Patents Examined by Charles T Shedrick
-
Patent number: 11488283Abstract: A point cloud reconstruction method and apparatus based on a pyramid transformer, a device, and a medium are provided. The method includes: after obtaining point feature data corresponding to each view, inputting the point feature data into a dual-channel pyramid network; when passing through a first channel, inputting an updated output of an attention mechanism of each layer to a next layer, when passing through a second channel, splicing and inputting the updated output of the attention mechanism of each layer and the updated output of the attention mechanism of a corresponding layer of the first channel in a same layer as the next layer to the next layer; converting the updated output of the attention mechanism of a bottommost layer of the second channel into point cloud coordinates to obtain a point cloud result, and taking an intersection of the point cloud result to characterize a target object.Type: GrantFiled: May 9, 2022Date of Patent: November 1, 2022Assignee: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGYInventors: Qiong Liu, Jun Zhang, You Yang
-
Patent number: 11481910Abstract: Highly accurate shape registration processing is performed. In the image processing apparatus, data, which correspond to N frames (N is an integer not less than 2), in units of frames including a plurality of three-dimensional models per frame is acquired. Then, shape registration processing is performed for the acquired three-dimensional models corresponding to the N frames by using information indicating a correspondence relationship of the three-dimensional models between frames of the N frames.Type: GrantFiled: January 30, 2020Date of Patent: October 25, 2022Assignee: CANON KABUSHIKI KAISHAInventors: Yuki Shiraishi, Tomokazu Sato
-
Patent number: 11475540Abstract: An electronic device is provided. The electronic device includes: a memory configured to include at least one instruction; and a processor configured to be connected to the memory to control the electronic device, and obtain an output image by upscaling an input image using an artificial intelligence model trained to upscale an image, wherein the processor is configured to control the electronic device to: obtain parameter information of the artificial intelligence model based on pre-processing related information performed on the input image, and upscale the input image using the artificial intelligence model corresponding to the obtained parameter information.Type: GrantFiled: March 26, 2020Date of Patent: October 18, 2022Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Sangkwon Na, Wooseok Kang, Minho Kim
-
Patent number: 11468597Abstract: Various embodiments include a correction method comprising: A) reading in data of an image of a calibration pattern recorded with an optical unit, the pattern including some structures; B) simulating a line through the image, the line extending through a reference point subdividing the line into half-lines, each intersecting the imaged structures; C) determining a first and a second sequence of measured values representing distances resulting from the intersection points on the half-lines line with respect to the reference point; D) determining a third and a fourth sequence of target values representing target distances of the intersection points; E) determining a mapping specification that at least approximately maps the target values of the third and fourth sequences to the measured values of the first and second sequences, or vice versa; and F) correcting image data of an image recorded using an optical unit using the mapping specification of step E).Type: GrantFiled: April 3, 2019Date of Patent: October 11, 2022Assignee: CONTINENTAL AUTOMOTIVE GMBHInventor: Andreas Weinlich
-
Patent number: 11468147Abstract: A computational apparatus for implementing a neural network model having multiple neurons that evaluate an activation function, the apparatus including a memory and circuitry. The memory is configured to hold values of a difference-function, each value being a respective difference between the activation function and a predefined baseline function. The circuitry is configured to evaluate the neural network model, including, for at least one of the neurons: evaluate the baseline function at the argument, retrieve from the memory one or more values of the difference-function responsively to the argument, and evaluate the activation function at the argument based on the baseline function at the argument and on the one or more values of the difference-function.Type: GrantFiled: February 24, 2020Date of Patent: October 11, 2022Assignee: HABANA LABS LTD.Inventors: Elad Hofer, Sergei Gofman, Shlomo Raikin
-
Patent number: 11460851Abstract: A system, comprising a computer that includes a processor and a memory, the memory storing instructions executable by the processor to input a red-green-blue (RGB) image and an eccentricity image to a neural network which outputs a located object based on combining the RGB image and the eccentricity image, wherein the eccentricity image is based on a per-pixel rolling average and a per-pixel rolling variance over a moving window of k video frames. The memory can further include instructions executable by the processor to receive the located object at a computing device included in one or more of a vehicle or a traffic information system.Type: GrantFiled: May 24, 2019Date of Patent: October 4, 2022Assignee: Ford Global Technologies, LLCInventors: Mostafa Parchami, Chandana Neerukonda, Gintaras Vincent Puskorius, Enrique Corona, Kunjan Singh
-
Patent number: 11443417Abstract: A system includes a memory and at least one processor to acquire a hyperspectral image of an object by an imaging device, the hyperspectral image of the object comprising a three-dimensional set of images of the object, each image in the set of images representing the object in a wavelength range of the electromagnetic spectrum, normalize the hyperspectral image of the object, select a region of interest in the hyperspectral image, the region of interest comprising at least one image in the set of images, extract spectral features from the region of interest in the hyperspectral image, and compare the spectral features from the region of interest with a plurality of images in a training set to determine particular characteristics of the object.Type: GrantFiled: December 17, 2020Date of Patent: September 13, 2022Assignee: Apeel Technology, Inc.Inventors: Lars Gustav Magnus Nipe, Abilasha Ramanan
