Patents by Inventor Chengtao ZHOU

Chengtao ZHOU 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).

  • Patent number: 12294773
    Abstract: A method and an apparatus for generating a video digest, and a readable storage medium are provided. The method is applied to a video acquisition device that includes a hardware unit configured to obtain movement information in real time, the movement information includes speed information and direction information of the video acquisition device. The method includes: starting acquisition of a video signal in response to an acquisition start instruction, and recording movement information corresponding to each frame during the acquisition of the video signal; determining a frequency for key frame extraction according to the movement information corresponding to each frame; determining a key frame from the acquired video signal according to the frequency for key frame extraction; and in response to an acquisition end instruction, generating a video digest according to the key frame.
    Type: Grant
    Filed: April 24, 2023
    Date of Patent: May 6, 2025
    Assignee: SHENZHEN MICROBT ELECTRONICS TECHNOLOGY CO., LTD.
    Inventors: Chengtao Zhou, Le Zhang, Zuoxing Yang
  • Patent number: 12149817
    Abstract: An image processing method includes determining a target object in a to-be-photographed scene, determining a preview image based on the target object, a zoom ratio specified by a user, and an original image that is captured by a sensor of a terminal when the terminal uses a target lens to perform photographing at the zoom ratio, and displaying the preview image on a display of the terminal. The preview image may be displayed in a single preview region, or displayed in a plurality of preview regions that are formed in combination with an auxiliary preview image.
    Type: Grant
    Filed: September 20, 2022
    Date of Patent: November 19, 2024
    Assignee: HUAWEI TECHNOLOIGES CO., LTD.
    Inventors: Yinting Wang, Chengtao Zhou, Xi Zhang, Yining Huang
  • Publication number: 20240334027
    Abstract: A method and an apparatus for generating a video digest, and a readable storage medium are provided. The method is applied to a video acquisition device that includes a hardware unit configured to obtain movement information in real time, the movement information includes speed information and direction information of the video acquisition device. The method includes: starting acquisition of a video signal in response to an acquisition start instruction, and recording movement information corresponding to each frame during the acquisition of the video signal; determining a frequency for key frame extraction according to the movement information corresponding to each frame; determining a key frame from the acquired video signal according to the frequency for key frame extraction; and in response to an acquisition end instruction, generating a video digest according to the key frame.
    Type: Application
    Filed: April 24, 2023
    Publication date: October 3, 2024
    Applicant: SHENZHEN MICROBT ELECTRONICS TECHNOLOGY CO., LTD.
    Inventors: Chengtao ZHOU, Le ZHANG, Zuoxing YANG
  • Patent number: 11882357
    Abstract: An image display method and device are provided. The method is applied to an electronic device having a display screen and a camera. The method includes: detecting a first operation of turning on the camera by a user; displaying a photographing interface on the display screen in response to the first operation, where the photographing interface includes a viewfinder frame including a first image; detecting a second operation of the camera indicated by the user; and displaying a second image in the viewfinder frame in response to the second operation, where the second image is an image obtained by processing N frames of raw images captured by the camera; a neural network model is applied to a processing process, and the neural network model uses an image whose noise is lower than a target threshold as an output objective; and N is an integer greater than or equal to 2.
    Type: Grant
    Filed: September 24, 2021
    Date of Patent: January 23, 2024
    Assignee: HUAWEI TECHNOLOGIES CO., LTD.
    Inventors: Chengtao Zhou, Qianwen Zhu, Yinting Wang
  • Publication number: 20230019164
    Abstract: A method for detecting a complexity of a traveling scenario of a vehicle includes obtaining a travelling speed of the vehicle and a travelling speed of a target vehicle, determining, based on the traveling speed of the vehicle and the traveling speed of the target vehicle, a dynamic complexity of a traveling scenario in which the vehicle is located, determining static information of each static factor in the traveling scenario in which the vehicle is currently located, obtaining, based on the static information of each static factor, a static complexity of the traveling scenario in which the vehicle is located, and obtaining, based on the dynamic complexity and the static complexity, a comprehensive complexity of the traveling scenario in which the vehicle is located.
    Type: Application
    Filed: September 20, 2022
    Publication date: January 19, 2023
    Inventors: Yinting Wang, Chengtao Zhou, Xi Zhang, Yining Huang
  • Publication number: 20220210308
    Abstract: Embodiments of this application disclose an image processing method and an electronic apparatus, to process a video image based on photographing environment brightness. The image processing method includes: detecting photographing environment brightness during video photographing; and when the photographing environment brightness is less than a preset threshold, processing a video image by using a neural network; or when the photographing environment brightness is greater than or equal to a preset threshold, processing a video image by using a preset denoising method, where the preset denoising method does not include a neural network architecture. A neural network in the artificial intelligence (artificial intelligence, AI) field requires a large quantity of computing units. This causes power consumption. According to the foregoing image processing method, a video image processing effect can be improved while power consumption of a terminal is ensured.
    Type: Application
    Filed: March 18, 2022
    Publication date: June 30, 2022
    Applicant: HUAWEI TECHNOLOGIES CO., LTD.
    Inventors: Wei ZHOU, Chengtao ZHOU, Yining HUANG
  • Patent number: 11363187
    Abstract: Examples in this application disclose a focusing method and apparatus applied to a terminal device, and the terminal device. One example method includes detecting whether a current frame includes a target object, where the target object is one of preset objects on which focusing needs to be performed. When the current frame includes the target object, a determination is made as to whether the target object is in a motion state. When the target object is in the motion state, tracking focusing is performed by using phase detection PD information with a variable filtering length. When the target object is in a static state, stable focusing is performed by using PD information obtained in an adaptive fixed PD configuration mode.
    Type: Grant
    Filed: April 9, 2021
    Date of Patent: June 14, 2022
    Assignee: Huawei Technologies Co., Ltd.
    Inventors: Cong Chen, Chengtao Zhou, Yongyi Wang, Kenji Ishibashi
  • Publication number: 20220014684
    Abstract: An image display method and device are provided. The method is applied to an electronic device having a display screen and a camera. The method includes: detecting a first operation of turning on the camera by a user; displaying a photographing interface on the display screen in response to the first operation, where the photographing interface includes a viewfinder frame including a first image; detecting a second operation of the camera indicated by the user; and displaying a second image in the viewfinder frame in response to the second operation, where the second image is an image obtained by processing N frames of raw images captured by the camera; a neural network model is applied to a processing process, and the neural network model uses an image whose noise is lower than a target threshold as an output objective; and N is an integer greater than or equal to 2.
    Type: Application
    Filed: September 24, 2021
    Publication date: January 13, 2022
    Inventors: Chengtao ZHOU, Qianwen ZHU, Yinting WANG
  • Publication number: 20210227147
    Abstract: Embodiments of this application disclose a focusing method and apparatus applied to a terminal device, and the terminal device. The method includes: detecting whether a current frame includes a target object, where the target object is one of preset objects on which focusing needs to be performed; when the current frame includes the target object, determining whether the target object is in a motion state; when the target object is in the motion state, performing tracking focusing by using phase detection PD information with a variable filtering length; and when the target object is in a static state, performing stable focusing by using PD information obtained in an adaptive fixed PD configuration mode.
    Type: Application
    Filed: April 9, 2021
    Publication date: July 22, 2021
    Inventors: Cong CHEN, Chengtao ZHOU, Yongyi WANG, Kenji ISHIBASHI