-
公开(公告)号：US09684817B2
公开(公告)日：2017-06-20
申请号：US14893035
申请日：2013-11-26
Inventor： Hui Huang
IPC: G06K9/00 , G06K9/40 , G06K9/20 , G06K9/56 , G06K9/62 , G06T15/10 , G06T19/20 , G06T19/00 , G06T5/00
CPC classification number: G06K9/00214 , G06K9/00201 , G06K9/209 , G06K9/40 , G06K9/56 , G06K9/6207 , G06K9/6211 , G06K9/6249 , G06T5/002 , G06T15/10 , G06T19/00 , G06T19/20 , G06T2207/10028 , G06T2210/56
Abstract: Disclosed is a method for automatically optimizing point cloud data quality, including the following steps of: acquiring initial point cloud data for a target to be reconstructed, to obtain an initial discrete point cloud; performing preliminary data cleaning on the obtained initial discrete point cloud to obtain a Locally Optimal Projection operator (LOP) sampling model; obtaining a Possion reconstruction point cloud model by using a Possion surface reconstruction method on the obtained initial discrete point cloud; performing iterative closest point algorithm registration on the obtained Possion reconstruction point cloud model and the obtained initial discrete point cloud; and for each point on a currently registered model, calculating a weight of a surrounding point within a certain radius distance region of a position corresponding to the point for the point on the obtained LOP sampling model, and comparing the weight with a threshold, to determine whether a region where the point is located requires repeated scanning. Further disclosed is a system for automatically optimizing point cloud data quality.
-
122.发明申请公开(公告)号：US20170105643A1
公开(公告)日：2017-04-20
申请号：US15389978
申请日：2016-12-23
Inventor： Ye LI , Xiaomao FAN , Furu XIANG , Yunpeng CAI , Fen MIAO
IPC: A61B5/04 , A61B5/00 , A61B5/0456
CPC classification number: A61B5/04017 , A61B5/0456 , A61B5/0472 , A61B5/7203 , A61B5/7264
Abstract: The present disclosure provides a GPU-based parallel electrocardiogram signal analysis method, comprising: performing a filtering process of electrocardiogram signals through a long interval artifact removal and a short interval artifact removal; performing a QRS detection of the filtering-processed electrocardiogram signals through an R-wave position extraction, a QRS complex start and end positions extraction and a QRS complex width extraction; performing an abnormal waveform classification of the QRS-detected electrocardiogram signals through template creation; wherein at least one of the long interval artifact removal, the short interval artifact removal, the R-wave position extraction, the QRS complex width extraction and the creation template is performed by a multiple threads at a GPU device side in parallel, any thread being read through its unique index number to process corresponding data. By executing one or more steps of the electrocardiogram signal analysis at GPU in parallel, the present disclosure increases the analysis speed of the electrocardiogram signals.
-
公开(公告)号：US09390552B1
公开(公告)日：2016-07-12
申请号：US14378976
申请日：2013-09-13
Inventor： Hui Huang , Shihao Wu , Baoquan Chen , Liangliang Nan
CPC classification number: G06T17/00 , G06T2210/56
Abstract: A method for extracting a skeleton form a point cloud includes: obtaining inputted point cloud sampling data; contracting the point cloud using an iterative formula and obtaining skeleton branches, the iterative formula is: arg min X ∑ i ∈ I = ∑ j ∈ J x i - q i θ ( x j - q j ) + R ( X ) , wherein R ( X ) = ∑ i ∈ I γ i ∑ i ′ ∈ I / { i } θ ( x i - x i ′ ) σ i x i - x i ′ , θ ( r ) = ⅇ 4 r 2 h 2 , wherein J represents a point set of the point cloud sampling data, q represents the sampling points in the point set J, I represents a neighborhood point set of the sampling points q, x represents the neighborhood points in the neighborhood point set I. R is a regular term, γ is a weighting coefficient, h is a neighborhood radius of the neighborhood point set I, and σ is a distribution coefficient; and connecting the skeleton branches and obtaining a point cloud skeleton.
