Patents by Inventor Shimin Hu
Shimin Hu 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: 11776097Abstract: Methods, devices, and storage medium for fusing at least one image are disclosed. The method includes obtaining a first to-be-fused image and a second to-be-fused image, the first to-be-fused image comprising first regions, and the second to-be-fused image comprising second regions; obtaining a first feature set according to the first to-be-fused image and obtaining a second feature set according to the second to-be-fused image; performing first fusion processing on the first to-be-fused image and the second to-be-fused image by using a shape fusion network model to obtain a third to-be-fused image, the third to-be-fused image comprising at least one first encoding feature and at least one second encoding feature; and performing second fusion processing on the third to-be-fused image and the first to-be-fused image by using a condition fusion network model to obtain a target fused image. Model training methods, apparatus, and storage medium are also disclosed.Type: GrantFiled: June 2, 2021Date of Patent: October 3, 2023Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Haozhi Huang, Senzhe Xu, Shimin Hu, Wei Liu
-
Patent number: 11754729Abstract: The present disclosure provides a nuclear detection simulation device based on a nanosecond light source and a nuclear signal inversion technology. Electronic circuits and nuclear pulse current signals are used to drive blue LEDs to emit nuclear pulse optical signals, so as to simulate a scintillator to receive ? radiation to emit light, and can simulate point sources and area sources, organic scintillator detectors and inorganic scintillators, scintillation efficiency and detection efficiency, radioactive sources, fast components and slow components, multi-type nuclear pulse signals, a statistical fluctuation phenomenon of nuclear pulses, the electron pair effect, the Compton effect, the photoelectric effect, and self-radiation of the scintillator, generate single or piled-up pulse signals, corresponding energy spectrum curves, and an environmental background spectral line. 3D visualization configuration and a nuclear signal detection process can be subjected to animated demonstration.Type: GrantFiled: April 20, 2022Date of Patent: September 12, 2023Assignee: Chengdu University of TechnologyInventors: Guoqiang Zeng, Chuanhao Hu, Qing Li, Min Gu, Xiaofeng Yang, Shimin Hu, Jian Yang
-
Publication number: 20230010244Abstract: The present disclosure provides a nuclear detection simulation device based on a nanosecond light source and a nuclear signal inversion technology. Electronic circuits and nuclear pulse current signals are used to drive blue LEDs to emit nuclear pulse optical signals, so as to simulate a scintillator to receive ? radiation to emit light, and can simulate point sources and area sources, organic scintillator detectors and inorganic scintillators, scintillation efficiency and detection efficiency, radioactive sources, fast components and slow components, multi-type nuclear pulse signals, a statistical fluctuation phenomenon of nuclear pulses, the electron pair effect, the Compton effect, the photoelectric effect, and self-radiation of the scintillator, generate single or piled-up pulse signals, corresponding energy spectrum curves, and an environmental background spectral line. 3D visualization configuration and a nuclear signal detection process can be subjected to animated demonstration.Type: ApplicationFiled: April 20, 2022Publication date: January 12, 2023Inventors: Guoqiang ZENG, Chuanhao HU, Qing LI, Min GU, Xiaofeng YANG, Shimin HU, Jian YANG
-
Publication number: 20230008042Abstract: The present disclosure provides a multi-parameter calibration system for a spectrometer based on a nanosecond light source, including a main channel for outputting nuclear pulse signals, and a coincidence channel for outputting the nuclear pulse signals. Each channel uses current nuclear pulse signals to drive a light-emitting diode (LED) to emit nuclear pulse optical signals, and a simulated scintillator is irradiated to emit nanosecond nuclear pulse optical signals. The present disclosure can respectively test and calibrate multiple parameter performance indexes of the spectrometer throughput baseline restoration spectrometer. The stability of the spectrometer is tested and calibrated through output of certain regular nuclear pulse signals.Type: ApplicationFiled: April 20, 2022Publication date: January 12, 2023Inventors: Guoqiang ZENG, Min GU, Qing LI, Chuanhao HU, Xiaofeng YANG, Shimin HU, Jian YANG
-
Publication number: 20210295483Abstract: Methods, devices, and storage medium for fusing at least one image are disclosed. The method includes obtaining a first to-be-fused image and a second to-be-fused image, the first to-be-fused image comprising first regions, and the second to-be-fused image comprising second regions; obtaining a first feature set according to the first to-be-fused image and obtaining a second feature set according to the second to-be-fused image; performing first fusion processing on the first to-be-fused image and the second to-be-fused image by using a shape fusion network model to obtain a third to-be-fused image, the third to-be-fused image comprising at least one first encoding feature and at least one second encoding feature; and performing second fusion processing on the third to-be-fused image and the first to-be-fused image by using a condition fusion network model to obtain a target fused image. Model training methods, apparatus, and storage medium are also disclosed.Type: ApplicationFiled: June 2, 2021Publication date: September 23, 2021Applicant: Tencent Technology (Shenzhen) Company LimitedInventors: Haozhi HUANG, Senzhe XU, Shimin HU, Wei LIU
