Abstract: Inspection systems and methods of inspection are provided that include an image sensor to acquire inspection data characterizing a video of at least a portion of an asset being inspected, wherein the asset includes one or more components, and a computing system communicatively coupled to the image sensor. The computing system includes a user interface display, a processor and a memory storing instructions which, when executed by the processor causes the processor to perform operations including: receiving, from the image sensor, the inspection data, identifying, automatically, at least a first component of the one or more components, generating a graphical user interface (GUI) including the inspection data, generating a first dynamic identifier within the GUI, wherein the first dynamic identifier corresponds to the first component and is arranged to follow the first component as it moves within the GUI, and providing the GUI to the user interface display.

Abstract: Provided is a method for detecting a surface defect of a copper-clad laminate based on multi-scale gridding. The method includes: S1, collecting a photographed image of the copper-clad laminate through a line-scan camera; S2, segmenting out a copper-clad region and a non-copper-clad region, and rotating the copper-clad region upright; S3, dividing the copper-clad region of the image of the copper-clad laminate, and performing a pyramid operation on a divided original grid image; S4, determining averages of pixel values at all levels; S5, fusing the average at all levels to obtain a final background average; and S6, searching for a final defect according to a difference between a background and a foreground.

Abstract: Systems and methods are provided for. One embodiment is a system that includes an interface configured to receive an image of media printed on with print data, and memory configured to store defect reference data of nozzles belonging to printheads of a printer. The system also includes a print defect controller configured to detect a nozzle defect in the image based on a comparison of the image with the print data, and to determine a type of the nozzle defect based on a comparison of the nozzle defect with the defect reference data.

Abstract: A computer is caused to perform processing of: acquiring a plurality of medical images generated based on signals detected by a catheter inserted into a lumen organ while the catheter is moving a sensor along a longitudinal direction of the lumen organ, the lumen organ including a main trunk, a side branch branched from the main trunk, and a bifurcated portion of the main trunk and the side branch; and recognizing a main trunk cross-section, a side branch cross-section, and a bifurcated portion cross-section by inputting the acquired medical images into a learning model configured to recognize the main trunk cross-section, the side branch cross-section, and the bifurcated portion cross-section.

Abstract: The present disclosure relates to a method for generating a learning model, a learned model, a program, and a controller of a bladder endoscope in which the program or the model is recorded. The method including: acquiring, as teaching data, endoscope image data on a Hunner lesion in a bladder; and generating the learning model by using the teaching data such that a bladder endoscope image serves as an input and the position indication of a Hunner lesion in the bladder endoscope image serves as an output. The program causing a computer to perform acquiring endoscope image data on a Hunner lesion in a bladder, inputting a target bladder endoscope image to a learning model in which a bladder endoscope image serves as an input and position-indication data on a Hunner lesion in an endoscope image serves as an output, and outputting the position indication of the Hunner lesion.

Abstract: An unsupervised region-growing network (RGN) is trained to perform object segmentation on video data degraded by atmospheric turbulence. The method includes obtaining input data containing turbulence-degraded video, extracting a video frame sequence, and training the RGN using a selected algorithm incorporating a region-growing algorithm and a grouping loss function. A bidirectional optical flow sequence is computed for multiple reference frames within the video sequence. Pixel-level masks are generated for detected moving objects, followed by applying the region-growing algorithm to create coarse masks. A grouping loss function refines these masks to ensure consistency across consecutive frames. The trained RGN outputs refined masks as object segmentation data for the received video, improving segmentation accuracy in turbulent environments.

Abstract: A method of object tracking includes detecting a dynamic object in a scene, sampling key points of the dynamic object, extracting short term features of the key points, combining long-term key point features read from a key point features database into combined key point features, applying attention processing to hash the combined key point features, applying a plurality of transformer layers on top of attention processing to update the combined key point features using the interactions of the key points to form the long-term key point features and storing the long-term key point features in the key point features database, and predicting an updated 3D box for the dynamic object from the updated combined key point features, the updated 3D box including a tracklet representing motion of the dynamic object in the scene over time.

Abstract: A video of medical scan images associated with an anatomical structure may be arranged into multiple image pairs. The multiple image pairs may be provided to a machine learning (ML) model successively and the ML model may determine respective first sets of image features associated with the multiple image pairs and, for each of the multiple image pairs, refine the first set of image features associated with the image pair based on the respective first sets of image features associated with one or more other image pairs. A motion field associated with the image pair may be determined based at least on the refined first set of image features associated with the image pair and a task may be performed based on the respective motion fields.

Abstract: Methods and systems are described herein for inspection of a workpiece, such as a honeycomb body. The methods and systems include collecting a plurality of images of the honeycomb body, extracting measurement data from each of the plurality of images, converting the measurement data extracted from each image into a common frame of reference, and combining the measurement data together.

Abstract: Provided herein are methods of drug design comprising using a machine learning model to classify images of tissue samples as being of tissue samples from subject in a first state and tissue samples from subjects in a second state and extracting from the machine learning model groups of biological components comprising at least two biological components whose spatial relationship contributed to the classifying. Methods of drug design, as well as methods of converting a subject from a first state to a second state are also provided.

