公开(公告)号：US11867778B2

公开(公告)日：2024-01-09

申请号：US17889802

申请日：2022-08-17

Applicant: ZHEJIANG LAB

Inventor： Qiang Guo ,  Ning Zhang ,  Ziwen Li ,  Zixuan Wang ,  Mengshi Zhang ,  Tingting Yu

IPC: G01R33/032

CPC classification number: G01R33/032

Abstract: The present disclosure discloses a system and method for testing the spatial distribution uniformity of an alkali metal atom number density of an atom magnetometer. The system includes a detection laser, a laser beam expanding system, a polarizing element, a magnetic shielding system, an alkali metal atom gas chamber, a beam profile camera, a beam splitting prism, etc., which are sequentially arranged in a light advancing direction. In the method, based on an optical absorption principle, light intensity attenuations of linearly polarized light before and after passing through the alkali metal gas chamber are tested by using the beam profile camera with pixels in the level of um, a two-dimensional distribution matrix of an atom number density in space is calculated, and the distribution uniformity of the atom number density is analyzed by using a discrete coefficient.

公开(公告)号：US20230410328A1

公开(公告)日：2023-12-21

申请号：US18240526

申请日：2023-08-31

Applicant: ZHEJIANG LAB ,  ZHEJIANG UNIVERSITY

Inventor： Wenyi ZHAO ,  Huajin TANG ,  Chaofei HONG ,  Xiao WANG ,  Mengwen YUAN ,  Yujing LU ,  Mengxiao ZHANG ,  Gang PAN

IPC: G06T7/246 ,  G06T3/40 ,  G06T7/73 ,  G06V10/82 ,  G06V10/774 ,  G06V10/77 ,  G06V10/74

CPC classification number: G06T7/248 ,  G06T3/4007 ,  G06T7/74 ,  G06V10/82 ,  G06V10/774 ,  G06V10/7715 ,  G06V10/761 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/10016

Abstract: A target tracking method and a target tracking system of a spiking neural network based on an event camera are provided. The method includes: acquiring a data stream of asynchronous events in a high dynamic scene of a target by an event camera as input data; dividing the data stream of the asynchronous events into synchronous event frames with millisecond time resolution; training a twin network based on a spiking neural network by a gradient substitution algorithm with a target image as a template image and a complete image as a searched image; and tracking the target by a trained twin network with interpolating a result of feature mapping to up-sample and obtaining the position of the target in an original image. The twin network includes a feature extractor and a cross-correlation calculator.

公开(公告)号：US11841839B1

公开(公告)日：2023-12-12

申请号：US18143059

申请日：2023-05-03

Applicant: ZHEJIANG LAB

Inventor： Jiaxi Yang ,  Chongning Na ,  Ye Yang ,  Kai Ding ,  Yao Yang ,  Yihan Wang

IPC: G06F16/215 ,  G06N3/0475 ,  G06N3/0455

CPC classification number: G06F16/215 ,  G06N3/0455 ,  G06N3/0475

Abstract: The present invention discloses a preprocessing and imputing method for structural data, comprising: step 1, querying the missing information of an original data, counting missing values, and obtaining a missing rate for the original data; step 2, based on the missing rate, performing listwise deletion on the original data, and then traversing the rows to generate corresponding dichotomous arrays, converting the arrays to the form of histogram, calculating the maximum rectangular area formed by the corresponding histogram, and then sorting all rectangular areas to obtain the maximum complete information matrix; step 3, using multiple imputation by chained equations, auto-encoders, or generative adversarial imputation networks to impute missing values on the original data. The present invention can carry out missing information statistics on the original data, automatically search the maximum complete information that meets the conditions, impute the structural data, greatly improve the quality of the original dataset and convenience for subsequent prediction tasks.

