Patents by Inventor Guiping WANG
Guiping 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).
-
Patent number: 11917302Abstract: The present disclosure discloses a camera exposure processing method and system. The method includes: obtaining trigger signals, the trigger signals being used to trigger the camera to collect image data and trigger the light source to turn on and off in turn in a fixed sequence; triggering cyclically n light sources to turn on in turn; triggering multiple sensor lines of the camera to perform image acquisition on the object simultaneously; extracting the image data of the exposed object under the turned-on light source collected by the multiple sensor lines to obtain effective data of the object, wherein a sequential lighting order is that after a former light source is cyclically turned on y times, a latter light source is cyclically turned on y times; and splicing all image data of the same position of the object to obtain a spliced image of the object under different light sources.Type: GrantFiled: July 13, 2022Date of Patent: February 27, 2024Assignee: HEFEI I-TEK OPTOELECTRONICS CO., LTD.Inventors: Ning Dong, Guiping Cao, Haixing Sun, Xue Wang
-
Patent number: 11895479Abstract: A method for steering binauralization of audio is provided. The method comprises steps of: receiving (410) an audio input signal, calculating (430) a confidence value indicating a likelihood that a current audio frame of the audio input signal comprises binauralized audio; determining (450) a state signal based on the confidence value; determining (460) a steering signal, based on the first confidence value, the state signal and an energy value of the audio frame; and generating (470) an audio output signal with steered binauralization by processing the audio input signal according to the steering signal.Type: GrantFiled: August 19, 2020Date of Patent: February 6, 2024Assignee: Dolby Laboratories Licensing CorporationInventors: Qingyuan Bin, Libin Luo, Ziyu Yang, Zhiwei Shuang, Xuemei Yu, Guiping Wang
-
Publication number: 20240038258Abstract: A method of audio content identification includes using a two-stage classifier. The first stage includes previously-existing classifiers and the second stage includes a new classifier. The outputs of the first and second stages calculated over different time periods are combined to generate a steering signal. The final classification results from a combination of the steering signal and the outputs of the first and second stages. In this manner, a new classifier may be added without disrupting existing classifiers.Type: ApplicationFiled: August 18, 2021Publication date: February 1, 2024Applicant: Dolby Laboratories Licensing CorporationInventors: Guiping Wang, Lie Lu
-
Patent number: 11570306Abstract: The present disclosure provides a call processing method, apparatus, electronic device and storage medium and relates to the field of cloud computing. The method may comprise: obtaining a calling subscriber's status information in real time while an intelligent dialogue robot is used to make a call with the calling subscriber; when it is determined that a call form of the intelligent dialogue robot needs to be adjusted, correspondingly adjusting the call form of the intelligent dialogue robot according to current status information of the calling subscriber. The solution of the present disclosure may be employed to improve the call performance of the intelligent dialogue robot.Type: GrantFiled: September 3, 2020Date of Patent: January 31, 2023Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Jun Dai, Jinli Dong, Guiping Wang, Guorui Huang
-
Publication number: 20220279300Abstract: A method for steering binauralization of audio is provided. The method comprises steps of: receiving (410) an audio input signal, calculating (430) a confidence value indicating a likelihood that a current audio frame of the audio input signal comprises binauralized audio; determining (450) a state signal based on the confidence value; determining (460) a steering signal, based on the first confidence value, the state signal and an energy value of the audio frame; and generating (470) an audio output signal with steered binauralization by processing the audio input signal according to the steering signal.Type: ApplicationFiled: August 19, 2020Publication date: September 1, 2022Applicant: Dolby Laboratories Licensing CorporationInventors: Qingyuan BIN, Libin LUO, Ziyu YANG, Zhiwei SHUANG, Xuemei YU, Guiping WANG
-
Patent number: 11257194Abstract: A method for image dehazing based on adaptively improved linear global atmospheric light of a dark channel. A haze image in haze weather is first obtained, a variation angle of atmospheric light of the image is obtain through calculating a slope of a connection line between a center and a center of gravity of a binary image of the image, a linear atmospheric light map that varies regularly along a variation direction of the atmospheric light is obtains, a dehazed image is solved through an atmospheric scattering model, and then a processed haze image taken in the haze weather is output.Type: GrantFiled: December 29, 2018Date of Patent: February 22, 2022Assignee: CHANG'AN UNIVERSITYInventors: He Huang, Jing Song, Lu Guo, Guiping Wang, Xinrui Li, Huifeng Wang, Zhe Xu, Bo Cui, Ying Huang, Xiaobin Hui