Abstract translation: 一种用于从点云提取骨架的方法包括：获得输入的点云采样数据; 使用迭代公式收集点云并获得骨架分支，迭代公式为：arg·peng minXΣi∈I =Σj∈Jx i-q iㄧ （x j-q j）+ R（X）其中R（X）=Σi∈IγiΣi'∈I / {i}＆thetas; （x i - x i'）＆sgr ix i - x i'，＆thetas; （r）=ⅇ4r 2 h 2，其中J表示点云采样数据的点集，q表示点集合J中的采样点，I表示采样点q的邻域点集， x表示邻域点集合I中的邻域点.R是常规项，γ是加权系数，h是邻域点集I的邻域半径，＆sgr; 是分布系数; 并连接骨架分支并获得点云骨架。
-
124.发明授权公开(公告)号：US09360310B2
公开(公告)日：2016-06-07
申请号：US14087162
申请日：2013-11-22
Inventor： Guang Tan , Bo Xie , Chenghua Mao
Abstract: The present disclosure relates to a multi-sensor indoor localization method and device. The method includes: an optical signal is received from a point light source using an optical sensor group having N optical sensors; the light intensity of the optical signal is obtained, the optical sensor group includes a polyhedron-shaped base where the normal vectors of each three faces are linearly independent, the N optical sensors are located on the faces of the base, and N≧6; the current heading is obtained by a magnetic sensor group; a current unit normal vector is obtained; a system of at least three equations is established; the system of equations is solved to obtain an approximate solution of minimum residual, the approximate solution is regarded as the coordinates of the optical sensor group.
Abstract translation: 本发明涉及多传感器室内定位方法和装置。 该方法包括：使用具有N个光学传感器的光学传感器组从点光源接收光信号; 获得光信号的光强度，光传感器组包括三面体的法线向线性独立的多面体基座，N个光学传感器位于基体的面上，N≥6; 当前航向由磁传感器组获得; 获得当前单位法向量; 建立至少三个方程的系统; 求解方程组得到最小残差的近似解，将近似解作为光传感器组的坐标。
-
公开(公告)号：US20250143822A1
公开(公告)日：2025-05-08
申请号：US19014150
申请日：2025-01-08
Inventor： WENKE DUAN , OLATUNJI MUMINI OMISORE , LEI WANG
Abstract: The present disclosure relates to a robotic system for respiratory diagnosis and treatment and a control method therefor. The present disclosure includes a master control apparatus for operating and controlling a control instruction, a slave control apparatus for receiving the control instruction of the master control apparatus and operating an operation action, and a navigation apparatus for guiding the slave control apparatus. The slave control apparatus includes a slave robot and a slave embedded controller installed inside the slave robot. The slave robot is provided with a mechanical arm, a propulsion support plate connected to the mechanical arm, a biopsy instrument introduction mechanism connected to a propulsion support plate for delivering a biopsy instrument, a bronchoscope rotation driving mechanism for controlling a bronchoscope, and a bending control mechanism for controlling an angle of a flexible end of the bronchoscope.
-
Patent Agency Ranking
公开(公告)号：US20250137909A1
公开(公告)日：2025-05-01
申请号：US19004464
申请日：2024-12-30
Inventor： LONG MENG , WEI ZHOU , HAIRONG ZHENG , LILI NIU , BENXIAN PENG
IPC: G01N15/149 , G01N15/10 , G01N15/14 , G01N15/1404
Abstract: A cellular mechanical property measurement and sorting method comprises: cells to be sorted being arranged in a straight line after passing through a standing wave acoustic field generated by a first interdigital transducer; the cells flowing through a focused acoustic field generated by a second interdigital transducer, and the focused acoustic field generating a radiation force on the cells, such that the cells are deformed; performing calculation according to information of the radiation force and deformation, so as to obtain elastic moduli of the cells; determining the positions of the cells, and selectively driving, with designed delay time, interdigital transducers in a cell sorting unit according to the moving speeds of the cells and the distances between the cells and the sorting unit, and triggering, according to the elastic moduli, a corresponding interdigital transducer to generate a planar acoustic field, so as to sort the cells.
