Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

1909results about How to "Implement extraction" patented technology

Voice recognition device and voice recognition method, language model generating device and language model generating method, and computer program

The invention discloses a voice recognition device and a voice recognition method, a language model generating device and a language model generating method, and computer program. The speech recognition device includes one intention extracting language model and more in which an intention of a focused specific task is inherent, an absorbing language model in which any intention of the task is not inherent, a language score calculating section that calculates a language score indicating a linguistic similarity between each of the intention extracting language model and the absorbing language model, and the content of an utterance, and a decoder that estimates an intention in the content of an utterance based on a language score of each of the language models calculated by the language score calculating section.
Owner:SONY CORP

Automatic recognition method pf mathematical formula in image

The invention relates to an automatic recognition method of a mathematical formula in an image, which comprises the steps that: a syntactic structure model of the mathematical formula is built, and a bottom knowledge base of the mathematical formula is built; the location of the mathematical formula in the image, the recognition of a mathematical symbol, the analysis and comprehension of a mathematical formula structure and the expression and formatted output of the mathematical formula structure are carried out. The automatic recognition method designs a complete set of method and model for solving the recognition and comprehension difficulties of an off-line mathematical formula image and forms a method for automatically processing the mathematical formula image in the whole process. The method can realize the automatic judgment and extraction of an individual-line / embedded mathematical formula in an image, thereby meeting the application requirements of the automatic inputting of the mathematical formula image and the comprehension and format recurrence of the mathematical formula structure. The method can be combined with the existing normal text OCR system to form a document image processing system with more complete functions and also can support the research on expression processing methods in other fields, such as automatic processing aiming at chemical equations, etc.
Owner:NANKAI UNIV

Method for carrying out face three-dimensional reconstruction at any viewing angle on basis of self-adaptive deformable model

The invention relates to a method for carrying out face three-dimensional reconstruction at any viewing angle on the basis of a self-adaptive deformable model. The method includes the steps of (1) obtaining face image data and screening a face image with high definition as original data, (2) positioning feature points, (3) coarsely estimating the angle of a face according to the positioning result of the feature points, (4) building a face three-dimensional deformable model, adjusting the feature points of the face to be at the same dimension as the face three-dimensional deformable model through translation and scaling and extracting coordinate information of the points corresponding to the feature points of the face to form a sparse face three-dimensional deformable model, (5) iterating face three-dimensional reconstruction by means of the particle swarm optimization algorithm according to the coarsely estimation value of the angle of the face and the sparse face three-dimensional deformable model to obtain a face three-dimensional geometric model, (6)mapping input face texture information in a two-dimensional image to the face three-dimensional geometric model in a texture pasting method after the face three-dimensional geometric model is obtained, so that a complete face three-dimensional model is obtained. The method can be widely used in the field of identity identification.
Owner:TSINGHUA UNIV

Weld seam surface detect feature extraction method based on grayscale image morphology

The invention relates to a weld seam surface defect feature extraction method based on the grayscale image morphology, which comprises the steps of setting shooting parameters of a miniature CCD camera according to an acquired image; converting the acquired true color image into a grayscale image, and carrying out median filtering processing on the image; eliminating a white interference region generated by residue noise and background texture by adopting a minimum area deleting method; avoiding influences imposed on edge line extraction by an undetermined black region through region filling processing; processing a completely filled weld seam region through an expansion algorithm so as to acquire a weld seam region whose area is identical to the actual weld seam area; extracting an edge line of the filled and expanded weld seam region by adopting a Canny operator so as to realize positioning for the weld seam region; and drawing a cross section grayscale B scanning curve which is vertical with the weld seam edge, wherein a gray-scale value of the weld seam surface changes obviously on the B scanning curve when the weld seam surface has defects such as a hole and an overlap, so that different types of defects at the weld seam surface are judged. The weld seam surface detect feature extraction method realizes accurate positioning for the weld seam edge and accurate recognition for the defects such as overlaps and holes.
Owner:BEIJING UNIV OF TECH

