Patents Examined by Ian L Lemieux
-
Patent number: 11333795Abstract: A method for automatic selection of typhoon center using vectors calculated from radar image data by an optical flow technique includes calculating a valid vector field from the radar image data using the optical flow technique, generating a dense vector field by interpolating an empty spot of the valid vector field using linear interpolation, extracting a rotating component anomaly vector field including typhoon rotating component anomaly vectors by removing a relative vector in the interpolated valid vector field, generating a normal vector intersection point of the vectors of the extracted rotating component anomaly vector field, and finally selecting the typhoon center by calculating a maximum density normal vector intersection point based on a Gaussian kernel density estimation technique. Accordingly, it is possible to detect the moving path of the typhoon rapidly and objectively.Type: GrantFiled: June 23, 2021Date of Patent: May 17, 2022Assignee: KOREA METEOROLOGICAL ADMINISTRATIONInventors: Sun Jin Mo, Ji-Young Gu
-
Patent number: 11328822Abstract: An interactive cognitive platform is provided that uses image-based interactivities for diagnosis, treatment, and to analyze the progress (for disease and/or treatment) of cognitive diseases via a graphical user interface. The interactivities engage multiple cognitive domains and involve Gestalt principles—aspects which can be personalized to be more effective for each user. The cognitive platform can be used by healthcare workers to produce diagnostics or treatment plans for specific cognitive conditions and diseases with a cognitive component. The cognitive platform can be used for gaming, stress reduction and skills development and performance enhancement for those without cognitive problems.Type: GrantFiled: August 23, 2019Date of Patent: May 10, 2022Assignee: Conflu3nce LTDInventor: Tami Robyn Ellison
-
Patent number: 11321813Abstract: An electronic device may include angle detection circuitry to receive input image data including a channel of pixel data and determine pixel statistics based on a difference between a first pixel cluster and a second pixel cluster, and the second pixel cluster is offset from the first pixel cluster at a first angle. The pixel statistics may also be based on a difference between the first pixel cluster and a third pixel cluster, wherein the third pixel cluster is offset from the first pixel cluster a second angle, different from the first angle. The angle detection circuitry may also determine a best angle based on the differences, wherein the best angle approximates an angle of uniformity in content of the image. Image processing circuitry may then modify the input image data based on the best angle by modifying pixel values of the channel of pixel data.Type: GrantFiled: August 2, 2018Date of Patent: May 3, 2022Assignee: Apple Inc.Inventors: Jim C. Chou, Honkai Tam, Yun Gong
-
Patent number: 11315283Abstract: A system for object detection and posture estimation based on an object-customized image feature detection algorithm according to an embodiment of the present disclosure comprises at least one or more processors; and at least one or more memories, wherein at least one application, as an application that is stored in the memory and performs object detection and posture estimation based on an object-customized image feature detection algorithm by being executed by the at least one or more processors, learns a goal object based on a plurality of image feature detection algorithms, generates an algorithm list that includes evaluation of the plurality of image feature detection algorithms for detecting the learned goal object, detects a target object corresponding to the goal object among at least one or more candidate objects within an input image based on the generated algorithm list, and performs a posture estimation process for the detected target object based on the generated algorithm list.Type: GrantFiled: December 16, 2021Date of Patent: April 26, 2022Assignee: VIRNECT INC.Inventors: Ki Young Kim, Yeon Jo Kim, Noh Young Park
-
Patent number: 11308394Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images or features of images using an image classification system that includes a batch normalization layer. One of the systems includes a convolutional neural network configured to receive an input comprising an image or image features of the image and to generate a network output that includes respective scores for each object category in a set of object categories, the score for each object category representing a likelihood that that the image contains an image of an object belonging to the category, and the convolutional neural network comprising: a plurality of neural network layers, the plurality of neural network layers comprising a first convolutional neural network layer and a second neural network layer; and a batch normalization layer between the first convolutional neural network layer and the second neural network layer.Type: GrantFiled: April 1, 2020Date of Patent: April 19, 2022Assignee: Google LLCInventors: Sergey Ioffe, Corinna Cortes
-
Patent number: 11308633Abstract: Provided is an apparatus and method for aligning fiducial markers. The apparatus may align positions of the fiducial markers on the two or more micrographs forming a two or more point sets corresponding to the two or more micrographs; create a first set of matched fiducial markers and unmatched fiducial markers; transform unmatched fiducial markers into transformed point sets and match the unmatched fiducial markers resulting in a second set of matched fiducial markers. The matching of the second set of matched fiducial markers results in improved alignment of a large number of fiducial markers. The aligned positions of fiducial markers may be constrained by an upper bound of transformation deviation of aligning positions of fiducial markers on two or more micrographs.Type: GrantFiled: October 18, 2018Date of Patent: April 19, 2022Assignee: KING ABDULLAH UNIVERSITY OF SCIENCE AND TECHNOLOGYInventors: Xin Gao, Renmin Han
-