公开(公告)号：US11836966B2

公开(公告)日：2023-12-05

申请号：US17896055

申请日：2022-08-25

Applicant: ZHEJIANG LAB

Inventor： Wei Hua ,  Yechi Ma ,  Shun Zhang

IPC: G06K9/00 ,  G06V10/74 ,  G06V10/82

CPC classification number: G06V10/761 ,  G06V10/82

Abstract: An efficient across-camera target re-identification method based on similarity, which obtains a plurality of matching pairs and similarity scores thereof through two groups of targets to be matched; wherein for the matching pairs that are not matched by both parties, only a part of the matching pairs with higher similarity scores are selected each time, and the matching pairs are traversed according to the order of the similarity scores thereof from large to small, and the matching pairs and the similarity scores thereof are output as a matching result; when any target to be matched in a matching pair already appears in the matching result, the target cannot be output as the matching result; unmatched matching pairs are repeated traversed until the matching result reaches the expectation. The method firstly solves the multi-target matching problem based on similarity, and greatly reduces the time complexity and improves the efficiency.

公开(公告)号：US11823053B2

公开(公告)日：2023-11-21

申请号：US17714454

申请日：2022-04-06

Applicant: ZHEJIANG LAB

Inventor： Hongsheng Wang ,  Wei Hua ,  Weiqiang Jia ,  Hujun Bao

IPC: G06N3/082 ,  G06N3/04

CPC classification number: G06N3/082 ,  G06N3/04

Abstract: The disclosure discloses a method of neural network model computation-oriented intermediate representation and apparatus thereof. The method includes the following steps: S1, parsing an input model file so as to acquire topological structure information of a neural network; S2, constructing a logical computation graph; S21, inferring physical layout information of each operator in the logical computation graph; S22, inferring meta attributes of each operator in the logical computation graph; S23, inferring description information of input and output logical tensors of each operator in the logical computation graph; S3, constructing a physical computation graph; S31, generating a physical computation graph, etc.

公开(公告)号：US20230351890A1

公开(公告)日：2023-11-02

申请号：US18349980

申请日：2023-07-11

Applicant: ZHEJIANG LAB

Inventor： Qian HUANG ,  Kan WU ,  Yongdong ZHU ,  Zhifeng ZHAO

IPC: G08G1/083 ,  G08G1/08 ,  G08G1/01

CPC classification number: G08G1/083 ,  G08G1/08 ,  G08G1/0125 ,  G08G1/0112 ,  G08G1/0145

Abstract: The present application discloses a traffic light control method for an urban road network based on expected return estimation, which uses C-V2X wireless communication technology to obtain real-time information of all vehicles and traffic state in the road network from vehicle-mounted terminals, and adaptively and dynamically controls the phase transformation of the traffic light. According to the present application, the expected returns of keeping the current phase and executing phase switch are calculated by estimating the timely driving distance and the future driving distance of the passable vehicles in the next green light duration in combination with the proposed road priority traffic index. By comparing the expected returns of keeping the current phase or switching to other phases, the best phase is selected, so as to make as many passable vehicles travel farther as possible in the next green light duration. Therefore, the efficiency of traffic will be improved.

公开(公告)号：US11782723B1

公开(公告)日：2023-10-10

申请号：US17992830

申请日：2022-11-22

Applicant: ZHEJIANG LAB

Inventor： Hongsheng Wang ,  Guang Chen ,  Lingfang Zeng ,  Aimin Pan

IPC: G06F8/40 ,  G06F9/38 ,  G06F8/41

CPC classification number: G06F9/3885 ,  G06F8/433 ,  G06F8/443

Abstract: Disclosed are an intermediate representation method and apparatus for parallel execution of graph computation. The method includes the following steps: S1: compiling a neural network into a computational graph on a computer; S2: defining branch states of tensor variables in the computational graph; S3: defining a data dependency relationship of the tensor variables in the computational graph; S4: defining a control dependency relationship of the tensor variables in the computational graph; S5: building a data dependency relationship graph of the tensor variables in the computational graph; S6: building a control dependency relationship graph of the tensor variables in the computational graph; and S7: transforming control dependencies into data dependencies. The present application derives, based on the dependency relationship, a parallel computing method that can execute the branch threads in parallel in the global computational graph, and optimizes the compilation efficiency of the computational graph.

