公开(公告)号：US20240338949A1

公开(公告)日：2024-10-10

申请号：US18508904

申请日：2023-11-14

申请人： HYUNDAI MOTOR COMPANY ,  KIA CORPORATION

发明人： Jong Hyun Choi

IPC分类号： G06V20/58 ,  G06V10/24 ,  G06V10/48 ,  G06V10/82

CPC分类号： G06V20/58 ,  G06V10/242 ,  G06V10/48 ,  G06V10/82

摘要： An object recognition apparatus and method for an autonomous vehicle are disclosed. The object recognition apparatus includes a processor and storage. The processor: trains a first network model based on an image; corrects distortion and rotation of the image; generates at least one distorted image based on the corrected image; trains a feature transfer module based on a feature extracted from the corrected image and a feature extracted from the at least one distorted image; inserts the feature transfer module into the first network model; and performs fine-tuning for a second network model including the feature transfer module based on the at least one distorted image.

公开(公告)号：US12106542B2

公开(公告)日：2024-10-01

申请号：US17688848

申请日：2022-03-07

申请人： INTELLIJOINT SURGICAL INC.

发明人： Joseph Arthur Schipper ,  Ryan Visee ,  Andre Novomir Hladio

IPC分类号： G06V10/48 ,  G06T7/20 ,  G06T7/70

CPC分类号： G06V10/48 ,  G06T7/20 ,  G06T7/70 ,  G06V2201/07

摘要： Described are targets for use in optical tracking, as well as related methods. In some implementations, a target comprises a planar surface with an optically detectable pattern thereon, and at least one protrusion extending from the planar surface. In other implementations, a target comprises a planar surface with an optically detectable pattern thereon, with a specular reflective region. The optically detectable pattern provides accurate position information of the target, and provides accurate orientation information of the target about a first axis, but may not provide accurate orientation information of the target about other axes. The at least one protrusion or the specular reflective region provide accurate information of orientation of the target, particularly orientations about axes other than the first axis.

公开(公告)号：US20240282077A1

公开(公告)日：2024-08-22

申请号：US18444492

申请日：2024-02-16

申请人： CANON KABUSHIKI KAISHA

发明人： TAKAMASA TSUNODA

IPC分类号： G06V10/48 ,  G06V10/80 ,  G06V10/98

CPC分类号： G06V10/48 ,  G06V10/80 ,  G06V10/993

摘要： An image processing apparatus includes a feature extractor, a map estimator, a first image estimator, a second image estimator, and an outputter. The feature extractor extracts an intermediate feature from an input image. The map estimator estimates an area map from the intermediate feature. The first image estimator estimates a first image from the intermediate feature. The second image estimator estimates a second image from the intermediate feature. The outputter outputs an output image obtained by, based on the area map, merging the first image and the second image. The second image estimator is trained to obtain desired image quality at a particular area based on the area map in the second image.

公开(公告)号：US12008078B2

公开(公告)日：2024-06-11

申请号：US17446175

申请日：2021-08-27

申请人： Grazper Technologies ApS

发明人： Thomas Jakobsen

IPC分类号： G06T9/00 ,  G06F18/214 ,  G06F18/22 ,  G06F21/60 ,  G06V10/48 ,  G06V10/74 ,  G06V10/774 ,  G06V20/40 ,  G06V20/52

CPC分类号： G06F18/22 ,  G06F18/214 ,  G06F21/602 ,  G06T9/00 ,  G06V10/48 ,  G06V10/74 ,  G06V10/774 ,  G06V20/40 ,  G06V20/52

摘要： Examples relate to a concept for anonymous re-identification, more specifically, but not exclusively, to systems, apparatuses, methods and computer programs for performing anonymous re-identification and for training a machine-learning model for use in anonymous re-identification. An apparatus for re-identification comprises processing circuitry configured to obtain media data via an interface. the processing circuitry is configured to generate a re-identification code representing at least a portion of the media data using a hashing algorithm. The processing circuitry is configured to transform the re-identification code using a transformation functionality to obtain a transformed re-identification code. The transformation functionality is configured to transform the re-identification code such that, if the re-identification code is similar to a further re-identification code generated by the hashing algorithm according to a similarity metric, the transformed re-identification code is similar to a further transformed re-identification code being a transformed version of the further re-identification code. The transformation functionality is configured to transform the re-identification code based on a transformation parameter, with the transformation parameter being dependent on a time and/or a location. The processing circuitry is configured to provide the transformed re-identification code.

公开(公告)号：US11921502B2

公开(公告)日：2024-03-05

申请号：US18151012

申请日：2023-01-06

申请人： NVIDIA Corporation

发明人： Minwoo Park ,  Xiaolin Lin ,  Hae-Jong Seo ,  David Nister ,  Neda Cvijetic

IPC分类号： G05D1/00 ,  G05D1/02 ,  G06F18/214 ,  G06F18/23 ,  G06F18/2411 ,  G06N3/04 ,  G06N3/08 ,  G06V10/44 ,  G06V10/48 ,  G06V10/75 ,  G06V10/764 ,  G06V10/766 ,  G06V10/776 ,  G06V10/82 ,  G06V10/94 ,  G06V20/56

CPC分类号： G05D1/0077 ,  G05D1/0088 ,  G06F18/2155 ,  G06F18/23 ,  G06F18/2411 ,  G06N3/0418 ,  G06V10/457 ,  G06V10/48 ,  G06V10/751 ,  G06V10/764 ,  G06V10/776 ,  G06V10/82 ,  G06V10/955 ,  G06V20/588 ,  G05D2201/0213

摘要： In various examples, systems and methods are disclosed that preserve rich spatial information from an input resolution of a machine learning model to regress on lines in an input image. The machine learning model may be trained to predict, in deployment, distances for each pixel of the input image at an input resolution to a line pixel determined to correspond to a line in the input image. The machine learning model may further be trained to predict angles and label classes of the line. An embedding algorithm may be used to train the machine learning model to predict clusters of line pixels that each correspond to a respective line in the input image. In deployment, the predictions of the machine learning model may be used as an aid for understanding the surrounding environment—e.g., for updating a world model—in a variety of autonomous machine applications.