-
公开(公告)号：US12288327B2
公开(公告)日：2025-04-29
申请号：US17764446
申请日：2021-02-03
Applicant: SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY
Inventor： Shuqiang Wang , Qiankun Zuo , Min Gan
Abstract: The present application is applicable to the field of medical imaging technologies, and provides an image-driven brain atlas construction method and apparatus, a device and a storage medium. The method includes: acquiring multi-modal data of a brain to be predicted, where the multi-modal data is acquired according to image data collected when the brain is under at least three different modalities; inputting the multi-modal data into a preset fusion network for processing to output and acquire feature parameters of the brain; where the processing of the multi-modal data by the fusion network includes: extracting a non-Euclidean spacial feature and an Euclidean spacial feature of the multi-modal data, and performing hypergraph fusion on the non-Euclidean spacial feature and the Euclidean spacial feature to acquire the feature parameters, where the feature parameters are used to characterize a brain connection matrix and/or a disease category of the brain.
-
公开(公告)号：US12254684B2
公开(公告)日：2025-03-18
申请号：US17763513
申请日：2019-11-19
Inventor： Shuqiang Wang , Wen Yu , Yanyan Shen , Zhuo Chen
Abstract: The present application is suitable for use in the technical field of computers, and provides a smart diagnosis assistance method and terminal based on medical images, comprising: acquiring a medical image to be classified; pre-processing the medical image to be classified to obtain a pre-processed image; and inputting the pre-processed image into a trained classification model for classification processing to obtain a classification type corresponding to the pre-processed image, the classification model comprising tensorized network layers and a second-order pooling module. As the trained classification model comprises tensor decomposed network layers and a second-order pooling module, when processing images on the basis of the classification model, more discriminative features related to pathologies can be extracted, increasing the accuracy of medical image classification.
-
公开(公告)号：US20250040827A1
公开(公告)日：2025-02-06
申请号：US18921953
申请日：2024-10-21
Inventor： Ye LI , Zhiguang MO , Xiaoping ZHANG , Huageng LIANG , Chao LUO , Qiaoyan CHEN , Changjun TIE , Qi CAO , Wen XIAO
Abstract: A multichannel endorectal coil for prostate MRI, a system, and a working method. The coil comprises a support body provided with a winding curved surface, a plurality of first endorectal coils (1, 2, 3) wrapped around the surface of the support body, and a second endorectal coil stacked on the plurality of first endorectal coils (1, 2, 3); wherein two adjacent first endorectal coils (1, 2, 3) are decoupled by means of partial overlapping, and two non-adjacent first endorectal coils (1, 2, 3) are decoupled by providing a shared capacitor (5); the second endorectal coil comprises a first coil section and a second coil section which are in intersecting connection with one another, the first coil section and the second coil section are arranged symmetrically, and no electrical connection exists at the intersection thereof. The invention increases the number of channels, and further achieves better high-resolution imaging capabilities.
-
公开(公告)号：US12208242B2
公开(公告)日：2025-01-28
申请号：US17312950
申请日：2020-11-13
Inventor： Zedong Nie , Jingzhen Li , Yuhang Liu
Abstract: A closed-loop artificial pancreas system based on a wearable monitoring method is provided. The system includes: a wearable blood glucose monitoring submodule, configured to obtain a blood glucose sensing signal in a noninvasive manner by utilizing a wearable device; a diet and exercise monitoring submodule, configured to obtain diet monitoring data and exercise monitoring data which can cause variations of blood glucose concentration of a subject to be tested; a calculation control submodule, configured to obtain information related to insulin infusion by utilizing a trained deep learning model, the diet monitoring data, and the exercise monitoring data; an insulin infusion submodule, configured to automatically implement insulin infusion; and an effect assessment module, configured to assess an insulin infusion effect, and to feed an assessment result back to the calculation control submodule, such that the calculation control submodule determines whether to update the information related to insulin infusion.
-
-
-
-
-
-
-
-
-
Search Results
337
records
(took 0.039 seconds)