-
Patent number: 11443443Abstract: A method aligns a first panoramic image and a second panoramic image in a navigation procedure. The method includes using a computer vision algorithm for extracting features that are present in the panoramic images and use the extracted features to prepare a first feature vector for the first panoramic image and a second feature vector for the second panoramic image. The first and the second feature vectors are compared and matches in both the first and the second feature vectors that are above a determined threshold are identified. For the identified matches in each of the first and the second feature vectors for each of the two images, the perspective angle between a reference point of the respective image and the features according to the identified matches are determined. Finally, a difference between the determined perspective angles for a part of the identified matches in the panoramic images is determined.Type: GrantFiled: July 16, 2020Date of Patent: September 13, 2022Assignee: Siemens Industry Software IncInventor: Vladislav Murashkin
-
Patent number: 11443459Abstract: A three-dimensional data encoding method includes: generating a bit sequence including N-bit information that is information of a current node included in an N-ary tree structure of three-dimensional points included in three-dimensional data and that indicates whether a three-dimensional point is present in each of child nodes belonging to the current node, where N is an integer greater than or equal to 2; generating (i) position information indicating a head position that is a position at which a predetermined code appears first in the bit sequence when the bit sequence is scanned in a predetermined scan order, and (ii) a remaining bit that is part of the bit sequence after the head position in the predetermined scan order; and encoding the position information and the remaining bit as information of the current node.Type: GrantFiled: September 18, 2020Date of Patent: September 13, 2022Assignee: PANASONIC INTELLECTUAL PROPERTY CORPORATION OF AMERICAInventors: Toshiyasu Sugio, Tatsuya Koyama
-
Patent number: 11436700Abstract: A device comprising filtering means having a pattern of at least four blocks wherein a second block is located vertical to a first block, a third block is located horizontal to said first block and a fourth block is located vertical to said third block and horizontal to said second block; and means to generate a new image from images captured using said filtered rays.Type: GrantFiled: January 31, 2019Date of Patent: September 6, 2022Assignee: InterDigital CE Patent HoldingsInventors: Neus Sabater, Benoit Vandame, Valter Drazic
-
Patent number: 11423511Abstract: The present invention provides an image composition method, an image composition device, and a recording medium that enable rapid and easy designation of correspondence points and image composition based on the designated correspondence points. In an image composition method according to an aspect of the invention, in a case where all of a plurality of images are unable to be composed into one image, a plurality of images are divided into composable image groups, whereby correspondence points may be designated for one image group and another image group (that is, image groups not subjected to automatic composition) without need of designating correspondence points for all images. A plurality of images are displayed on a display device by composable image group, whereby it is possible to allow ascertainment of image groups for which correspondence points are designated.Type: GrantFiled: December 11, 2019Date of Patent: August 23, 2022Assignee: FUJIFILM CorporationInventor: Makoto Yonaha
-
Patent number: 11410275Abstract: A video super resolution (SR) method based on video coding for machine (VCM) is provided for an electronic device. The method includes obtaining a lower resolution (LR) video; generating feature representations of the LR video based on a deep neural network (DNN); encoding the feature representations of the LR video, based on a VCM standard, and the LR video to form encoded feature representations of the LR video and an encoded LR video, wherein the feature representations of the LR video contain both space and temporal information on the LR video for creating a high resolution (HR) video corresponding to the LR video; and storing and transferring the encoded feature representations of the LR video and an encoded LR video for decoding.Type: GrantFiled: September 16, 2020Date of Patent: August 9, 2022Assignee: TENCENT AMERICA LLCInventors: Wei Jiang, Wei Wang, Shan Liu
-
Patent number: 11410295Abstract: A system includes a memory and at least one processor to acquire a hyperspectral image of a food object by an imaging device, the hyperspectral image of the food object comprising a three-dimensional set of images of the food object, each image in the set of images representing the food object in a wavelength range of the electromagnetic spectrum, normalize the hyperspectral image of the food object, select a region of interest in the hyperspectral image, the region of interest comprising a subset of at least one image in the set of images, extract spectral features from the region of interest in the hyperspectral image, and compare the spectral features from the region of interest with a plurality of images in a training set to determine particular characteristics of the food object and determine that the hyperspectral image indicates a foreign object.Type: GrantFiled: December 17, 2020Date of Patent: August 9, 2022Assignee: Apeel Technology, Inc.Inventors: Lars Gustav Magnus Nipe, Abilasha Ramanan
-
