Patents by Inventor Xianghan WANG

Xianghan WANG has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • MULTI-GRANULARITY PERCEPTION INTEGRATED LEARNING METHOD, DEVICE, COMPUTER EQUIPMENT AND MEDIUM
    Publication number: 20230385597
    Abstract: Disclosed are a multi-granularity perception integrated learning method, a device, a computer equipment and a storage medium.
    Type: Application
    Filed: March 16, 2023
    Publication date: November 30, 2023
    Inventors: Xianqiang ZHU, Xueqin HUANG, Cheng ZHU, Xianghan WANG, Bin LIU, Yun ZHOU, Zhaoyun DING, Yuanyuan GUO
  • Method and system for hand pose recognition, device and storage medium
    Patent number: 11688098
    Abstract: The disclosure relates to a method and a system for hand pose recognition, a device and a storage medium are disclosed in embodiments of the disclosure. The method includes: capturing a RGB image of a hand from a RGB camera and capturing a depth image of the hand from an active depth camera, so as to obtain a hand pose data set according to the RGB image and the depth image; processing the hand pose data set to obtain a 3D joint position, and taking the 3D joint position as a data set for training a software model; extracting the RGB image by a feature extractor based on a depth neural network to obtain a feature map of a hand pose; and processing the feature map according to an attention mechanism to obtain a global feature map of the hand pose.
    Type: Grant
    Filed: September 2, 2022
    Date of Patent: June 27, 2023
    Assignee: National University of Defense Technology
    Inventors: Jie Jiang, Yang Liu, Xianghan Wang, Jiahao Sun, Junyan Yang, Yixiang He, Liang Bai, Lai Kang, Yingmei Wei, Yuxiang Xie
  • METHOD AND SYSTEM FOR HAND POSE RECOGNITION, DEVICE AND STORAGE MEDIUM
    Publication number: 20230116029
    Abstract: The disclosure relates to a method and a system for hand pose recognition, a device and a storage medium are disclosed in embodiments of the disclosure. The method includes: capturing a RGB image of a hand from a RGB camera and capturing a depth image of the hand from an active depth camera, so as to obtain a hand pose data set according to the RGB image and the depth image; processing the hand pose data set to obtain a 3D joint position, and taking the 3D joint position as a data set for training a software model; extracting the RGB image by a feature extractor based on a depth neural network to obtain a feature map of a hand pose; and processing the feature map according to an attention mechanism to obtain a global feature map of the hand pose.
    Type: Application
    Filed: September 2, 2022
    Publication date: April 13, 2023
    Inventors: Jie JIANG, Yang LIU, Xianghan WANG, Jiahao SUN, Junyan YANG, Yixiang HE, Liang BAI, Lai KANG, Yingmei WEI, Yuxiang XIE