公开(公告)号：US20230281981A1

公开(公告)日：2023-09-07

申请号：US18315866

申请日：2023-05-11

Applicant: Huawei Technologies Co., Ltd.

Inventor： Xin DING ,  Deepak SRIDHAR ,  Juwei LU ,  Sidharth SINGLA ,  Peng DAI ,  Xiaofei WU

IPC: G06V10/82 ,  G06V10/776

CPC classification number: G06V10/82 ,  G06V10/776

Abstract: Method and devices for training a keypoint estimation network are described. In each training iteration, synthetic images are generated by a generator, each synthetic image being assigned respective assigned keypoints by the generator. Using a prior-iteration of the keypoint estimation network, a set of predicted keypoints is obtained for each synthetic image. Based on an error score between the predicted keypoints and the assigned keypoints, poor quality synthetic images are discarded. The remaining synthetic images, together with real world images, are used to train an updated keypoint estimation network. The performance of the updated keypoint estimation network is validated, and the training iterations are performed until a convergence criteria is satisfied.

公开(公告)号：US20230350499A1

公开(公告)日：2023-11-02

申请号：US18345794

申请日：2023-06-30

Applicant: Huawei Technologies Co., Ltd.

Inventor： Juwei LU ,  Sayem Mohammad SIAM ,  Deepak SRIDHAR ,  Sidharth SINGLA ,  Yannick VERDIE ,  Xiaofei WU ,  Srikanth MURALIDHARAN ,  Roy YANG ,  Peng DAI ,  Songcen XU

IPC: G06F3/01 ,  G06V40/20 ,  G06V40/10 ,  G06V20/40 ,  G06T7/70

CPC classification number: G06F3/017 ,  G06V40/28 ,  G06V40/10 ,  G06V20/46 ,  G06T7/70 ,  G06T2207/10016

Abstract: Methods and devices for machine vision-based selection of content are described. One or more hands are detected in a current frame of video data. A respective fingertip location is determined for each of up to two of the detected hands. A content selection gesture is determined corresponding to the up to two detected hands. Selected content is extracted, as indicated by the content selection gesture and based on the up to two fingertip locations. The device may be a smartphone, a tablet, a laptop, a smart light device, a reader device, etc.

公开(公告)号：US20230082789A1

公开(公告)日：2023-03-16

申请号：US17950246

申请日：2022-09-22

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Juwei LU ,  Sayem Mohammad SIAM ,  Wei ZHOU ,  Peng DAI ,  Xiaofei WU ,  Songcen XU

IPC: G06F3/01 ,  G06V40/20

Abstract: Methods and systems for gesture-based control of a device are described. An input frame is processed to determine a location of a distinguishing anatomical feature in the input frame. A virtual gesture-space is defined based on the location of the distinguishing anatomical feature, the virtual gesture-space being a defined space for detecting a gesture input. The input frame is processed in only the virtual gesture-space, to detect and track a hand. Using information generated from detecting and tracking the at least one hand, a gesture class is determined for the at least one hand. The device may be a smart television, a smart phone, a tablet, etc.

公开(公告)号：US20220198836A1

公开(公告)日：2022-06-23

申请号：US17689630

申请日：2022-03-08

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Xiaofei WU ,  Fei HUANG ,  Songcen XU ,  Youliang YAN

IPC: G06V40/20 ,  G06V40/10 ,  G06V10/74 ,  G06F3/01

Abstract: A gesture recognition method, an electronic device, a computer-readable storage medium, and a chip, are provided, and relate to the field of artificial intelligence. The gesture recognition method includes: obtaining an image stream, and determining, based on a plurality of consecutive frames of hand images in the image stream, whether a user makes a preparatory action; when the user makes the preparatory action, continuing to obtain an image stream, and determining a gesture action of the user based on a plurality of consecutive frames of hand images in the continuously obtained image stream; and next, further responding to the gesture action to implement gesture interaction with the user. In this application, the preparatory action is determined before gesture recognition is performed, so that erroneous recognition occurring in a gesture recognition process can be reduced, thereby improving a gesture recognition effect.

公开(公告)号：US20210350168A1

公开(公告)日：2021-11-11

申请号：US17383181

申请日：2021-07-22

Applicant: Huawei Technologies Co., Ltd.

Inventor： Zhi TIAN ,  Tong HE ,  Chunhua SHEN ,  Youliang YAN ,  Songcen XU ,  Yiren ZHOU ,  Xiaofei WU ,  Jianzhuang LIU

IPC: G06K9/62 ,  G06K9/46 ,  G06T3/40 ,  G06K9/34 ,  G06N3/08

Abstract: This application discloses an image segmentation method in the field of artificial intelligence. The method includes: obtaining an input image and a processing requirement; performing multi-layer feature extraction on the input image to obtain a plurality of feature maps; downsampling the plurality of feature maps to obtain a plurality of feature maps with a reference resolution, where the reference resolution is less than a resolution of the input image; fusing the plurality of feature maps with the reference resolution to obtain at least one feature map group; upsampling the feature map group by using a transformation matrix W, to obtain a target feature map group; and performing target processing on the target feature map group based on the processing requirement to obtain a target image.

公开(公告)号：US20230401799A1

公开(公告)日：2023-12-14

申请号：US18455507

申请日：2023-08-24

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Zhihao LI ,  Bin SHAO ,  Xiaofei WU ,  Zhensong ZHANG

IPC: G06T19/00 ,  G06T19/20 ,  G06T5/50 ,  G06V10/26 ,  G06V10/74

CPC classification number: G06T19/006 ,  G06T19/20 ,  G06T5/50 ,  G06V10/26 ,  G06V10/761 ,  G06T2219/2004 ,  G06T2219/2016 ,  G06T2207/20221

Abstract: This application provides an augmented reality method, to dynamically associate an orientation of a virtual object with an orientation of a real object. The method in this application includes: obtaining a target image shot by a camera and first location information of a first object in the target image; obtaining second location information of a second object in a three-dimensional coordinate system and third location information of a third object in the three-dimensional coordinate system; obtaining a pose variation of the first object relative to the second object based on the first location information and the second location information; transforming the third location information based on the pose variation, to obtain fourth location information of the third object in the three-dimensional coordinate system; and rendering the third object in the target image based on the fourth location information, to obtain a new target image.

公开(公告)号：US20210012198A1

公开(公告)日：2021-01-14

申请号：US17033316

申请日：2020-09-25

Applicant: Huawei Technologies Co., Ltd. ,  The University of Sydney

Inventor： Weichen ZHANG ,  Wanli OUYANG ,  Dong XU ,  Wen LI ,  Xiaofei WU ,  Jianzhuang LIU ,  Li QIAN

IPC: G06N3/08 ,  G06K9/62 ,  G06N3/04

Abstract: The present disclosure relates to artificial intelligence, and proposes a cooperative adversarial network. A loss function is set at a lower layer of the cooperative adversarial network, and is used to learn a domain discriminating feature. In addition, a cooperative adversarial target function includes the loss function and a domain invariant loss function that is set at a last layer (that is, a higher layer) of the cooperative adversarial network, to learn both the domain discriminating feature and a domain-invariant feature. Further, an enhanced collaborative adversarial network is proposed. Based on the collaborative adversarial network, target domain data is added to training of the collaborative adversarial network, an adaptive threshold is set based on precision of a task model, to select a target domain training sample, network confidence is discriminated based on a domain, and a weight of the target domain training sample is set.