Abstract: Disclosed herein are methods, systems, and computer-readable media for generating image captions for training a machine learning model. Current image generation models are hindered by the prevalence of improper or inaccurate captions, which leads to suboptimal training data. This results in less effective image generation models. Disclosed systems and methods involve obtaining a text-to-image dataset including one or more digital image-caption pairs. Systems and methods involve generating a recaptioned dataset by applying an image captioner model to images in the text-to-image dataset. An image captioner model can be trained with an improved image dataset, a first tuning stage, and a second tuning stage, for improved performance.

Abstract: A computer-implemented method comprises: receiving, from a first local site remote from a model aggregator device, a local update of a machine learned model and a parameterization of local data, wherein the local update was generated at the first local site based on the local data; generating a synthetic representation of the local data based on the parameterization using a generative AI function; evaluating the local update using the synthetic representation to obtain an evaluation result indicative of the performance of the local update; and updating the machine learned model based on the evaluation result and the local update.

Abstract: An object is to provide a video processing system, a video processing apparatus, and a video processing method that can be expected to improve recognition accuracy of an object in a video. A video processing system includes video acquisition means, time difference information acquisition mean, and recognition means. The video acquisition means acquires an input video. The time difference information acquisition means acquires first time difference information between the frames of the input video. The recognition means inputs the input video and the first time difference information between the frames of the input video to a trained recognition model trained using a training video and second time difference information between frames of the training video and recognizing an object in the input video.

Abstract: The decision process of a first machine learning (ML) model may be explained based on a second ML model implemented on an apparatus. The apparatus may obtain a prediction about an image made based on the first ML model. The apparatus may further determine visual concepts associated with the image that may have been used by the first ML model to make the prediction, and determine respective contributions of the visual concepts to the prediction made by the first ML model. The apparatus may then generate, based on the second ML model, a textual description that explains the respective contributions of the visual concepts to the prediction made by the first ML model. The second ML model may determine respective image features associated with the visual concepts, map the determined image features to corresponding text features, and generate the textual description based at least on the text features.

Abstract: An inspection assistance system includes one or more processors including hardware, and the one or more processors are configured to: acquire a video signal including information of a medical image; perform recognition processing based on the video signal, to enable outputting of inspection assistance information for assisting an inspection; acquire identification information included in the video signal, the identification information being different from the information of the medical image; and determine whether the video signal is a video signal for the recognition processing, based on the identification information.

Abstract: The present invention relates to an edge computing system comprising a data processing unit, the data processing unit configured to generate a status data element based on an image of an area, and send the status data element to a remote component, wherein the image comprises an aerial image of the area, wherein the edge computing system, particularly the data processing unit thereof, is configured to receive a data stream from a sensor, and wherein a time interval between receiving the data stream and generating the status data element is less than 30 minutes, preferably less than 10 minutes, further preferably less than 1 minute. The present invention also relates to an associated method, and to an aerial vehicle comprising the edge computing system.

Abstract: A system for faster object attribute and/or intent classification may include an machine-learned (ML) architecture that processes temporal sensor data (e.g., multiple instances of sensor data received at different times) and includes a cache in an intermediate layer of the ML architecture. The ML architecture may be capable of classifying an object's intent to enter a roadway, idling near a roadway, or active crossing of a roadway. The ML architecture may additionally or alternatively classify indicator states, such as indications to turn, stop, or the like. Other attributes and/or intentions are discussed herein.

Abstract: A system includes one or more cameras configured to attach to an aircraft and capture a plurality of images. The plurality of images includes a first image including a runway and a subsequently captured second image including the runway. The system includes an aircraft computing system configured to identify common features in the first and second images, determine changes in locations of the common features between the first and second images, and determine a predicted landing location of the aircraft in the second image based on the changes in locations of the common features. The aircraft computing system is configured to abort landing on the runway based on the predicted landing location relative to the runway.

Abstract: This application provides an image processing method and apparatus, an electronic device, and a computer-readable storage medium. The method includes receiving a prompt that needs to be processed; obtaining a text feature of the prompt, and mapping the text feature to a generability index and a description type of the prompt; in response to the generability index being greater than an index threshold, the description type representing that the prompt does not comprise a verb, and the prompt comprising a plurality of clauses, obtaining similar images respectively corresponding to the plurality of clauses, image-text similarities between the clauses and the corresponding similar images being greater than an image-text similarity threshold; determining an image difference between the similar images respectively corresponding to the plurality of clauses; and in response to the image difference being less than an image difference threshold, using the similar images as illustrations of the corresponding clauses.

Abstract: According to implementations of the subject matter described herein, there is provided a solution for semantic representation of text in a document. In this solution, textual information comprising a sequence of text elements and layout information of the text element are determined from a document. The layout information indicates a spatial arrangement of the plurality of text elements presented within the document. Based at least in part on the plurality of text elements and the layout information, respective semantic feature representations of the plurality of text elements are generated. By jointly using both the textual information and the layout information, rich semantics of the text elements in the document can be effectively captured in the feature representations.