公开(公告)号：US11776879B1

公开(公告)日：2023-10-03

申请号：US18306948

申请日：2023-04-25

Applicant: ZHEJIANG LAB

Inventor： Guandong Liu ,  Weihao Wang ,  Shunbin Li ,  Ruyun Zhang

IPC: H01L23/02 ,  H01L23/473 ,  H01L23/498 ,  H01L23/31 ,  H01L23/367 ,  H01L25/065 ,  H01L23/00

CPC classification number: H01L23/473 ,  H01L23/3128 ,  H01L23/367 ,  H01L23/49816 ,  H01L24/16 ,  H01L25/0657 ,  H01L2224/32245 ,  H01L2225/06589 ,  H01L2924/15311 ,  H01L2924/182

Abstract: The present disclosure discloses a three-dimensional stacked package structure with a micro-channel heat dissipation structure and a packaging method thereof. The three-dimensional stacked package structure includes a chip package portion comprising a multi-layered structure with stacked chips, wherein the stacked chips are provided with through silicon vias and packaged in a three-dimensional stacked packaging manner and a silicon substrate package portion comprising a silicon substrate. The silicon substrate is provided with micro bumps which are to be interconnected with external lead wires. The chip package portion is assembled on the silicon substrate by bonding with the micro bumps. The stacked chips are etched with micro-channels and through holes corresponding to each other. The micro-channels are for coolant flowing in a horizontal direction, and the through holes are for coolant flowing in upper and lower layers. Sealing rings are arranged around the micro-channels and the through holes.

公开(公告)号：US11774344B2

公开(公告)日：2023-10-03

申请号：US17553841

申请日：2021-12-17

Applicant: ZHEJIANG LAB ,  ZHEJIANG UNIVERSITY

Inventor： Cuihong Li ,  Yuanyuan Ma ,  Zhaoxiong He ,  Shaochong Zhu ,  Zhiming Chen ,  Huizhu Hu

IPC: G01N15/14

CPC classification number: G01N15/1434 ,  G01N2015/1438 ,  G01N2015/1493

Abstract: The present application discloses a nanoparticle recognition device and method based on detection of scattered light with electric dipole rotation. According to the scattering model of nanoparticles, the in situ detection of particle morphology in an optical trap is realized by the methods of particle suspension control and scattered light detection and separation. Specifically, two linearly polarized laser beams are used, wherein the first laser beam suspends nanoparticles and rotates nanoparticles by adjusting the polarization direction; the polarization direction of the second linearly polarized light is unchanged, and scattered light in a specific dipole direction is excited; the change of the polarizability of the nanoparticles is deduced by monitoring the change of the light intensity of the scattered light excited by the second laser beam at the fixed position, so that particle morphology recognition is realized.

公开(公告)号：US20230301542A1

公开(公告)日：2023-09-28

申请号：US18125640

申请日：2023-03-23

Applicant: ZHEJIANG LAB

Inventor： Yu ZHANG ,  Wenyuan QIU ,  Zhichao WANG ,  Chaoliang SUN ,  Haotian QIAN ,  Jingsong LI

IPC: A61B5/055 ,  G06T7/00

CPC classification number: A61B5/055 ,  G06T7/0012 ,  G06T2207/30016 ,  G06T2207/10088 ,  G06T2207/20084

Abstract: The present disclosure discloses a brain atlas individualization method and system based on magnetic resonance and a twin graph neural network. Firstly, a feature is extracted from resting-state functional magnetic resonance imaging (rs-fMRI) by utilizing functional connectivity based on a region-of-interest, and at the same time, Fisher transformation and exponential transformation are performed on the feature; secondly, a corresponding adjacent matrix is extracted from T1-weighted magnetic resonance data in a data set; and then the twin graph neural network is designed for training and testing with the transformed feature and the adjacent matrix as inputs and a group atlas label and a sampling mask as outputs.