Patent number: 11298062Abstract: An interactive multi-purpose interactive cognitive platform is provided that uses image-based interactivities and may use enriched visual stimuli for diagnoses, treatment, and to evaluate and assess the progress and/or treatment of cognitive diseases and/or conditions with cognitive impacts. The platform may be used for performance enhancement training. The platform may include a graphical user interface. The platform is designed to cooperatively engage multiple cognitive domains using interactivities-embedded assessments. The images and image sets may involve the application of Gestalt principles for assessments and may be personalized address individual user preferences. The multi-purpose interactive cognitive platform may be used to produce diagnostics and/or treatment plans for specific cognitive conditions and diseases with a cognitive component.Type: GrantFiled: January 24, 2020Date of Patent: April 12, 2022Assignee: Conflu3nce LTDInventor: Tami Robyn Ellison
-
Patent number: 11291507Abstract: Navigation systems and methods for tracking physical objects near a target site during a surgical procedure are provided, the navigation system comprises a robotic device and an instrument attached to the robotic device; a process of optical registration and calibration can improve operation results by increasing accuracy and speed and eliminate the need for additional reference trackers, such as a pointer.Type: GrantFiled: June 14, 2019Date of Patent: April 5, 2022Assignee: MAKO Surgical Corp.Inventors: Jean Stawiaski, Fadi Ghanam, David Hofmann
-
Patent number: 11295472Abstract: A positioning method, a positioning device, a positioning system, a storage medium, and a construction method for an offline map database. The positioning method includes: obtaining a current image information, and extracting a visual feature in the current image information; matching the visual feature in the current image information with a key frame in an offline map database, and determining a candidate key frame similar to the visual feature in the current image information, wherein the offline map database is generated based on a global grid map and a visual map; and determining a pose corresponding to the candidate key frame, and converting the pose to coordinate values.Type: GrantFiled: May 17, 2019Date of Patent: April 5, 2022Assignee: BOE TECHNOLOGY GROUP CO., LTD.Inventors: Yue Li, Tong Liu, Jingtao Xu, Kai Zhao
-
Patent number: 11288493Abstract: Discussed herein are devices, systems, and methods for merging point cloud data with error propagation. A can include reducing a sum aggregate of discrepancies between respective tie points and associated 3D points in first and second 3D images, adjusting 3D error models of the first and second 3D images based on the reduced discrepancies to generate registered 3D images, and propagating an error of the first or second 3D images to the registered 3D image to generate error of the registered 3D images.Type: GrantFiled: February 25, 2020Date of Patent: March 29, 2022Assignee: Raytheon CompanyInventors: Jody D. Verret, Corey J. Collard
-
Patent number: 11288816Abstract: Provided are an image detection device, an image detection method and a program, which are capable of improving correspondence to a target deformation by optimizing a template shape, when performing target detection using template matching. An image detection device 100 for detecting a target from an input image comprises: a template generation unit 10 that generates a template for detecting a target; a mask generation unit 20 that generates a mask which shields a portion of the template, on the basis of temporal variations of a feature point extracted from an area including the image target; and a detection unit 30 that detects the target from the image using the template a portion of which is shielded by the mask.Type: GrantFiled: September 5, 2019Date of Patent: March 29, 2022Assignee: NEC CORPORATIONInventor: Takuya Ogawa
-
Patent number: 11281713Abstract: Systems and methods for image-based item identification are disclosed. Image data corresponding to one or more images depicting an item may be sent to one or more remote systems for image-based item identification. The identification indications and/or identification confidence scores received from the remote systems may be aggregated and weighted based at least in part on one or more factors related to the remote systems, the results, domains, image capture timing, image capture angles, and/or events to more accurately identify an item depicted in the images.Type: GrantFiled: January 17, 2020Date of Patent: March 22, 2022Assignee: Amazon Technologies, Inc.Inventors: Justin-Josef Angel, Milena Sadee, Cressida Magdalen Harding, Eric Alan Breitbard, Animesh Mishra, Vlastimil Pis, Robert Steven Murdock
-
Patent number: 11281933Abstract: An information processing device includes a categorizing section and a display control section. The categorizing section extracts a material component image identified as a material component from plural images obtained by imaging a sample fluid containing plural types of material element, and categorizes the extracted material component image serving as a detected component by predetermined category. The display control section performs control to re-categorize a material component image serving as the detected component already categorized into a different category, such that, when selection of a movement destination category is received in a state in which a first image list of detected components is being displayed, in a subsequent state in which the first image list and a second image list for the movement destination are being displayed at the same time, a material component image selected from the first image list is moved to the second image list.Type: GrantFiled: November 8, 2019Date of Patent: March 22, 2022Assignees: ARKRAY, Inc., SUMITOMO LIFE WELFARE AND CULTURE FOUNDATIONInventors: Koji Fujimoto, Shinya Nakajima, Kenichi Nagao
-
