enables adaptive, reliable, and interpretable clinical decision support.

Abstract: Described is measuring an object by: determining measurement data using a device for measuring the object, wherein the measurement data generates a digital representation of the object with image data; and before the determining measurement data has ended: analyzing part of the digital representation to identify defects; if a defect is identified: determining at least one conformity result relating to the analyzed part, the conformity result indicating to what extent the analyzed part with the determined defect fulfils at least one predefined conformity criterion for the object; and if no defect is identified and sufficient measurement data have been acquired to determine that the analyzed part fulfils the at least one conformity criterion: generating a conformity result relating to the analyzed part, the conformity result indicating that the at least one predefined conformity criterion is fulfilled for the object; adapting the step of determining, taking the conformity result into account.

Abstract: A method, comprises identifying a set of image data captured by at least one autonomous vehicle when the at least one autonomous vehicle was positioned in a lane of a roadway, and respective ground truth localization data of the at least one autonomous vehicle; determining a plurality of lane width values for the set of image data; labeling the set of image data with the plurality of lane width values, the plurality of lane width values representing a width of a lane in which the at least one autonomous vehicle was positioned; and training using the labeled set of image data, a machine learning model, such that the machine learning model is configured to predict a new lane width value for a new lane as output.

Abstract: Provided is an object recognition device for detecting an object in an image, with which it is possible to detect, with high accuracy, a target object even in an image that has a background and other objects shown therein. This object recognition device is characterized by comprising: an image acquisition unit which acquires a first image composed of two-dimensional pixels; a three-dimensional shape approximation determination unit which determines whether image information of a prescribed rectangular region within the first image can be approximated by prescribed three-dimensional shape information; an image region estimation unit which clips out the rectangular region as a first estimation region on the basis of a determination result provided by the three-dimensional shape approximation determination unit; and a region selection unit which selects, from among a plurality of the first estimation regions, a first estimation region that has the smallest area.

Abstract: A method of decoding point cloud data comprises: determining that the point cloud data is split into a plurality of largest prediction units (LPUs), wherein at least two of the LPUs have different sizes along different directions; performing inter prediction to determine predicted points for the LPUs; and reconstructing points within the LPUs based on the predicted points for the LPUs.

Abstract: A measurement device including a centrifuge for holding porous media samples configured to test samples under centrifugal motion during rotation. A fluid capture device adjacent each media sample receives fluid from the sample due to centrifugal motion. A measurement system measures an amount of fluid from the media samples by taking an image of a fluid meniscus in the fluid capture device. A position sensor determines a position of the fluid capture device and triggers a camera to take the image of the fluid meniscus when the fluid meniscus is in a field of view of the camera. To prevent a false image from appearing in the captured image, a shield blocks light from reaching the camera when the meniscus is not in the field of view. The image of the fluid meniscus is processed to determine a fluid volume correlated to capillary pressure of the media sample.

Abstract: Disclosed are a target tracking method and apparatus based on a path. The target tracking method may include displaying an image that is received through a camera included in a target tracking apparatus on a display included in the target tracking apparatus, setting two or more points based on the image displayed on the display, and tracking a path that is determined based on the two or more points by controlling a rotation of the camera through a driving unit included in the target tracking apparatus.

Abstract: A method of crowdsourcing annotation for medical image data based on image comparison, includes developing an annotation task; acquiring and verifying medical images according to requirements of the annotation task, and performing statistics on the medical images that meet verification standards to obtain an amount of image data acquired; archiving the medical images that meet the verification standards to form a medical image database; setting up annotation rules, and generating annotation schemes and annotation samples according to the requirements of the annotation task and annotation rules; distributing the medical images in the medical image database to multiple crowdsourcing annotation sides, so that each medical image being annotated by the multiple crowdsourcing annotation sides; annotating, by the crowdsourcing annotation sides, the distributed medical images according to the annotation schemes and the annotation examples to form the annotated images; and merging multiple annotated images correspondi

Abstract: A real-time, intra-uterine operating field image is displayed to an operator. A processor identifies anatomical features and marks anatomical boundaries on the image with the aid of a trained classifier model. Labels for the identified anatomical features and the anatomical boundaries are displayed on the image. The trained classifier model is trained based on a set of prior surgical field images that have anatomical features and anatomical boundaries therein identified and marked, respectively, by previous operators. The trained classifier model is typically a convolutional deep neural network. The operator is allowed to modify the anatomical feature labels and anatomical boundaries, as well as update the set of training images with the modified image. The labeling of the anatomical features and establishment of the anatomical features facilitate performing treatments in the uterus, such as the ablation of uterine fibroids.

Abstract: A system for selecting motion models for aligning scene content captured by different image sensors, is configurable to (i) access a first image captured by a first image sensor and a second image captured by a second image sensor; (ii) access a set of motion models; (iii) define a reference patch within the second image; (iv) generate a respective match patch for each motion model of the set of motion models; (v) determine a similarity between each respective match patch and the reference patch within the second image; (vi) select a final motion model from the set of motion models based upon the similarity between each respective match patch and the reference patch within the second image; and (vii) utilize the final motion model to generate an output image for display to a user.

Abstract: Systems, components, methods, and algorithms for generating template information are described. a computer-implemented method includes receiving microscope image data, detecting a feature in the microscope image data, receiving feature template data describing a grouping of features including the feature, detecting the grouping in the microscope image data based at least in part on the feature template data, generating template information describing the grouping, and outputting the template information.

Abstract: In various examples, circadian rhythm-based data augmentation for drowsiness detection systems and applications are provided. Embodiments described herein may produce an estimated circadian rhythm for a test subject and/or vehicle driver or other machine operator or occupant, and use the pattern of that circadian rhythm to correct, confirm, calibrate, or otherwise augment drowsiness assessments derived from video image data. The position of a person in the context of their process C circadian cycle may be used as indication of their level of drowsiness. An estimated process C circadian cycle may be used to generate more accurate ground truth training data for training machine learning models, and may be used by real-time, in-vehicle drowsiness detection systems that infer driver drowsiness levels based on captured images. In various embodiments, a circadian rhythm drowsiness estimate may be used to correct, calibrate, augment, and/or replace a drowsiness score predicted by a machine learning model.

Abstract: A system for correcting an alignment of positions of points affiliated with an object, in images of a location, that has one or more of a linear feature or a planar feature can include a processor and a memory. The memory can store an alignment module and a communications module. The alignment module can include instructions to: (1) identify, within data affiliated with the images, the positions of the points affiliated with the object that has the one or more of the linear feature or the planar feature and (2) correct, in a manner that recognizes that the object has the one or more of the linear feature or the planar feature, the alignment of the positions to produce a digital map of the location. The communications module can include instructions to transmit the digital map to a vehicle to be used to control a movement of the vehicle.

Abstract: The present disclosure provides a method and an apparatus for estimating a body part position of a person, the method comprising: detecting, by a processor, a plurality of body part positions of the person from an image in which the person is detected, wherein each of the plurality of body part positions corresponds to a body part of the person; and estimating, by the processor, a body part position of the person based on the detected plurality of body part positions.