Patent number: 11405981Abstract: Routing server communications through a nearby mobile device. In some embodiments, the method may include establishing a direct communication channel between the first mobile device and the second mobile device, determining which of the first mobile device and the second mobile device is currently a more efficient mobile device that is able to communicate with a server device more efficiently, sending a first server query from the less efficient mobile device to the more efficient mobile device over the direct communication channel, forwarding the first server query from the more efficient mobile device to the server device over the Internet, receiving a first server response at the more efficient mobile device from the server device over the Internet, and forwarding the first server response from the more efficient mobile device to the less efficient mobile device over the direct communication channel.Type: GrantFiled: May 18, 2020Date of Patent: August 2, 2022Assignee: NORTONLIFELOCK INC.Inventors: Anand Darak, Sharad Subhash Mhaske
-
Patent number: 11403760Abstract: A system and method to analyze image data. The image data may be used to assist in determine the presence of a feature in the image. The feature may include a bubble.Type: GrantFiled: February 21, 2019Date of Patent: August 2, 2022Assignee: Medtronic Navigation, Inc.Inventors: Christine R. Drown, Andrew Wald, Rebecca L. Vincelette, William A. Grissom
-
Patent number: 11393229Abstract: Methods and systems for artificial intelligence based medical image segmentation are disclosed. In a method for autonomous artificial intelligence based medical image segmentation, a medical image of a patient is received. A current segmentation context is automatically determined based on the medical image and at least one segmentation algorithm is automatically selected from a plurality of segmentation algorithms based on the current segmentation context. A target anatomical structure is segmented in the medical image using the selected at least one segmentation algorithm.Type: GrantFiled: November 24, 2020Date of Patent: July 19, 2022Assignee: Siemens Healthcare GmbHInventors: Shaohua Kevin Zhou, Mingqing Chen, Hui Ding, Bogdan Georgescu, Mehmet Akif Gulsun, Tae Soo Kim, Atilla Peter Kiraly, Xiaoguang Lu, Jin-hyeong Park, Puneet Sharma, Shanhui Sun, Daguang Xu, Zhoubing Xu, Yefeng Zheng
-
Patent number: 11393116Abstract: This invention provides an information processing apparatus which comprises an image acquiring unit configured to acquire images captured by a plurality of image capturing devices, a contour extracting unit configured to extract a contour of an object from the image acquired by the image capturing device, a matching unit configured to match corresponding points on the contours between the images, a depth calculating unit configured to calculate a depth of the matched point, a reliability extracting unit configured to acquire a reliability of the depth based on an angle formed by an epipolar line and a tangential direction of the contour, and a depth correcting unit configured to correct the depth based on the depth and the reliability.Type: GrantFiled: August 27, 2019Date of Patent: July 19, 2022Assignee: CANON KABUSHIKI KAISHAInventor: Masashi Nakagawa
-
Patent number: 11393129Abstract: A method and apparatus for calibrating an image capture device are provided. The method includes capturing one or more of a single or Multiview image set by the image capture device, detecting one or more calibration features in each set by a processor, initializing each of the one or more calibration parameters a corresponding default value, extracting one or more relevant calibration parameters, computing an individual cost term for each of the identified relevant calibration parameters, and scaling each of the relevant cost terms. The method continues with combining all the cost terms once each of the calculated relevant cost terms have been scaled, determining if the combination of the cost terms has been minimized, adjusting the calibration parameters if it is determined that that the combination of the cost terms has not been minimized, and returning to the step of extracting one or more of the relevant calibration parameters.Type: GrantFiled: October 30, 2018Date of Patent: July 19, 2022Assignee: Edge 3 TechnologiesInventors: Tarek El Dokor, Jordan Cluster, Milind Subhash Gide
-
Patent number: 11393068Abstract: A method for interpolating values of an attribute for an image grid may include determining a root value of the attribute for a root node located centrally in the image grid, pre-calculating metadata for multiple child nodes in one or more hierarchical levels based on one or more gradients of the attribute, and deriving values of the attribute for each of the child nodes at each of the hierarchical levels based on the corresponding root value and metadata for the hierarchical level of each child node, wherein each child node may be used as a root node in the next hierarchical level. The image grid may have multiple outer cells arranged radially around a central cell, and the root node may be located in the central cell.Type: GrantFiled: October 29, 2019Date of Patent: July 19, 2022Inventors: Rahul Kumar, Fnu Gurupad, David Tannenbaum
-
Patent number: 11393072Abstract: Systems and methods are disclosed for automatically correcting a rotation of an image. One method comprises receiving an input image to be processed for rotation correction, and providing the input image to a machine learning model configured to predict a rotation angle and an orientation of an image. The machine learning model may comprise a convolutional neural network utilizing one or more rectangle-shaped filters to extract features from the input image. A rotation angle may be determined using a first branch of fully connected layer configured for a regression task of the machine learning model, and an orientation of the image may be determined using a second branch of fully connected layer configured for a classification task of the machine learning model. The input image may then be rotated based on the determined rotation angle and orientation.Type: GrantFiled: June 26, 2020Date of Patent: July 19, 2022Assignee: Adobe Inc.Inventor: Ionut Mironica