Abstract: Disclosed are methods, systems, and computer-implemented method for detecting foreign objects on a landing surface. For instance, the method may include capturing an image from one or more cameras associated with a vehicle, detecting the landing surface present in the captured image, retrieving a reference image for the detected landing surface, and extracting a plurality of feature points present in both the captured image and the reference image. The method may further include determining a transformation between the captured image and the reference image by correlating the plurality of feature points between the captured image and the reference image, creating a virtual image by applying the transformation to one of the captured image or the reference image, and comparing the virtual image to the other one of the captured image or the reference image that was not transformed to detect one or more foreign objects.

Abstract: Methods and systems for detecting defects on a specimen are provided. One method includes generating first and second mode test, reference, and difference images of a specimen for first and second modes of an inspection subsystem, respectively. The method also includes combining the first and second mode test images, the first and second mode reference images, and the first and second mode difference images as an input for defect detection. In addition, the method includes detecting defects on the specimen based on at least the first and second mode difference images.

Abstract: An information processing apparatus acquires a first image obtained by capturing an image of a structure and first damage information of the structure extracted from the first image; acquires a second image obtained by capturing an image of the structure at a time point different from a time point at which the first image is captured and second damage information of the structure extracted from the second image; extracts feature points from the first image; extracts feature points from the second image; searches for corresponding feature points between the first image and the second image; performs coarse registration followed by fine registration on the first damage information and the second damage information based on information on the corresponding feature points to perform registration between the first damage information and the second damage information; and calculates a difference between the first damage information and the second damage information after the registration.

Abstract: In some examples, a computing system accesses a field of view (FOV) image that has a field of view less than 360 degrees and has low dynamic range (LDR) values. The computing system estimates lighting parameters from a scene depicted in the FOV image and generates a lighting image based on the lighting parameters. The computing system further generates lighting features generated the lighting image and image features generated from the FOV image. These features are aggregated into aggregated features and a machine learning model is applied to the image features and the aggregated features to generate a panorama image having high dynamic range (HDR) values.

Abstract: An image processing device 100 of the present invention includes a region extraction unit 121 that extracts, from a captured image, a mobile body region that is a region having a possibility that a mobile body exists, a matching unit 122 that performs template matching on the mobile body region by using a template corresponding to a mobile body that is a detection object, and a detection unit 123 that detects each mobile body from the mobile body region separately, on the basis of the template matching.

Abstract: An image acquisition method. N images of an object to be shot are acquired. The N images are shot by N shooting devices. Shooting fields of view of the N shooting devices are different from each other. The N images are in one-to-one correspondence with the N shooting devices. Feature extraction is performed on the N images to obtain M features of the N images. M is an integer multiple of N. The M features include M/N types of features.

Abstract: A computer-implemented method for the ordinal classification of at least one microscope image calculates a classification into one of a plurality of classes which form an order with respect to an image property. The microscope image is input into a machine-learned model for ordinal classification. The model comprises binary classifiers which calculate estimates regarding whether the microscope image belongs to cumulative auxiliary classes, which combine different numbers of the classes which follow each other in the order. The estimates can be combined so as to form a total score, wherein the classification occurs by comparing the total score with threshold values which can be defined in a variable manner depending on the application, or interval limits of the classes can be defined so that the classes form intervals of different widths. The model for ordinal classification can also comprise further binary classifiers for inverse auxiliary classes.

Abstract: One example method includes receiving a digital image, receiving an input list that includes a respective hash for each frame in a group of frames, creating new frames on a particular area of the digital image, and the new frames are created and located based on the information in the input list, obtaining a respective hash for content included within each of the new frames, comparing one of the hashes generated for one of the new frames with a hash from the input list and, when the hashes match, continue the comparing for all frames of the particular area, and when all hashes from the input list have been checked, determining whether or not the digital image is an illegal image.

Abstract: A system and method for extracting a full range hyperspectral data from one or more RGB images. The method encompasses pre-processing, the one or more RGB images. Further the method encompasses estimating, an illumination component associated with each pre-processed RGB image. The method thereafter comprises removing, the illumination component from the each pre-processed RGB image. Further the method encompasses tracking, a trajectory of pixel(s) over frame(s) associated with the each pre-processed RGB image. The method then leads to identifying, a position of the pixel(s) in one or more adjacent frames of the frame(s) based on a patch defined around said one or more pixels. Thereafter the method encompasses extracting, the full range hyperspectral data from the each pre-processed RGB image based on at least one of the removal of the illumination component, the trajectory of the pixel(s) and the position of the pixel(s).

Abstract: A method for enhancing images for metrological applications. A first set of first images is provided, wherein the first set comprises at least one first image, the first set representing a scene of interest, and a second set of second images is provided, wherein the second set comprises at least one second image, the second set representing at least a part of the scene of interest. The method comprises the following steps: 1) jointly processing the first set and the second set by a neural network, and 2) outputting a third set of images by the neural network, the third set comprising at least one processed image, from which is determinable the position and/or orientation of the at least one object with a processed precision, wherein the processed precision is equal to or higher than the initial precision.

Abstract: A portion of a polygon is appropriately extracted from an image.

