Abstract: An information processing device includes a displacement calculation means and a motion estimation means. The displacement calculation means acquires time-series images obtained by capturing images of a measurement target region of a structure supported by a supporting member. The displacement calculation means calculates a three-dimensional displacement of the measurement target region from the acquired time-series images. The motion estimation means estimates a motion of the supporting member in the structure based on the three-dimensional displacement of the measurement target region.

Abstract: Some aspects of the subject matter disclosed herein include a system implemented on one or more data processing apparatuses. The system can include an interface configured to obtain, from one or more sensor subsystems, sensor data describing an environment of a vehicle, and to generate, using the sensor data, (i) one or more first neural network inputs representing sensor measurements for a particular object in the environment and (ii) a second neural network input representing sensor measurements for at least a portion of the environment that encompasses the particular object and additional portions of the environment that are not represented by the one or more first neural network inputs; and a convolutional neural network configured to process the second neural network input to generate an output, the output including a plurality of feature vectors that each correspond to a different one a plurality of regions of the environment.

Abstract: A method of making-up tubular string components can include inputting to an image processor image data output from at least one camera, the image processor in response detecting positions of a tubular and a mark on another tubular, threading the tubulars with each other while inputting position data from the image processor to a controller, and the controller terminating the threading in response to the position of the mark relative to the position of the first tubular being within a predetermined range. Another method of making-up tubular string components can include, in response to inputting image data to an image processor, the image processor detecting longitudinal positions of two tubulars, threading the tubulars with each other, and a controller terminating the threading in response to the longitudinal position of one tubular relative to the longitudinal position of the other tubular being within a predetermined range.

Abstract: Systems and methods for roof condition assessment from digital images using machine learning are disclosed, including receiving an image of a structure having roof characteristic(s), first pixel values depicting the structure, second pixel values outside of the structure depicting a background surrounding the structure, and first geolocation data; generating a synthetic shape image of the structure from the image using machine learning, including pixel values forming a synthetic outline shape, and having second geolocation data; mapping the synthetic shape onto the image, based on the first and second geolocation data, and changing the second pixel values so as to not depict the background; assessing roof characteristic(s) based on the first pixel values with a second machine learning algorithm resulting in a plurality of probabilities, each for a respective roof condition classification category, and determining a composite probability based upon the plurality of probabilities so as to classify the roof char

Abstract: A pistachio sorting device capable of accurately detecting BGY fluorescence emitted from a fluorescent material adhered to a shell of an in-shell pistachio to perform pass/fail determination and sort out defective products at high speed is provided. The pistachio sorting device comprises a lighting device 11 for irradiating in-shell pistachios which are objects to be sorted in an inspection region with ultraviolet light having a maximum peak wavelength within a range of 345 nm to 390 nm, an optical filter 12 for selectively transmitting light within a wavelength range of 500 nm to 600 nm, a sensor 13 for detecting a two-dimensional intensity distribution of the fluorescence transmitted through the optical filter 12 to generate two-dimensional image data indicating a two-dimensional intensity distribution of fluorescence in the inspection region, and a determining device for determining a pass/fail of for each object to be sorted 10 based on the two-dimensional image data.

Abstract: The present disclosure relates to a method for ultrasonic guided wave quantitative imaging in a form of variable array and belongs to the technical field of ultrasonic non-destructive testing. The method includes: converting a non-linear lippmann-Schwinger equation into a form of linear summation by a method of moments; and selecting acquisition arrays with different numbers of probes to measure a scattered field signal, and modifying Green's functions by variable born approximation for continuous iterations to approximate a true solution, so as to obtain a final objective function Ok to be solved. According to the present disclosure, by adjusting the arrays, the number of probes and appropriate solution algorithm can be selected based on the testing accuracy; and the method can achieve quantitative evaluation of non-destructive testing, and can be widely used in practical guided wave testing applications of industrial non-destructive testing.

Abstract: Methods, systems and apparatus, including computer programs encoded on computer storage media for receiving a set of images at a social media system, wherein each image includes one or more recognized features associated with one or more lightness values; indexing each image using the one or more recognized features and the associated range of lightness values; receiving a query; determining a first group of images that is responsive to the query; determining that the query triggers a lightness filter to be displayed on the user device; providing the first group of images for display on a user interface with one or more lightness filter indicators; and in response to a user selection of one of the one or more lightness filter indicators: filtering the first group of images to determine a filtered group of images, and updating the images provided for display according to the filtered group of images.

Abstract: An image processing system and an imaging device are provided. The image processing system includes a circuit board, an ambient light sensor, a light guide, a camera sensor and a camera lens. The ambient light sensor is integrated on the circuit board. An output end of the light guide is connected to the ambient light sensor to guide light to a detecting part of the ambient light sensor. The camera sensor is integrated on the circuit board. The camera lens is connected to the camera sensor. In the present disclosure, light guide is optically coupled with the ambient light sensor, such that a field of view of the ambient light sensor can be controlled to enhance color performance. Further, the light guide can provide spatial selectivity for the ambient light sensor while improving system integration and minimizing impact on appearance of the imaging device.