Tunnel lining disease detection device based on infrared temperature field and gray level image

The invention relates to a tunnel lining disease detection device based on an infrared temperature field and a gray level image. The tunnel lining disease detection device comprises a vehicle-mounted mobile platform, illumination equipment, a photoelectric encoder, a GPS (Global Position System) receiver, an inertia unit, a synchronous controller, an area-array camera, an infrared thermal imager, an acquisition server, a display control device and a power supply system; tunnel lining two-dimensional image data, infrared temperature field data and fracture surface deformation data are combined with positioning data of the GPS, the inertia unit and the photoelectric encoder to establish a tunnel model with gray level information, temperature information and fracture surface deformation; and tunnel lining cracks are analyzed, and the length, width and lining leakage water information of the cracks are automatically detected. For the tunnel lining disease detection device, the advantages of infrared temperature field detection and two-dimensional gray level image crack detection are combined so that the detection result is relatively reliable, the speed is rapid and the working efficiency is greatly improved.
Owner:WUHAN WUDA ZOYON SCI & TECH

Analogue circuit fault diagnosis neural network method based on particle swarm algorithm

The invention discloses a neural network method for diagnosing analog circuit failures which is based on a particle swarm algorithm, and comprises the following steps: imposing an actuating signal to an analog circuit to be tested, measuring an actuating response signal in the testing nodes of the circuit, extracting the candidate signal of failure characteristics by implementing noise elimination and then wavelet packet transformation on the measured actuating response signal, extracting the failure characteristics information by further implementing orthogonal principal component analysis and normalization processing on the candidate signal of failure characteristics, and sending the failure characteristics information as samples to the neural network for implementing classification. The method adopts the particle swarm algorithm instead of a gradient descent method in traditional BP algorithms, thus leading the improved algorithm to be characterized in that the algorithm avoids the local minimum problem and has better generalization performance. The BP neural network method for diagnosing the analog circuit failures which is optimized on the basis of particle swarm can obviously reduce iteration times in the algorithm, improve the precision of network convergence, and improve diagnosis speed and precision.
Owner:HUNAN UNIV

Method and system for extracting information of content in Internet

The method comprises: a) getting the source code of the target webpage; b) extracting the address link matching the a preset extracting term from said source code of the target webpage; c) according to the extracted address link, getting the source code of its corresponding content webpage; d) extracting the content information matching the preset extracting term from the content webpage. The system thereof comprises: a setting unit used for presetting a target webpage and an extracting term; a first acquisition unit used for the getting the address link from the target webpage source code; and a second acquisition unit used for getting the content information from the content webpage source code.
Owner:TENCENT TECH (SHENZHEN) CO LTD

Power channel corridor routing-inspection method based on tilt photography three-dimensional reconstruction technology

The invention discloses a power channel corridor routing-inspection method based on a tilt photography three-dimensional reconstruction technology, wherein the method includes the steps: A, combining a laser radar data measurement technology and a tilt photography technology, and rapidly constructing power transmission line channel high-precision three-dimensional base map data by using the laser radar measurement technology; B, acquiring three-dimensional real scene data of a channel corridor by using the tilt photography measurement technology; and C, carrying out fused analysis of the three-dimensional real scene information and a laser radar channel base map, effectively identifying and extracting trees and obstacles in the channel corridor, and then generating a tree barrier assessment report. By using the method, qualitative analysis of the tree barrier can be effectively turned into quantitative analysis, the position of a to-be-felled tree in the channel can be calculated, the felling area is statistical, and thus the safe operation of the line corridor is ensured.
Owner:航天图景(北京)科技有限公司

Road zebra crossing automatic extraction method based on vehicle-mounted laser scanning point cloud

