Disclosed is a technique for a railway disaster monitoring system for monitoring a foreign matter on a railway, which includes a camera and an image processing unit that receives a railway image captured by the camera. The image processing unit includes a segmented image acquisition unit that obtains a plurality of segmented images including a rail from the railway image received from the camera and scales the segmented images to obtain segmented image blocks of a predetermined size, and a segmented image determination unit which includes deep neural network (DNN) discriminators trained with deep learning neural networks and inputs the segmented image blocks to the DNN discriminators to determine whether the railway is in a normal state in which there is no foreign matter on the railway except a train passing by. Using the segmented images, a foreign matter on a railway can be rapidly and easily determined using a deep learning neural network even with a small number of resources.

An image recognition system includes a first detection unit, an extracted image generation unit, and a second detection unit. The first detection unit detects a person region showing at least part of a body of a person from a first image where a target object related to the person is captured. The extracted image generation unit cuts out an extracted region defined according to the person region from the first image. The second detection unit detects the target object on the basis of the cutout extracted region.

A computer readable medium for sizing a product includes instructions, that when executed by at least one processor, cause a computing device to: retrieve from a webpage information on a product including product dimensions; present on a display of a client device a graphical button that upon access by a user activates a camera for capturing an image of an object positioned at a focal distance from the camera, the object having a surface; prompt the user to enter boundary information of an imaginary housing to be placed on the surface; generate the imaginary housing dimensions in two dimensions (2D) based on the boundary information and the focal distance; and determine whether the product fits within the imaginary housing by comparing the product dimensions against the imaginary housing dimensions.

Provided are an image processing circuit, a system-on-chip including the same, and a method of improving quality of a first image. The image processing circuit includes a tuning circuit configured to receive a segmentation map including pixel-by-pixel class inference information of the first image and a confidence map including confidence of the class inference information, determine classes of respective pixels of the first image, correction effects for each pixel of the image, and correction values indicating intensity of the correction effects based on the segmentation map and the confidence map, and generate a correction map based on the classes and the correction values of the respective pixels; and at least one correcting circuit configured to generate an enhanced image by applying correction effects according to the correction values to the respective pixels of the first image based on the correction map.

In some embodiments, apparatuses and methods are provided herein useful to presenting information to customers. In some embodiments, an augmented reality system for presenting information to customers comprises a personalization server configured to store personalized data for the customers, receive an indication of a customer, receive a product identifier for a product, retrieve personalized data for the customer, and transmit the personalized data for the customer, an application configured to be executed by the mobile device, the application when executed by the mobile device causing the mobile device to capture images of products in a retail facility, receive user input to select the product from the images of products, receive the personalized data for the customer, generate an augmented reality presentation, and present the augmented reality presentation, and a control circuit configured to identify the product, and determine the product identifier for the product.

A method for determining, in parts, the volume of a bulk material (2) fed onto a conveyor belt (1) captures a depth image (6) of the bulk material (2), in parts, in a capturing region (4) by means of a depth sensor (3). So that bulk material can be reliably classified at conveying speeds of more than 2 m/s even in the case of overlaps without structurally complicated measures, the captured two-dimensional depth image (6) is fed to a convolutional neural network trained in advance, which has at least three convolutional layers lying one behind the other and a downstream volume classifier (20), the output value (21) of which is output as the bulk material volume present in the capturing region (4).

A method for monitoring a rotor assembly of a wind turbine includes receiving, via an imaging analytics module of a controller, thermal imaging data of the rotor assembly. The thermal imaging data includes a plurality of image frames. The method also includes automatically identifying, via a first machine learning model of the imaging analytics module, a plurality of sections of a rotor blade of the rotor assembly within the plurality of image frames until all sections of the rotor blade are identified. Further, the method includes selecting, via a function of the imaging analytics module, a subset of image frames from the plurality of image frames, the subset of image frames comprising a minimum number of the plurality of image frames required to represent all sections of the rotor blade. Moreover, the method includes generating, via a visualization module of the controller, an image of the rotor assembly using the subset of image frames.

Various examples of the disclosure relate to aspects associated with training a machine-learned algorithm configured to count cells in a microscopy image or to determine a degree of confluence of the cells.

Example systems, methods, and non-transitory computer readable media are directed to obtaining a point cloud that represents an environment based at least in part on a plurality of points in three-dimensional space; determining corresponding classifications of points in the point cloud as ground or not-ground based at least in part on a plurality of ground classification algorithms; determining respective point cloud features associated with the points in the point cloud; determining respective cell features associated with a plurality of cells that segment the point cloud; generating feature data for a machine learning model based at least in part on one or more of: the classifications of the points based on the plurality of ground classification algorithms, the point cloud features, or the cell features; and classifying the points in the point cloud based at least in part on an output from the machine learning model.

The present invention provides a method of angiography for cerebrovascular obliteration includes: using a classifier to obtain a 2D medical image using from a plurality of Multiphase CTA images; using a gray-scale conversion to obtain a N*M pixels grayscale image; filtering the grayscale image not being meet a condition of grayscale threshold and performing an image binarization to obtain a binarized image; confirming at least one vascular region and performing an image skeletonization; filtering according to a vascular image features of a vascular region to obtain a vascular-enhanced image; using a fracture analysis to obtain an analysis report related to a plurality of quantifying parameters of vascular characteristics; wherein the quantifying parameters of vascular characteristics comprises a quantitative value of fractal dimension (FD), vessel density (VD), skeleton density (SD) and vascular diameter index (VDI). Therefore, improve the accuracy of clinician diagnosis and the survival rates of patients with ischemic stroke