公开(公告)号：US20230394786A1

公开(公告)日：2023-12-07

申请号：US17829844

申请日：2022-06-01

申请人： Synaptics Incorporated

发明人： Karthikeyan Shanmuga Vadivel ,  Omar Oreifej ,  Patrick A. Worfolk

IPC分类号： G06V10/48 ,  G06V20/70 ,  G06N3/08

CPC分类号： G06V10/48 ,  G06N3/08 ,  G06V20/70

摘要： This disclosure provides methods, devices, and systems for training machine learning models. The present implementations more specifically relate to techniques for automating the annotation of data for training machine learning models. In some aspects, a machine learning system may receive a reference image depicting an object of interest with one or more annotations and also may receive one or more input images depicting the object of interest at various distances, angles, or locations but without annotations. The machine learning system maps a set of points in the reference image to a respective set of points in each input image so that the annotations from the reference image are projected onto the object of interest in each input image. The machine learning system may further train a machine learning model to produce inferences about the object of interest based on the annotated input images.

公开(公告)号：US20230351722A1

公开(公告)日：2023-11-02

申请号：US17796530

申请日：2021-02-01

申请人： U-NICA SYSTEMS AG

发明人： Sergei Startchik ,  Serge Heughebaert

IPC分类号： G06V10/44 ,  G06V10/48 ,  G06V10/426

CPC分类号： G06V10/457 ,  G06V10/48 ,  G06V10/426

摘要： A computer implemented method of skin identification having scales, especially reptile skin identification, includes the steps of acquiring at least one image of a skin portion to be identified, detecting of features corresponding to borders of scales in the image, building a graph of the repetitive pattern scales positions of detected scales, determining the outline of the detected scales and representing the detected scales based on their outline, and determining recognition features data of detected scales for traceable identification of the skin comprising scales. The detection of scales is based on scan lines.

公开(公告)号：US20230245423A1

公开(公告)日：2023-08-03

申请号：US18002690

申请日：2021-06-18

申请人： SONY SEMICONDUCTOR SOLUTIONS CORPORATION

发明人： TAKAHIRO HIRANO

IPC分类号： G06V10/764 ,  G06V10/48

CPC分类号： G06V10/764 ,  G06V10/48 ,  G01S13/867

摘要： The present technique relates to an information processing apparatus, an information processing method, and a program that enable recognition accuracy to be improved while suppressing an increase in load in object recognition using a CNN.
An information processing apparatus: performs, a plurality of times, convolution of an image feature map representing a feature amount of an image of a first frame and generates a convolutional feature map of a plurality of layers; performs deconvolution of a feature map based on the convolutional feature map based on an image of a second frame preceding the first frame and generates a deconvolutional feature map; and performs object recognition based on the convolutional feature map based on an image of the first frame and on the deconvolutional feature map based on an image of the second frame. The present technique can be applied to, for example, a system which performs object recognition.

公开(公告)号：US11682197B2

公开(公告)日：2023-06-20

申请号：US17373615

申请日：2021-07-12

申请人： Insurance Service Office, Inc.

发明人： Bryce Zachary Porter ,  Ryan Mark Justus ,  John Caleb Call

IPC分类号： G06V10/82 ,  G06T3/40 ,  G06T7/60 ,  G06T17/05 ,  G06T7/80 ,  G06V20/10 ,  G06V10/56 ,  G06V10/764 ,  G06V10/48 ,  G06V20/64

CPC分类号： G06V10/82 ,  G06T3/4038 ,  G06T7/60 ,  G06T7/80 ,  G06T17/05 ,  G06V10/48 ,  G06V10/56 ,  G06V10/764 ,  G06V20/176 ,  G06V20/64

摘要： Systems and methods for property feature detection and extraction using digital images. The image sources could include aerial imagery, satellite imagery, ground-based imagery, imagery taken from unmanned aerial vehicles (UAVs), mobile device imagery, etc. The detected geometric property features could include tree canopy, pools and other bodies of water, concrete flatwork, landscaping classifications (gravel, grass, concrete, asphalt, etc.), trampolines, property structural features (structures, buildings, pergolas, gazebos, terraces, retaining walls, and fences), and sports courts. The system can automatically extract these features from images and can then project them into world coordinates relative to a known surface in world coordinates (e.g., from a digital terrain model).

公开(公告)号：US20230011430A1

公开(公告)日：2023-01-12

申请号：US17860680

申请日：2022-07-08

申请人： Samsung Electronics Co., Ltd.

发明人： Jian ZHAO ,  Seungju HAN ,  Feng ZHU ,  Han XU ,  Jingjing HAN ,  Min YANG

IPC分类号： G06V40/16 ,  G06V10/48

摘要： An electronic device includes a memory configured to store instructions, and a processor configured to execute the instructions to configure the processor to obtain a first heat map feature and a first coordinate value feature based on a face image, and detect a face key point based on the first heat map feature and the first coordinate value feature.