Patents by Inventor Yongzhen Huang

Yongzhen Huang 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).

  • Publication number: 20210164676
    Abstract: Systems and methods for controlling an air-conditioning system based on gait recognition. The system includes a communication interface configured to receive sensor data captured of a scene by a sensor. The system further includes a storage configured to store the sensor data and a profile of registered users. The system also includes at least one processor. The at least one processor is configured to identify a human object within the sensor data. The processor is further configured to recognize gait features of the identified human object. The processor is also configured to generate a first instruction controlling the air-conditioning system based on the recognized gait features.
    Type: Application
    Filed: December 20, 2018
    Publication date: June 3, 2021
    Applicant: WATRIX TECHNOLOGY CORPORATION LIMITED
    Inventors: Yongzhen HUANG, Daoliang TAN, Yuqi ZHANG
  • Patent number: 10540768
    Abstract: A method of segmenting an object from an image includes receiving an input image including an object; generating an output image corresponding to the object from the input image using an image model; and extracting an object image from the output image.
    Type: Grant
    Filed: July 22, 2016
    Date of Patent: January 21, 2020
    Assignees: SAMSUNG ELECTRONICS CO., LTD., INSTITUTE OF AUTOMATION CHINESE ACADEMY OF SCIENCES
    Inventors: Byungin Yoo, Jungbae Kim, Chang Kyu Choi, Jaejoon Han, Yongzhen Huang, Liang Wang
  • Patent number: 10223582
    Abstract: The present disclosure relates to a gait recognition method based on deep learning, which comprises recognizing an identity of a person in a video according to the gait thereof through dual-channel convolutional neural networks sharing weights by means of the strong learning capability of the deep learning convolutional neural network. Said method is quite robust to gait changes across a large view, which can effectively solve the problem of low precision in cross-view gait recognition existing with the prior art gait recognition technology. Said method can be widely used in scenarios having video monitors, such as security monitoring in airports and supermarkets, person recognition, criminal detection, etc.
    Type: Grant
    Filed: October 28, 2014
    Date of Patent: March 5, 2019
    Assignee: Watrix Technology
    Inventors: Tieniu Tan, Liang Wang, Yongzhen Huang, Zifeng Wu
  • Patent number: 10096121
    Abstract: A human-shape image segmentation method comprising: extracting multi-scale context information for all first pixel points for training a human-shape image; sending image blocks of all scales of all the first pixel points into a same convolution neural network to form a multi-channel convolutional neural network group, wherein each channel corresponds to image blocks of one scale; training the neural network group using a back propagation algorithm to obtain human-shape image segmentation training model data; extracting multi-scale context information for all second pixels points for testing the human-shape image; sending image blocks of different scales of each of the second pixel points into a neural network channel corresponding to the human-shape image segmentation training model, wherein if said first probability is larger than said second probability, the second pixel points belong to the human-shape region, otherwise, the second pixel points are outside of the human-shape region.
    Type: Grant
    Filed: May 23, 2014
    Date of Patent: October 9, 2018
    Assignee: Watrix Technology
    Inventors: Tieniu Tan, Yongzhen Huang, Liang Wang, Zifeng Wu
  • Publication number: 20170243058
    Abstract: The present disclosure relates to a gait recognition method based on deep learning, which comprises recognizing an identity of a person in a video according to the gait thereof through dual-channel convolutional neural networks sharing weights by means of the strong learning capability of the deep learning convolutional neural network. Said method is quite robust to gait changes across a large view, which can effectively solve the problem of low precision in cross-view gait recognition existing with the prior art gait recognition technology. Said method can be widely used in scenarios having video monitors, such as security monitoring in airports and supermarkets, person recognition, criminal detection, etc.
    Type: Application
    Filed: October 28, 2014
    Publication date: August 24, 2017
    Inventors: Tieniu TAN, Liang WANG, Yongzhen HUANG, Zifeng WU
  • Publication number: 20170200274
    Abstract: A human-shape image segmentation method comprising: extracting multi-scale context information for all first pixel points for training a human-shape image; sending image blocks of all scales of all the first pixel points into a same convolution neural network to form a multi-channel convolutional neural network group, wherein each channel corresponds to image blocks of one scale; training the neural network group using a back propagation algorithm to obtain human-shape image segmentation training model data; extracting multi-scale context information for all second pixels points for testing the human-shape image; sending image blocks of different scales of each of the second pixel points into a neural network channel corresponding to the human-shape image segmentation training model, wherein if said first probability is larger than said second probability, the second pixel points belong to the human-shape region, otherwise, the second pixel points are outside of the human-shape region.