Patent number: 11275964Abstract: Methods for determining a unit load device (ULD) container type are disclosed herein. An example method includes capturing a set of image data featuring the ULD and aligning the set of image data with a template. The method further includes converting the set of image data and the template to down-sampled grids including a plurality of rows and columns. The method further includes removing portions of the image data grid that do not exceed a density threshold. The method further includes identifying a ULD border and a template border by extracting leftmost, rightmost, and topmost grid values from the respective grids. The method further includes calculating a match score corresponding to the template by determining a shortest respective distance between grid values in the ULD border and the template border, and determining ULD container type corresponding to the ULD based on the match score.Type: GrantFiled: March 27, 2020Date of Patent: March 15, 2022Assignee: Zebra Technologies CorporationInventor: Justin F. Barish
-
Patent number: 11276199Abstract: An image analyzer is configured to use an image processing technique to detect coordinates of a region of a first image frame that matches a target template and update the target template by copying a portion of the first image frame corresponding to the coordinates and a first size. The image analyzer is also configured to receive a second image frame and generate a plurality of pixel match counts based on a comparison of the target template with a plurality of regions of the first size of the second image frame. The image analyzer is further configured to determine that a region of the second image frame matches the target template based on a pixel match count of the second region. The image analyzer is configured to generate an output indicating coordinates of the region of the second image frame.Type: GrantFiled: February 17, 2020Date of Patent: March 15, 2022Assignee: THE BOEING COMPANYInventors: Jeffrey H. Hunt, Caleb G. Price
-
Patent number: 11270404Abstract: In one aspect, assembly of multi-part food packaging is checked by reference to payloads of steganographically-encoded digital watermarks printed across the packaging components. Marking all surfaces of the packaging components allows arbitrary orientation of feed stock in assembly equipment, and wide latitude in placement of inspection cameras along the packaging line. In another aspect, a scanner at a retail checkout station is alert to any gap detected in steganographic encoding on retail product packaging and, if found, alerts an operator to possible presence of an adhesive label with a misleading barcode. A great variety of others features and arrangements are also detailed.Type: GrantFiled: July 2, 2020Date of Patent: March 8, 2022Assignee: Digimarc CorporationInventors: Sean Calhoon, Tony F. Rodriguez, William Y. Conwell
-
Patent number: 11270445Abstract: A method for registering multiple data types of diverse modalities for a target volume includes acquiring at least at least two datasets associated with the target volume where the at least two datasets having different modalities. Using information field theory and entropy spectrum pathways theory, a local connectivity matrix is constructed for one or both of spatial connectivity and temporal connectivity for each of the datasets. The local connectivity matrices for the datasets are fused into a common coupling matrix and the datasets are merged to generate a registered image displaying the spatial and temporal features within the target volume.Type: GrantFiled: March 6, 2018Date of Patent: March 8, 2022Assignee: The Regents of the University of CaliforniaInventors: Lawrence R. Frank, Vitaly L. Galinsky
-
Patent number: 11250261Abstract: Provided is a method for monitoring a manufacturing process of an agricultural product. The method utilizes hyperspectral imaging and comprises scanning at least one region along a sample of agricultural product using at least one light source of a single or different wavelengths; generating hyperspectral images from the at least one region; determining a spectral fingerprint for the sample of agricultural product from the hyperspectral images; and comparing the spectral fingerprint so obtained to a spectral fingerprint database containing a plurality of fingerprints obtained at various points of the manufacturing process, using a computer processor, to determine which point in the manufacturing process the sample has progressed to.Type: GrantFiled: March 23, 2020Date of Patent: February 15, 2022Assignee: Altria Client Services LLCInventors: Henry M. Dante, Samuel Timothy Henry, Seetharama C. Deevi
-
Patent number: 11244190Abstract: Images in bitonal formats often include watermarks, stamps, or other patterns and artifacts. These patterned artifacts may be represented as a series of geometric points, dots, and/or dashes in the general shape of the original pattern. These patterned artifacts make other processes such as optical character recognition (OCR) difficult or impossible when items or pixels of interest are also found within the pattern of such artifact(s). Current patterned artifact removal solutions use methods of erosion to minimize the unwanted patterned artifact. However, such methods also erode the pixels/items of interest which, in turn, cause failures in other processes, such as OCR, that are desired to be carried out on or with the image.Type: GrantFiled: March 17, 2020Date of Patent: February 8, 2022Assignee: Revenue Management Solutions, LLCInventor: Jay Wagner
-
Patent number: 11237003Abstract: An image-based navigation system is arranged to obtain a terrain image of a target terrain from one or more image sensors at a low altitude imaging location. The terrain image includes at least one celestial image feature and at least one terrain feature. Map database information stored in at least one hardware memory device is accessed and compared to the at least one celestial image feature and the at least one terrain feature in the terrain image to determine absolute location coordinates of the imaging location.Type: GrantFiled: June 2, 2020Date of Patent: February 1, 2022Assignee: The Charles Stark Draper Laboratory, Inc.Inventors: Juha-Pekka J. Laine, Gregory P. Blasche, Benjamin F. Lane, Daniel M. Meiser, Eric T. Hoke, Matthew T. Jamula, Robin M. A. Dawson, Stephen P. Smith