Abstract: A driving assistance device that recognizes a lane marking around an own vehicle with at least one sensor includes a lane marking detection unit that detects lane marking information from data acquired by the sensor, a lane marking type candidate estimation unit that recognizes a lane marking type from the detected lane marking information and calculates a likelihood of each lane marking type, a lane marking type branch point estimation unit that detects a lane marking type branch point that is a point at which a likelihood of the lane marking type changes with respect to an advancing direction of the own vehicle, and distinguishes regions before and after the lane marking type branch point as a first region and a second region, and a lane marking information integration unit that, in a case where a lane marking of the first region and a lane marking of the second region have the same lane marking type, integrates the lane marking of the first region and the lane marking of the second region into a continuous

Abstract: According to at least one embodiment, a multi-angle multi-time-point method authenticates 2D objects with high confidence by sampling the object through space and time while being capable of automatically authenticating and inputting object information. Some embodiments further enhance authentication confidence by utilizing unique characteristics of hologram and/or personal photo. While this method possesses artificial intelligence comparable to human's in term of authenticating and extracting information from 2D objects, it's also highly efficient and can achieve real-time performance (e.g., processing 5 frames per second) on ordinary personal computers. Structural information is first extracted from a 2D image to reduce processing time for subsequent steps as more operations on the 2D images are avoided. By employing similar divide-and-conquer strategy according to a binary search algorithm for 1D data array, a Visual Binary Edge Search Algorithm is applied to a 2D image application.

Abstract: Some embodiments provide systems comprising: a machine learning model database; a deblur system configured to receive at least a portion of an image comprising a presumed location label captured by the image capture device, and apply at least a deblurring machine learning framework to generate a deblurred label image comprising the presumed location label; a rectification system configured to apply an machine learning transform algorithm to the deblurred label image to generate a rectified label image; an optical character recognition (OCR) system configured to apply a recognition machine learning model to the rectified label image to estimate text; and a location estimation system configured to estimate a location of the presumed location label as a function of the estimated text of the presumed location label relative to known text on known location labels position at respective different known locations within the product storage facility.

Abstract: Real world object reconstruction and representation include performing operations that include sampling locations along a camera ray from a virtual camera to a target object to obtain a sample set of the locations along the camera ray. For each location of the at least a subset of the sample set, the operations include determining a position of the location with respect to the target object, executing, based on the position, a reflectance multilayer perceptron (MLP) model, to determine an albedo and material shininess for the location, and computing a radiance for the location and based on a viewing direction of the camera ray using the albedo and the material shininess. The operations further includes rendering a color value for the camera ray by compositing the radiance across the first sample set.

Abstract: A method for inspecting an object includes determining a first inspection package that includes a first inspection image of the object and a first designation. The method includes determining data indicative of a second inspection package that includes a second inspection image of the object and a second designation. The method includes determining a first property of the object based on the first inspection image of the object, one or more properties maps of the object, and the first designation. The method includes determining a second property of the object based on the second inspection image of the object, the one or more properties maps of the object, and the second designation. The method includes displaying the first property and the second property or displaying data indicative of a comparison of the first property with the second property.

Abstract: Disclosed embodiments may include a system for identifying a statement. This may include receiving document image data which is then processed using optical character recognition to create language data and position data. The system may include identifying a plurality of dates from the language data and determining whether the plurality of dates is aligned in a first direction using the position data. The system may include determining whether the plurality of dates is within a predetermined time threshold or counting the plurality of dates to determine whether the count is greater than a predetermined count threshold. The system may create a label for the document and generate and transmit a graphical user interface to a user device for displaying the label and/or the document image data. The user may be able to interact with the user device to change the document label.

Abstract: A method of image enhancement, the method comprising: obtaining image data representing an image comprising a plurality of pixels, each having a pixel intensity value, the image further comprising a region of interest; analyzing image data associated with the region of interest and gathering relevant statistics thereon; analyzing image data associated with the image as a whole and gathering relevant statistics thereon; accumulating a histogram based on the intensity value of pixels in the image as a whole; defining histogram bins of interest that correspond to a range of pixel intensity values from within the region of interest; attenuating histogram bins outside of the bins of interest OR multiplying bins of interest by a scaling factor; using the attenuated or scaled histogram to create a cumulative distribution function; and using the cumulative distribution function to produce a contrast enhanced image.

Abstract: A method for tracking a movable implement of a work vehicle. The method comprises the steps of 1.) accessing images during movement of the work vehicle providing a view onto an environment and at least part of the implement, 2.) providing by a feature tracking algorithm a 3D environment model and referencing of the sensor pose to the 3D environment model, 3.) tracking implement features at different poses of the implement and, determining implement tracking data providing positional and arrangement information for the implement features, 4.) accessing benchmark information providing a real distance between two benchmark points, 5.) using the benchmark information to provide the implement tracking data with absolute scale information, and 6.) using the implement tracking data for the tracking of the implement.

Abstract: An operation method of a wafer analysis device include: generating a wafer map that is an image visualizing and showing whether each of a plurality of chips included in a wafer is normal or defective; applying virtual normal chips to the wafer map such that the number of chips adjacent to each of all the chips on an outermost edge of the wafer map is eight; obtaining the number of normal chips among eight adjacent chips of each of defective chips among the plurality of chips; determining whether a failure of each of the defective chips is caused by a systematic failure or a random failure.