    Type: Application
    Filed: May 23, 2014
    Publication date: July 13, 2017
    Inventors: Tieniu TAN, Yongzhen HUANG, Liang WANG, Zifeng WU
  • Publication number: 20170091951
    Abstract: A method of segmenting an object from an image includes receiving an input image including an object; generating an output image corresponding to the object from the input image using an image model; and extracting an object image from the output image.
    Type: Application
    Filed: July 22, 2016
    Publication date: March 30, 2017
    Applicants: Samsung Electronics Co., Ltd., Institute of Automation Chinese Academy of Sciences
    Inventors: Byungin Yoo, Jungbae Kim, Chang Kyu Choi, Jaejoon Han, Yongzhen Huang, Liang Wang
  • Patent number: 8732172
    Abstract: A shape classification method based on the topological perceptual organization (TPO) theory, comprising steps of: extracting boundary points of shapes (S1); constructing topological space and computing the representation of extracted boundary points (S2); extracting global features of shapes from the representation of boundary points in topological space (S3); extracting local features of shapes from the representation of boundary points in Euclidean space (S4); combining global features and local features through adjusting the weight of local features according to the performance of global features (S5); classifying shapes using the combination of global features and local features (S6). The invention is applicable for intelligent video surveillance, e.g., objects classification and scene understanding. The invention can also be used for the automatic driving system wherein robust recognition of traffic signs plays an important role in enhancing the intelligence of the system.
    Type: Grant
    Filed: May 13, 2010
    Date of Patent: May 20, 2014
    Assignee: Institute of Automation, Chinese Academy of Sciences
    Inventors: Tieniu Tan, Kaiqi Huang, Yongzhen Huang
  • Publication number: 20130046762
    Abstract: A shape classification method based on the topological perceptual organization (TPO) theory, comprising steps of: extracting boundary points of shapes (S1); constructing topological space and computing the representation of extracted boundary points (S2); extracting global features of shapes from the representation of boundary points in topological space (S3); extracting local features of shapes from the representation of boundary points in Euclidean space (S4); combining global features and local features through adjusting the weight of local features according to the performance of global features (S5); classifying shapes using the combination of global features and local features (S6). The invention is applicable for intelligent video surveillance, e.g., objects classification and scene understanding. The invention can also be used for the automatic driving system wherein robust recognition of traffic signs plays an important role in enhancing the intelligence of the system.
    Type: Application
    Filed: May 13, 2010
    Publication date: February 21, 2013
    Applicant: Institute of Automation, Chinese Academy of Sciences
    Inventors: Tieniu Tan, Kaiqi Huang, Yongzhen Huang
  • Publication number: 20080310474
    Abstract: A square micro-cavity laser with an output waveguide comprises: a substrate; a resonator, which has a square shape and is fabricated on the substrate; a stripe output waveguide, which is fabricated on the substrate and is connected to the midpoint of one side face of the resonator; wherein the area of the resonator or the stripe output waveguide is less than that of the substrate.
    Type: Application
    Filed: June 12, 2008
    Publication date: December 18, 2008
    Inventors: Yongzhen Huang, Wei Zhao
  • Patent number: 6763052
    Abstract: A semiconductor laser with an equilateral triangle micro optical resonator has an output waveguide connected to the resonator for realizing directional emission, and the laser wafer structure is the slab waveguide constituted by lower cladding layer, active region and the upper cladding layer. The outer region of the equilateral triangle is etched to the lower cladding layer or substrate, while the unetched equilateral triangle region is used as the resonator, and the triangular sides serve as the reflecting mirrors. On one of the vertices or the sides of the triangle resonator connected or coupled an output waveguide can form an edge emission semiconductor laser and array having directive light emission.
    Type: Grant
    Filed: October 16, 2002
    Date of Patent: July 13, 2004
    Assignee: Institute of Semiconductors, Chinese Academy of Sciences
    Inventor: Yongzhen Huang
  • Publication number: 20030123515
    Abstract: A semiconductor laser with an equilateral triangle micro optical resonator has an output waveguide connected to the resonator for realizing directional emission, and the laser wafer structure is the slab waveguide constituted by lower cladding layer, active region and the upper cladding layer. The outer region of the equilateral triangle is etched to the lower cladding layer or substrate, while the unetched equilateral triangle region is used as the resonator, and the triangular sides serve as the reflecting mirrors. On one of the vertices or the sides of the triangle resonator connected or coupled an output waveguide can form an edge emission semiconductor laser and array having directive light emission.
    Type: Application
    Filed: October 16, 2002
    Publication date: July 3, 2003
    Inventor: Yongzhen Huang