The invention provides a road zebra crossing automatic extraction method based on vehicle-mounted laser scanning point cloud, and relates to public traffic road zebra crossings. According to the method, global positioning system data for recording vehicle positions and tracks in real time is used for extracting a plurality of cross sections from the vehicle-mounted laser scanning point cloud data, and the road and non-road classification is realized through detecting the elevation mutation of road shoulders of the roads in the scanning line data; then, the three-dimension road data is converted into an intensity characteristic image with space distribution characteristics, the laser scanning point normal distribution characteristics are utilized for dynamically cutting the road zebra crossings, the GPS (global positioning system) track data is used again for calculating the linear morphology closed operation direction and size, and the extraction of the road zebra crossings is realized. Through the cross section subdivision on the vehicle-mounted moving scanning data, and the three-dimension road surface data detection is converted into the detection of the elevation mutation of the road shoulders of the roads in the two-dimension profile for realizing the road and non-road classification. Compared with a method of directly processing mass three-dimension data, the method has the advantages that the calculation quantity is small, and the efficiency is high.
Owner:XIAMEN UNIV

Method for extracting and purifying DNA

The invention discloses a method for extracting and purifying DNA, comprising the following steps: 1) pre-treatment: a biological sample is in contact with pre-treated lysis solution, and solid substance adhering to biological cells is removed to obtain rude lysis solution; 2) nucleic acid adsorption: the rude lysis solution obtained in step 1 is mixed with lyse combined liquid and magnetic bead suspension to form a solution system containing magnetic nanosphere-DNA composite body, and the magnetic nanosphere-DNA composite body in the solution system is collected; 3) washing: the magnetic nanosphere-DNA composite body obtained in step 2 is successively washed with a cleaning solution I and a cleaning solution II, and then DNA is dissolved out by spent regenerant. The method provided by the invention has 90% of the DNA extracting efficiency, the extracted DNA can be used in down stream analysis operation, such as STR multiplex amplification, DNA sequencing, DNA quantitation and the like.
Owner:INST OF FORENSIC SCI OF MIN OF PUBLIC SECURITY

Vector building drawing based method for reconstructing three-dimensional model

The invention provides a vector building drawing based method for reconstructing a three-dimensional model. The method comprises the following steps: performing preprocessing including primitive conversion, drawing alignment and height adjustment on a related vector building drawing for rebuilding the three-dimensional model to acquire corresponding primitive data; reading the primitive data in the processed vector building drawing, and identifying a building structural member to be shown in the vector building drawing according to the primitive data so as to acquire a profile of the buildingstructural member; completing three-dimensional rebuilding of the building structural member according to the identified profile after profile identification is completed for the building structural member in the vector building drawing so as to complete three-dimensional rebuilding of a building shown by the vector building drawing. The method realizes identification and extraction of related information in the drawing by processing the vector building drawing, completes the three-dimensional rebuilding of the building shown in the vector building drawing based on the information, and has greater improvement in efficiency by comparing with the prior artificial rebuilding method.
Owner:INST OF COMPUTING TECH CHINESE ACAD OF SCI

Automatic tracking control and online correction system with welding gun and control method thereof

The invention relates to an automatic tracking control and online correction system with a welding gun and a control method thereof and belongs to the technical field of robotic arc welding. The automatic tracking and control and online correction system comprises a vision sensing system, an image processing system, a tracking control system and an online correction system, wherein the vision sensing system comprises a CCD (Charge Coupled Device) vision sensor; the image processing system comprises an image preprocessing module and an image processing module; the tracking control system comprises the welding gun, a control system, a driving system, a signal processing module and an arc sensor; the online correction system comprises a laser two-dimensional outline scanning sensor and an error analysis module. According to the automatic tracking control and online correction system, butt-welded seams are predicated, tracked and corrected respectively a prewelding stage, a welding stage and a post-welding stage by virtue of error online fusion of three sensors, namely the CCD vision sensor, the arc sensor and the laser two-dimensional outline scanning sensor, so that the welded seam tracking precision and the fault tolerance of the system are improved, the welding production efficiency and the welding quality are improved, and the automatic tracking control and online correction system has generality.
Owner:WUHU ANPU ROBOT IND TECH RES INST