-
Patent number: 11176482Abstract: Embodiments of training signal processing models for component replacement in signal processing systems are disclosed. A device for training a third signal processing model via a machine learning method include a first calculating unit, a second calculating unit and a training unit. The first calculating unit calculates a first output from each first sample in a first sample set based on a first signal processing model. The second calculating unit calculates a second output from the first sample based on a second signal processing model. The training unit trains a third signal processing model by minimizing a first cost including a first error between the first output and a third output, so that the combination of the second signal processing model and the third signal processing model can simulate the behaviors of the first signal processing model on the first sample set. The third output is an output of the third signal processing model in response to an input including the second output.Type: GrantFiled: May 4, 2016Date of Patent: November 16, 2021Assignee: Dolby Laboratories Licensing CorporationInventors: Guiping Wang, Lie Lu
-
Publication number: 20210075912Abstract: The present disclosure provides a call processing method, apparatus, electronic device and storage medium and relates to the field of cloud computing. The method may comprise: obtaining a calling subscriber's status information in real time while an intelligent dialogue robot is used to make a call with the calling subscriber; when it is determined that a call form of the intelligent dialogue robot needs to be adjusted, correspondingly adjusting the call form of the intelligent dialogue robot according to current status information of the calling subscriber. The solution of the present disclosure may be employed to improve the call performance of the intelligent dialogue robot.Type: ApplicationFiled: September 3, 2020Publication date: March 11, 2021Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Jun DAI, Jinli DONG, Guiping WANG, Guorui HUANG
-
Publication number: 20210049744Abstract: A method for image dehazing based on adaptively improved linear global atmospheric light of a dark channel. A haze image in haze weather is first obtained, a variation angle of atmospheric light of the image is obtain through calculating a slope of a connection line between a center and a center of gravity of a binary image of the image, a linear atmospheric light map that varies regularly along a variation direction of the atmospheric light is obtains, a dehazed image is solved through an atmospheric scattering model, and then a processed haze image taken in the haze weather is output.Type: ApplicationFiled: December 29, 2018Publication date: February 18, 2021Inventors: He Huang, Jing Song, Lu GUO, Guiping WANG, Xinrui LI, Huifeng WANG, Zhe XU, Bo CUI, Ying HUANG, Xiaobin HUI
-
Publication number: 20190276881Abstract: The present invention generally relates to microscopy, and to systems and methods for imaging or determining nucleic acids or other desired targets, for instance, within cells. In certain aspects, a sample is contained within an expandable material, which is expanded and imaged in some fashion. Expansion of the material improves the effective resolution of the subsequent image. This may be combined, for example, with other super-resolution techniques, such as STORM, and/or with techniques such as MERFISH for determining nucleic acids such as mRNA within the sample, for example, by binding nucleic acid probes to the sample. Other aspects are generally directed to compositions or devices for use in such methods, kits for use in such methods, or the like.Type: ApplicationFiled: November 8, 2017Publication date: September 12, 2019Applicant: President and Fellows of Harvard CollegeInventors: Xiaowei Zhuang, Jeffrey R. Moffitt, Guiping Wang
-
Publication number: 20180181880Abstract: Embodiments of training signal processing models for component replacement in signal processing systems are disclosed. A device for training a third signal processing model via a machine learning method include a first calculating unit, a second calculating unit and a training unit. The first calculating unit calculates a first output from each first sample in a first sample set based on a first signal processing model. The second calculating unit calculates a second output from the first sample based on a second signal processing model. The training unit trains a third signal processing model by minimizing a first cost including a first error between the first output and a third output, so that the combination of the second signal processing model and the third signal processing model can simulate the behaviors of the first signal processing model on the first sample set. The third output is an output of the third signal processing model in response to an input including the second output.Type: ApplicationFiled: May 4, 2016Publication date: June 28, 2018Applicant: Dolby Laboratories Licensing CorporationInventors: Guiping WANG, Li LU