公开(公告)号：US11972545B2

公开(公告)日：2024-04-30

申请号：US17482998

申请日：2021-09-23

Applicant: Intel Corporation

Inventor： Anbang Yao ,  Ming Lu ,  Yikai Wang ,  Shandong Wang ,  Yurong Chen ,  Sungye Kim ,  Attila Tamas Afra

IPC: G06T5/50 ,  G06N3/02 ,  G06T7/13 ,  G06V40/16

CPC classification number: G06T5/50 ,  G06N3/02 ,  G06T7/13 ,  G06V40/161 ,  G06V40/171 ,  G06T2207/20084 ,  G06T2207/30201

Abstract: The present disclosure provides an apparatus and method of guided neural network model for image processing. An apparatus may comprise a guidance map generator, a synthesis network and an accelerator. The guidance map generator may receive a first image as a content image and a second image as a style image, and generate a first plurality of guidance maps and a second plurality of guidance maps, respectively from the first image and the second image. The synthesis network may synthesize the first plurality of guidance maps and the second plurality of guidance maps to determine guidance information. The accelerator may generate an output image by applying the style of the second image to the first image based on the guidance information.

公开(公告)号：US20230298204A1

公开(公告)日：2023-09-21

申请号：US18000389

申请日：2020-06-26

Applicant: Intel Corporation

Inventor： Shandong Wang ,  Yangyuxuan Kang ,  Anbang Yao ,  Ming Lu ,  Yurong Chen

IPC: G06T7/73 ,  G06T17/00

CPC classification number: G06T7/74 ,  G06T17/00 ,  G06T2207/20084 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/30244 ,  G06T2207/30196

Abstract: Apparatus and methods for three-dimensional pose estimation are disclosed herein. An example apparatus includes an image synchronizer to synchronize a first image generated by a first image capture device and a second image generated by a second image capture device, the first image and the second image including a subject; a two-dimensional pose detector to predict first positions of keypoints of the subject based on the first image and by executing a first neural network model to generate first two-dimensional data and predict second positions of the keypoints based on the second image and by executing the first neural network model to generate second two-dimensional data; and a three-dimensional pose calculator to generate a three-dimensional graphical model representing a pose of the subject in the first image and the second image based on the first two-dimensional data, the second two-dimensional data, and by executing a second neural network model.

公开(公告)号：US11763467B2

公开(公告)日：2023-09-19

申请号：US17255837

申请日：2018-09-28

Applicant: INTEL CORPORATION

Inventor： Xiaofeng Tong ,  Chen Ling ,  Ming Lu ,  Qiang Li ,  Wenlong Li ,  Yikai Fang ,  Yumeng Wang

IPC: G06T7/70 ,  G06T7/292 ,  G06T7/215 ,  H04N7/18 ,  G06V20/40 ,  G06V20/52 ,  G06F18/22

CPC classification number: G06T7/292 ,  G06F18/22 ,  G06T7/215 ,  G06T7/70 ,  G06V20/40 ,  G06V20/52 ,  H04N7/181 ,  G06T2207/20084 ,  G06T2207/30224

Abstract: A multi-camera architecture for detecting and tracking a ball in real-time. The multi-camera architecture includes network interface circuitry to receive a plurality of real-time videos taken from a plurality of high-resolution cameras. Each of the high-resolution cameras simultaneously captures a sports event, wherein each of the plurality of high-resolution cameras includes a viewpoint that covers an entire playing field where the sports event is played. The multi-camera architecture further includes one or more processors coupled to the network interface circuitry and one or more memory devices coupled to the one or more processors. The one or more memory devices includes instructions to determine the location of the ball for each frame of the plurality of real-time videos, which when executed by the one or more processors, cause the multi-camera architecture to simultaneously perform one of a detection scheme or a tracking scheme on a frame from each of the plurality of real-time videos to detect the ball used in the sports event and perform a multi-camera build to determine a location of the ball in 3D for the frame from each of the plurality of real-time videos using one of detection or tracking results for each of the cameras.