Method for scanning quickly residual matrix in video coding

The present invention relates to a quick scanning method for a residual error matrix in video coding process, which belongs to the field of video coding in signal processing. The method comprises: storing elements in a two dimension residual error matrix to a one-dimension serial according to a preset mapping way; extracting the lots of residual error elements gradually and orderly from the one-dimension serial, computing a level value, a map value and a run value of each residual error element, and storing them respectively. In the process of scanning the residual error matrix, the invention can parallelizably and effectively read the residual error element, accomplish parallelizably data computing and information extracting, and can quickly obtain the required scanning results, thereby, the invention greatly reduces the time cost in whole scanning process, enhances the coding rate of a coder, and facilitates the realization of real-time encoding under high distinguishability.
Owner:TSINGHUA UNIV

Power equipment fault knowledge graph construction method

The invention discloses a power equipment fault knowledge graph construction method. The method comprises the steps of power text preprocessing; named entity identification: identifying and extractingpower domain entities, obtaining local features on global features through a CRF model, and accurately obtaining optimal sequence annotations of the text; relationship identification: analyzing sentence structures by analyzing dependency relationships among components of sentences, and analyzing sentence dependency relationships by identifying and positioning grammatical relationships in the sentences; and knowledge storage and visualization: carrying out knowledge aggregation on the identified entities and relationships to form an RDF ternary form, and importing knowledge into a graphic database Neo4j to carry out knowledge storage and knowledge visualization. The method can achieve the extraction and aggregation of the power equipment fault knowledge, facilitates the quick and comprehensive construction of a power equipment fault knowledge graph, and facilitates the improvement of the intelligent level of power equipment fault diagnosis.
Owner:NORTHEAST DIANLI UNIVERSITY

Web page structural data extraction method and system

InactiveCN101561802AImplement extractionSolve problems with ever-changing structuresSpecial data processing applicationsWeb siteData ingestion
The invention relates to a web page structural data extraction method which is characterized by comprising the following steps: choosing a training web page content set and extracting target structural data; training the training web page content set to obtain a regular expression matched with the target structural data; writing the regular expression in a configuration module; utilizing the configuration module to collect a web page; and extracting the structural data from the collected web page. The web page structural data extraction method and system can realize the structural data extraction of static web pages and dynamic web pages and are suitable for acquiring various types of website information and extracting the structural data.
Owner:上海光华如新信息科技股份有限公司

Improved deep convolutional neural network-based remote sensing image classification model

The invention relates to an improved deep convolutional neural network-based remote sensing image classification model. The model comprises the following steps of: S1, carrying out dimensionality reduction on a remote sensing feature image on the basis of a bottleneck unit; S2, carrying out convolutional multichannel optimization on the remote sensing feature image on the basis of grouped convolution; S3, improving feature extraction ability of the remote sensing feature image on the basis of channel shuffling; and S4, carrying out band processing on spatial position features of the remote sensing image. The model has the advantages that the dimensionality reduction of to-be-input remote sensing images is realized, and the convolutional calculation amount during the training of deep convolutional neural network-based remote sensing image classification model is reduced; a channel shuffling structure is constructed in allusion to spatial correlation of the remote sensing images, so thatthe feature extraction ability of a neural network in the grouped convolution stage is enhanced; and aiming at spatial position features of the remote sensing images, spatial position feature recognition degrees, for the remote sensing images, of the deep convolutional neural network-based model are improved.
Owner:SHANGHAI OCEAN UNIV

Abnormal vehicle license plate recognition method and system

The invention discloses an abnormal vehicle license plate recognition method and a system. the method comprises the following steps: 10, an image of an abnormal vehicle license plate is captured; 20, the image of the abnormal vehicle license plate is pre-treated to obtain a filter image; 30, a vehicle body image is detected in the filter image; 40, the abnormal vehicle license plate is positioned in the vehicle body image; 50, characters of the abnormal vehicle license plate are segmented in the vehicle license plate region; and 60, a Chinese character classifier, an alphabet classifier and a mixed number and alphabetclassifier are arranged respectively so as to recognize the characters of the abnormal vehicle license plate, and the following operation is carried out on each classifier. Thus, the vehicle license plate can be recognized in the abnormal condition, and the vehicle license plate recognition precision is high.
Owner:ZHEJIANG LISHI TECH