-
Patent number: 10325181Abstract: An image classification method is provided. The method includes: inputting a to-be-classified image into a plurality of neural network models; obtaining data output by multiple non-input layers specified by each neural network model to generate a plurality of image features corresponding to the plurality of neural network models; respectively inputting the plurality of corresponding image features into linear classifiers, each of the linear classifiers being trained by one of the plurality of neural network models for determining whether an image belongs to a preset class; obtaining, using each neural network model, a corresponding probability that the to-be-classified image comprises an object image of the preset class; and determining, according to each obtained probability, whether the to-be-classified image includes the object image of the preset class.Type: GrantFiled: September 13, 2017Date of Patent: June 18, 2019Assignees: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, TSINGHUA UNIVERSITYInventors: Kun Xu, Xiaowei Guo, Feiyue Huang, Ruixin Zhang, Juhong Wang, Shimin Hu, Bin Liu
-
Patent number: 10091484Abstract: The present invention discloses a method for acquiring a comfort degree of a motion-sensing binocular stereoscopic video. The method includes the following steps: S1. carrying out binocular parallax and movement speed analysis on an input binocular video, and calculating a binocular parallax d, a movement speed vxy in a visual plane direction and a movement speed vz in a depth direction of each pixel point in the video; S2. calculating a corresponding comfort degree value c according to the parameters (d, vxy, vz) of the pixel point; S3. calculating the comfort degree value of the entire frame according to the calculated comfort degree value of each pixel point; S4. calculating the comfort degree value of the entire video according to the comfort degree value of each frame.Type: GrantFiled: December 25, 2013Date of Patent: October 2, 2018Assignee: TSINGHUA UNIVERSITYInventors: Shimin Hu, Songpei Du, Masia Belen, Gutierrez Diego
-
Patent number: 10074164Abstract: Provided are a method and an apparatus for adjusting image brightness. The method includes: acquiring a single-channel brightness image based on grayscales of each channel of an image to be processed; performing Gaussian filtering on the single-channel brightness image to acquire a Gaussian filtered image; adjusting grayscales of the Gaussian filtered image based on the grayscales of the Gaussian filtered image and a preset proportion; acquiring a grayscale change rate of each pixel with respect to the Gaussian filtered image after adjustment and the Gaussian filtered image before adjustment; and processing the image to be processed based on the grayscale change rate of each pixel to acquire a processed image.Type: GrantFiled: October 17, 2017Date of Patent: September 11, 2018Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Shimin Hu, Jianyu Wang, Baoli Li, Haifeng Deng, Xianying Li
-
Publication number: 20180053290Abstract: Provided are a method and an apparatus for adjusting image brightness. The method includes; acquiring a single-channel brightness image based on grayscales of each channel of an image to be processed; performing Gaussian filtering on the single-channel brightness image to acquire a Gaussian filtered image; adjusting grayscales of the Gaussian filtered image based on the grayscales of the Gaussian filtered image and a preset proportion; acquiring a grayscale change rate of each pixel with respect to the Gaussian filtered image after adjustment and the Gaussian filtered image before adjustment; and processing the image to be processed based on the grayscale change rate of each pixel to acquire a processed image.Type: ApplicationFiled: October 17, 2017Publication date: February 22, 2018Inventors: Shimin HU, Jianyu WANG, Baoli LI, Haifeng DENG, Xianying LI
-
Publication number: 20180012107Abstract: An image classification method is provided. The method includes: inputting a to-be-classified image into a plurality of neural network models; obtaining data output by multiple non-input layers specified by each neural network model to generate a plurality of image features corresponding to the plurality of neural network models; respectively inputting the plurality of corresponding image features into linear classifiers, each of the linear classifiers being trained by one of the plurality of neural network models for determining whether an image belongs to a preset class; obtaining, using each neural network model, a corresponding probability that the to-be-classified image comprises an object image of the preset class; and determining, according to each obtained probability, whether the to-be-classified image includes the object image of the preset class.Type: ApplicationFiled: September 13, 2017Publication date: January 11, 2018Inventors: Kun XU, Xiaowei GUO, Feiyue HUANG, Ruixin ZHANG, Juhong WANG, Shimin HU, Bin LIU