公开(公告)号：US11669718B2

公开(公告)日：2023-06-06

申请号：US16609732

申请日：2018-05-22

Applicant: INTEL CORPORATION

Inventor： Anbang Yao ,  Hao Zhao ,  Ming Lu ,  Yiwen Guo ,  Yurong Chen

IPC: G06V10/82 ,  G06N3/063 ,  G06N3/04 ,  G06N3/08 ,  G06F18/214 ,  G06V10/764 ,  G06V10/44 ,  G06V20/70 ,  G06V10/94 ,  G06V20/10 ,  G06V20/40

CPC classification number: G06N3/063 ,  G06F18/214 ,  G06N3/04 ,  G06N3/08 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  G06V10/955 ,  G06V20/10 ,  G06V20/41 ,  G06V20/70

Abstract: Methods and apparatus for discrimitive semantic transfer and physics-inspired optimization in deep learning are disclosed. A computation training method for a convolutional neural network (CNN) includes receiving a sequence of training images in the CNN of a first stage to describe objects of a cluttered scene as a semantic segmentation mask. The semantic segmentation mask is received in a semantic segmentation network of a second stage to produce semantic features. Using weights from the first stage as feature extractors and weights from the second stage as classifiers, edges of the cluttered scene are identified using the semantic features.

公开(公告)号：US20220207656A1

公开(公告)日：2022-06-30

申请号：US17483074

申请日：2021-09-23

Applicant: Intel Corporation

Inventor： Anbang Yao ,  Ming Lu ,  Yikai Wang ,  Yurong Chen ,  Attila Tamas Afra ,  Sungye Kim ,  Karthik Vaidyanathan

IPC: G06T5/00 ,  G06N20/10 ,  G06N3/08

Abstract: Embodiments are generally directed to a Conditional Kernel Prediction Network (CKPN) for image and video de-noising and other related image and video processing applications. Disclosed is an embodiment of a method for de-noising an image or video frame by a convolutional neural network implemented on a compute engine, the image including a plurality of pixels, the method comprising: for each of the plurality of pixels of the image, generating a convolutional kernel having a plurality of kernel weights for the pixel, the plurality of kernel weights respectively corresponding to pixels within a region surrounding the pixel; adjusting the plurality of kernel weights of the convolutional kernel for the pixel based on convolutional kernels generated respectively for the corresponding pixels within the region surrounding the pixel; and filtering the pixel with the adjusted plurality of kernel weights and pixel values of the corresponding pixels within the region surrounding the pixel to obtain a de-noised pixel.

公开(公告)号：US11188794B2

公开(公告)日：2021-11-30

申请号：US16630419

申请日：2017-08-10

Applicant: INTEL CORPORATION

Inventor： Anbang Yao ,  Tao Kong ,  Ming Lu ,  Yiwen Guo ,  Yurong Chen

IPC: G06K9/62 ,  G06K9/20 ,  G06N3/04 ,  G06N3/08

Abstract: A convolutional neural network framework is described that uses reverse connection and obviousness priors for object detection. A method includes performing a plurality of layers of convolutions and reverse connections on a received image to generate a plurality of feature maps, determining an objectness confidence for candidate bounding boxes based on outputs of an objectness prior, determining a joint loss function for each candidate bounding box by combining an objectness loss, a bounding box regression loss and a classification loss, calculating network gradients over positive boxes and negative boxes, updating network parameters within candidate bounding boxes using the joint loss function, repeating performing the convolutions through to updating network parameters until the training converges, and outputting network parameters for object detection based on the training images.

公开(公告)号：US10818064B2

公开(公告)日：2020-10-27

申请号：US16327779

申请日：2016-09-21

Applicant: Intel Corporation

Inventor： Shandong Wang ,  Ming Lu ,  Anbang Yao ,  Yurong Chen

IPC: G06T13/40 ,  G06T17/00 ,  G06F3/01 ,  G06T15/04 ,  G06T15/10

Abstract: Techniques related to estimating accurate face shape and texture from an image having a representation of a human face are discussed. Such techniques may include determining shape parameters that optimize a linear spatial cost model based on 2D landmarks, 3D landmarks, and camera and pose parameters, determining texture parameters that optimize a linear texture estimation cost model, and refining the shape parameters by optimizing a nonlinear pixel intensity cost function.