Method for extracting rice protein by using rice

The invention discloses a method for extracting rice protein by using rice, which comprises the following steps: soaking and grinding, rice milk adjustment, primary liquefying, centrifugal separation, homogenizing, washing, centrifuging, enzymolysis, enzyme inactivation, screen separation, washing, centrifuging, drying, crushing and packing so as to obtain the rice protein. The method overcomes the defects that the high-concentration alkali liquor has damage effect on rice protein amino acid in an alkali extraction process, the quality of the extracted rice protein is poor, and the purity and sanitary index of the extracted protein cannot reach the edible standard; and in other methods for extracting the rice protein by using enzyme preparations, the rice milk is liquefied at a temperature of over 95 DEG C and then is dried at the high temperature, so the rice protein is denatured, the color is darkened, and the function of the rice protein is damaged. The extracting method of the invention keeps good physical functionality of the rice protein, implements industrialization of the extraction and production of the rice protein, and meanwhile improves the production conversion rate and quality of rice starch sugar.
Owner:北京佳沃臻诚科技有限公司

JPEG image information hiding based private information communication method and system

The invention relates to a JPEG image information hiding based private information communication method and system. The system comprises a preprocessing module used for converting to-be-transmitted information into binary data, an encryption / decryption module used for generating an information hiding key by a password input by a user, an information hiding module used for embedding the converted binary data into a carrier JPEG image, a transmission module for transmitting and sharing the JPEG image embedded with the binary data information, and an information extraction module used for extracting the binary data in the image embedded with the binary data information, wherein the information hiding module comprises an entropy decoding module, an information embedding module and an entropy encryption module. The invention provides a complete multi-morphological information hiding core algorithm taking an image as a medium and a communication solution. The private information communication method and system have important theoretical and application values.
Owner:FUJIAN NORCA TECH

Internet-oriented place name extraction and standardization method

The invention discloses an internet-oriented place name extraction and standardization method. According to the method, aimed at existing ways and structural features of place names and addresses in an internet page, identification is performed based on state administrative division information and a nationwide basic place name and address library by utilizing identification rules and dynamic relationships of the place names and the addresses, a multi-stage place name and address expression model and an extraction method are researched, automatic identification, extraction and standardization of Chinese place names and addresses in text information of the internet page are realized with reference to a place name and address standard model through superior-subordinate semantic relationships of the place names and the addresses in the text, and a technical basis is provided for spatial positioning of related geographic information of geographic entities, events and the like.
Owner:CHINASO INFORMATION TECH

Method for preparing cellulose water-based solution by stalk

InactiveCN101456958ABroad application prospectsReduce the amount of alkali usedPaper material treatmentBiomassSeparation process
The invention relates to a method for preparing cellulose water-based solution by straws, which consists of three parts: 1) the separation of the cellulose in the straws; 2) cellulose purification and molecular weight adjustment; 3) the dissolution of purified cellulose in aqueous medium. The separation process of the cellulose adopts the method of separating hemicellulose first and then removing lignin; the cellulose purification respectively adopts the method of acid or alkali treatment, and the molecular weight adjustment is finished by hydrolysis; the obtained cellulose is dissolved in alkaline aqueous solution through a pre-cooling method; and uniform and transparent cellulose solution is finally obtained. The method of the invention can realize the process of directly preparing cellulose aqueous solution by straw biomass; the obtained cellulose solution can be widely applied to cellulosic spinning, and the preparation and chemical derivatization reaction of regeneration membrane and resin.
Owner:UNIV OF SCI & TECH OF CHINA