Abstract: Input data may be received. The input data may include an image of a pattern and location data that identifies a modified portion of the pattern. A processing device may determine a first parameter of a first dimension within the pattern and a second parameter of a second dimension outside of the pattern. A combined set may be generated based on the first parameter and the second parameter. A defect associated with the modified portion may be classified based on the combined set.

Abstract: A depth calculation processor, a data processing method, and a 3D image device are disclosed herein. The depth calculation processor includes: at least two input ports configured to receive a first image data, wherein the first image data comprises at least a structured light image acquired under projection of a structured light; a data processing engine configured to perform a calculation process on the first image data to output a second image data, wherein the second image data comprises at least a depth map, wherein the data processing engine comprises at least a depth processing engine configured to perform a depth calculation process on the structured light image to obtain the depth map; and at least an output port coupled to the data processing engine and configured to output the second image data to a host device.

Abstract: A product defect detection method, device and system are disclosed.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using an image processing neural network system that includes a spatial transformer module. One of the methods includes receiving an input feature map derived from the one or more input images, and applying a spatial transformation to the input feature map to generate a transformed feature map, comprising: processing the input feature map to generate spatial transformation parameters for the spatial transformation, and sampling from the input feature map in accordance with the spatial transformation parameters to generate the transformed feature map.

Abstract: An object texture measurement device includes a visual detection unit that detects a visual texture of an object, a tactile detection unit that detects a tactile texture of the object, and an acquisition unit that acquires a detection result of each of the visual detection unit and the tactile detection unit while relatively moving each of the visual detection unit and the tactile detection unit with respect to the object.

Abstract: The present invention is capable of determining the location(s) of waste (e.g. nuclear fuel debris, obstacles, contaminated or otherwise radioactive materials), monitoring and inspecting their surroundings, and transporting them, as well as use in repair, construction, and reactor decommissioning work in high radiation environment. Ultrasound (or sound) waves are not subject to interference from radiation. This modality is utilized in the present invention to detect and image waste and/or objects of interest. The system combines the resulting ultrasound (or sound) wave images for detecting waste and/or objects of interest with radiation information acquired by a radiation detector, to generate and adjust new composite images to display. For example, the image in the direction of strong radiation is red and the image in the direction of weak radiation is blue. Additionally, the constituent imaging apparatus may be fitted on a drone or robotic system for repair and construction work.

Abstract: Systems and methods are provided for intelligently monitoring environments, classifying objects within such environments, detecting events within such environments, receiving and propagating input concerning image information from multiple users in a collaborative environment, identifying and responding to situational abnormalities or situations of interest based on such detections and/or user inputs.

Abstract: A semiconductor image processing apparatus has an image input unit inputs a first semiconductor image, an exposure condition input unit configured to input exposure conditions, a generator performs a process of extracting a feature amount in consideration of the exposure conditions while reducing resolution of the first semiconductor image and thereafter use the extracted feature amount to increase the resolution to generate a second semiconductor image, and a discriminator configured to discriminate whether the input image is the second semiconductor image or a third semiconductor image provided in advance. The generator performs learning so that the discriminator erroneously discriminates the second semiconductor image as the third semiconductor image based on a result discriminated by the discriminator.

Abstract: Various embodiments of a cyber-physical system for providing cloud prediction for photovoltaic array control are disclosed herein.

Abstract: A system for use in repairing a stamping press die. The system includes an imaging system configured to perform a scan on a pressing surface of the stamping press die, wherein a profile of the pressing surface is determined based on the scan. A computing device is configured to compare the determined profile to a desired profile of the pressing surface, and to generate a repair template based on dimensional variations between the determined profile and the desired profile. A projection system is configured to display the repair template on the pressing surface.

Abstract: The systems and methods discussed herein provide for a method that includes receiving, by a device, a first image of a plurality of individuals. The method further includes identifying, by the device from a database comprising images of individuals, a plurality of individuals within the first image. The method further includes for each identified individual within the first image, by the device, identified individual with a first value. The method further includes, generating, by the device to a second device, a record comprising identifications of each identified individual within the first image and the first value.

Abstract: The present invention relates to a detection method for an assembly body multi-view change based on feature matching, comprising the following steps: S1, acquiring a first image and a second image; S2, performing feature point extraction and feature matching on the first image and the second image to obtain a matching pair set, a first unmatched point set of the first image and a second unmatched point set of the second image; S3, acquiring a first to-be-matched area set of the first image according to the first unmatched point set; acquiring a second to-be-matched area set of the second image according to the second unmatched point set; S4, performing feature matching on each first unmatched area and each second unmatched area one by one to obtain a plurality of matching results; and S5, outputting the assembly body change type according to the plurality of matching results.