-
Patent number: 9836880Abstract: The present invention relates to the technical field of image processing, and in particular, to a patch net model for image representation and a construction method of the patch net model. The patch net model for image representation is of a forest-shaped structure consisting of a plurality of composite nodes and basic nodes, each composite node is a non-leaf node, and each basic node is a leaf node; the basic node includes a certain patch region of an image and a representative patch representing an apparent feature of the patch region; the composite node includes a certain patch region of the image and can be further decomposed into basic nodes and/or composite nodes; an edge exists between two nodes, which are located on the same layer of the forest-shaped structure and are spatially connected, and a relation matrix used for expressing the spatial relative position of the two nodes is arranged on the edge.Type: GrantFiled: December 25, 2013Date of Patent: December 5, 2017Assignee: TSINGHUA UNIVERSITYInventors: Shimin Hu, Fanglue Zhang, Miao Wang
-
Patent number: 9824430Abstract: Provided are a method and an apparatus for adjusting image brightness. The method includes: acquiring an image to be processed, and acquiring a single-channel brightness image based on grayscales of each channel of the image to be processed; performing Gaussian filtering on the single-channel brightness image to acquire a Gaussian filtered image; adjusting grayscales of the Gaussian filtered image based on the grayscales of the Gaussian filtered image and a preset proportion; comparing the Gaussian filtered image after adjustment with the Gaussian filtered image before adjustment to acquire a grayscale change rate of each pixel through adjustment; processing the image to be processed based on the grayscale change rate of each pixel to acquire a processed image; and outputting the processed image.Type: GrantFiled: July 22, 2015Date of Patent: November 21, 2017Assignee: Tencent Technology (Shenzhen) Company LimitedInventors: Shimin Hu, Jianyu Wang, Baoli Li, Haifeng Deng, Xianying Li
-
Patent number: 9736336Abstract: The disclosure relates to an image tone adjustment method, an apparatus thereof, and a computer-readable storage medium. The method includes: fitting overlapping areas to obtain a first correction parameter and a second correction parameter, performing interpolation on each pixel of the target image to obtain a corresponding correction parameter, correcting the target image according to the corresponding correction parameters; fitting an overlapping area between the corrected target image and the first image, and an overlapping area between the corrected target image and the second image to obtain a first RGB three-channel linear transformation parameter and a second RGB three-channel linear transformation parameter, performing linear interpolation on each pixel of the corrected target image to obtain a corresponding RGB three-channel linear transformation parameter, and transforming the corrected target image.Type: GrantFiled: July 17, 2015Date of Patent: August 15, 2017Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Shimin Hu, Jianyu Wang, Baoli Li, Haifeng Deng, Xianying Li
-
Patent number: 9508162Abstract: The present invention discloses a method for rapidly vectorizing an image by gradient meshes based on parameterization, which comprises the following steps: determining an image region to be vectorized (S1); converting the image region into a mesh representation (S2); mapping the meshes to a planar rectangular region by parameterizing the meshes (S3); and generating a gradient mesh image according to the parameterization result of said meshes (S4). The present invention generates gradient meshes by converting an image region into meshes and by parameterization, so the gradient meshes are obtained completely automatically without the need for the user to give original meshes and moreover, the computation speed is improved significantly since nonlinear optimization is avoided. In addition, the method of the present invention can process image regions containing or not containing holes.Type: GrantFiled: June 2, 2010Date of Patent: November 29, 2016Assignee: TSINGHUA UNIVERSITYInventors: Shimin Hu, Yukun Lai
-
Publication number: 20160249037Abstract: The present invention discloses a method for acquiring a comfort degree of a motion-sensing binocular stereoscopic video. The method includes the following steps: S1. carrying out binocular parallax and movement speed analysis on an input binocular video, and calculating a binocular parallax d, a movement speed vxy in a visual plane direction and a movement speed vz in a depth direction of each pixel point in the video; S2. calculating a corresponding comfort degree value c according to the parameters (d, vxy, vz) of the pixel point; S3. calculating the comfort degree value of the entire frame according to the calculated comfort degree value of each pixel point; S4. calculating the comfort degree value of the entire video according to the comfort degree value of each frame.Type: ApplicationFiled: December 25, 2013Publication date: August 25, 2016Inventors: Shimin HU, Songpei DU, Masia BELEN, Gutierrez DIEGO