Text identification method and device based on verification

The invention discloses a method for test recognition based on verification and a device thereof, the steps of the method comprise receiving a verification request, splicing a generated identifying code segment and a to-be-recognized image segment comprising test characteristics into an identifying code image to transmit to a terminal, receiving user recognition information which is transmitted by the terminal and is input by users after the users recognize the identifying code image, and extracting text characteristics included by the image segment in the user recognition information to be the recognition result of the image segment. The scheme of the invention increases the accurate recognition rate of the recognition result, and resolves the limitation of the computer recognition.
Owner:TENCENT TECH (SHENZHEN) CO LTD

Nuclear safety shell surface defect automatic detection method and system

The invention provides a nuclear safety shell surface defect automatic detection method and system, and provides a systematic and effective technical scheme to overcome the defects in a nuclear safety shell surface, including cracks, corrosion and seepage. The method comprises: image preprocessing, and then utilizing a contour expansion filtering algorithm to perform denoising enhancement to obtain pretreated binary images; feature extraction comprising utilizing a linear weighting tensor voting algorithm, extracting cracks from discrete noises through detecting high light degree to obtain a result probability graph; and performing object tracking to obtain a crack center line, back-projecting positioning to extract real crack information, measuring crack length and stable width, crack integration and other defect detection and storing information. The invention further provides utilizing an adaptive width template method and an iterative method to respectively binarize images, and obtaining final binary images by performing AND operation on two results. The technical scheme creates an own system, and can meet real engineering demands, and guarantee nuclear shell safety.
Owner:WUHAN UNIV

Root right acquiring method and device

InactiveCN104506639AImplement Root permissionsImplement extractionTransmissionComputer terminalComputer science
The invention provides a Root right acquiring method and device. The method includes the steps of starting a corresponding upgrade mode of a mobile terminal; writing an executable file, used for acquiring a highest system right, into the mobile terminal; rebooting the mobile terminal to acquire the system Root right. The invention further provides a Root right acquiring device correspondingly. The Root right acquiring method and device is applicable to the Root of various brands of mobile terminals and is also applicable to the acquisition of the Root right for the mobile terminals difficult to Root.
Owner:BEIJING QIHOO TECH CO LTD +1

A digital twinning system based on a virtual imaging technology

ActiveCN109819233ASolve the strength problemSolve the incomplete display of digital entity informationTransmissionImage data processingEdge computingMultiple sensor
The invention relates to a strong mapping digital twin system based on a virtual imaging technology. According to the system, a multi-information cooperative communication mechanism is established between digital twin bodies, morphological information, state information and behavior information of a physical entity system are collected through multiple sensors and sent to an edge computing node, and the edge computing node is responsible for receiving sensor information and carrying out edge computing processing on the received information; A virtual imaging technology is applied to project digital entities of the digital twin system into a real space in a three-dimensional visualization mode, meanwhile, state information of the physical entities is displayed in a virtual reality mode, thedetail display effect of the digital twin system is enhanced, and the requirements for multi-view observation and immersion experience are met; According to the system, strong information mapping isestablished between a physical entity and a digital entity through the process, and it is guaranteed that information is transmitted between twin bodies in real time at a high speed in an undistortedmode.
Owner:合肥哈工热气球数字科技有限公司

Hierarchical cluster aviation pump multiple fault diagnostic method based on frequency multiplication relative energy sum

InactiveCN101571120AImplement diagnosticsRealize multi-fault high-precision diagnosisPump testingPositive-displacement liquid enginesAviationRelative energy
The invention discloses a hierarchical cluster aviation pump multiple fault diagnostic method based on frequency multiplication relative energy sum. In the method, firstly fault mode effect influence analysis technology is used for carrying out sensor optimal distribution on an aviation hydraulic pump and acquiring sensor signal; then common faults of the aviation hydraulic pump are classified by hierarchical cluster to determine the sequence and hierarchy of fault diagnosis; and finally fault diagnosis of a first diagnosis layer, a second diagnosis layer and a third diagnosis layer is carried out to complete the multiple fault diagnosis on the aviation pump. The method realizes the multiple fault diagnosis of the aviation pump with high accuracy; a extraction method of fault feature and frequency doubling relative energy sum is designed aiming that typical gradual fault of the aviation hydraulic pump is extremely weak at fault initial signature, the method can effectively realize the fault feature extraction of weak signal, and the method is proved to be accurate and efficient by plenty of experiments.
Owner:BEIHANG UNIV