-
Publication number: 20160196686Abstract: The present invention relates to the technical field of image processing, and in particular, to a patch net model for image representation and a construction method of the patch net model. The patch net model for image representation is of a forest-shaped structure consisting of a plurality of composite nodes and basic nodes, each composite node is a non-leaf node, and each basic node is a leaf node; the basic node includes a certain patch region of an image and a representative patch representing an apparent feature of the patch region; the composite node includes a certain patch region of the image and can be further decomposed into basic nodes and/or composite nodes; an edge exists between two nodes, which are located on the same layer of the forest-shaped structure and are spatially connected, and a relation matrix used for expressing the spatial relative position of the two nodes is arranged on the edge.Type: ApplicationFiled: December 25, 2013Publication date: July 7, 2016Inventors: Shimin HU, Fanglue ZHANG, Miao WANG
-
Publication number: 20160078674Abstract: three-dimensional scene model generating method, comprising: analyzing and extracting object structure groups of a scene and the semantic relationship of objects from a scene model library; counting and fitting the relative position of the objects in each object structure group, and calculating a Gaussian distribution function; : retrieving each object in the sketch in the model library; : determining a model corresponding to the sketch; calculating the initial position of the corresponding object according to the sketch; finding out a local optimal position according to the initial position calculated and the Gaussian distribution function in combination with a gradient descent method, and placing each model according to the position to obtain a final scene model.Type: ApplicationFiled: December 25, 2013Publication date: March 17, 2016Inventors: Kun Xu, Kang CHEN, Weilun SUN, Shimin HU
-
Publication number: 20150326753Abstract: The disclosure relates to an image tone adjustment method, an apparatus thereof, and a computer-readable storage medium. The method includes: fitting overlapping areas to obtain a first correction parameter and a second correction parameter, performing interpolation on each pixel of the target image to obtain a corresponding correction parameter, correcting the target image according to the corresponding correction parameters; fitting an overlapping area between the corrected target image and the first image, and an overlapping area between the corrected target image and the second image to obtain a first RGB three-channel linear transformation parameter and a second RGB three-channel linear transformation parameter, performing linear interpolation on each pixel of the corrected target image to obtain a corresponding RGB three-channel linear transformation parameter, and transforming the corrected target image.Type: ApplicationFiled: July 17, 2015Publication date: November 12, 2015Inventors: Shimin HU, Jianyu WANG, Baoli LI, Haifeng DENG, Xianying LI
-
Publication number: 20150324961Abstract: Provided are a method and an apparatus for adjusting image brightness. The method includes: acquiring an image to be processed, and acquiring a single-channel brightness image based on grayscales of each channel of the image to be processed; performing Gaussian filtering on the single-channel brightness image to acquire a Gaussian filtered image; adjusting grayscales of the Gaussian filtered image based on the grayscales of the Gaussian filtered image and a preset proportion; comparing the Gaussian filtered image after adjustment with the Gaussian filtered image before adjustment to acquire a grayscale change rate of each pixel through adjustment; processing the image to be processed based on the grayscale change rate of each pixel to acquire a processed image; and outputting the processed image.Type: ApplicationFiled: July 22, 2015Publication date: November 12, 2015Inventors: Shimin HU, Jianyu WANG, Baoli LI, Haifeng DENG, Xianying LI
-
Publication number: 20120113098Abstract: The present invention discloses a method for rapidly vectorizing an image by gradient meshes based on parameterization, which comprises the following steps: determining an image region to be vectorized (S1); converting the image region into a mesh representation (S2); mapping the meshes to a planar rectangular region by parameterizing the meshes (S3); and generating a gradient mesh image according to the parameterization result of said meshes (S4). The present invention generates gradient meshes by converting an image region into meshes and by parameterization, so the gradient meshes are obtained completely automatically without the need for the user to give original meshes and moreover, the computation speed is improved significantly since nonlinear optimization is avoided. In addition, the method of the present invention can process image regions containing or not containing holes.Type: ApplicationFiled: June 2, 2010Publication date: May 10, 2012Inventors: Shimin Hu, Yukun Lai