Three-dimensional investigation method for dangerous falling rock based on air-borne laser radar

The invention discloses a three-dimensional investigation method for a dangerous falling rock based on an air-borne laser radar. Original laser point cloud data and original video image data which cover an engineering zone and the initial exterior orientation elements of the original video image data are collected and processed to generate a DEM (Digital Elevation Model), a DOM (Digital Orthophoto Map) and a color laser point cloud. An index database is generated, the dangerous falling rock is recognized by information in the index database, the information factors of the dangerous falling rock are extracted to classify the hazard rate of the dangerous falling rock and provide a treatment strategy, and cross section lines required by a treatment design are extracted. The high-precision color laser point cloud, the high-precision DEM and the high-precision DOM are established by the advanced space-to-land observation technology based on the air-borne laser radar, the information extraction, quantitative analysis and risk evaluation of the dangerous falling rock are realized, and a novel method for surveying mountain hazards based on the air-borne laser radar technology is created.
Owner:CHINA RAILWAY SIYUAN SURVEY & DESIGN GRP

High-resolution remote sensing image plane extraction method based on skeleton characteristic

The invention discloses a high-resolution remote sensing image plane extraction method based on skeleton characteristics, comprising the following steps: selecting a remote sensing image edge detection algorithm based on embedded confidence coefficient for edge detection, and realizing the remote sensing image edge detection algorithm based on embedded confidence coefficient; vectorizing a groundfeature target edge; extracting a ground feature skeleton base line from the vector edge of a ground feature based on a constraint Delaunay triangulation network algorithm; carrying out the target main skeleton extraction algorithm based on a binary tree structure; carrying out feature analysis on the target main skeleton of the plane; and realizing the automatic identification method of a plane target. By means of the invention, the plane target can be automatically identified and extracted and better identification extraction effect is obtained. The plane target skeleton has the excellent characteristics of rotation invariance and high discrimination index with other ground features, the vector edge of the ground feature target can be efficiently and precisely extracted from a remote sensing image with high spatial resolution, and the improved target skeleton can be extracted.
Owner:NANJING UNIV

Optical coherent tomographic image retinopathy intelligent testing system and testing method

The invention discloses an optical coherent tomographic image retinopathy intelligent testing system and a testing method. A current acquired retina image is mainly determined by an ophthalmology doctor by means of naked eye observation, and large-scale popularization is not facilitated. According to the system, a deep learning concept is used as a technical core; a migration learning strategy isutilized; a convolutional neural network algorithm in a deep learning model is used for establishing a classifier, thereby realizing classification of retinopathy; furthermore an image segmenting algorithm is used for realizing focus extraction and retina layering, thereby obtaining specific information of a pathology position in a picture and quantification information of shape parameters, and generating a related diagnosis report for further diagnosis by the doctor. The optical coherent tomographic image retinopathy intelligent testing system and the testing method have advantages of fillingin gaps in pathology intelligent identification and accurate positioning in a current optical coherent chromatography imaging system, effectively reducing working intensity of the doctor, and furtherpromoting clinical application and technical development of the optical coherent chromatography imaging system in ophthalmology disease diagnosis.
Owner:HANGZHOU DIANZI UNIV

Local sampling-based multi-geometrical characteristic point cloud data splitting method

The invention discloses a local sampling-based multi-geometrical characteristic point cloud data splitting method. The method includes the following steps: a three-dimensional rule grid is utilized to divide all acquired point cloud data into a plurality of first grid units; the process of extracting each geometrical characteristic includes the following steps: a sampling point is randomly chosen from the first current data set, the current first grid unit with the sampling point is determined, the sampling point and the other points in the current first grid unit are utilized to construct Alpha candidate geometrical models, an optimal model is determined from the Alpha candidate geometrical models, a consistent set of the optimal model is calculated in the first current data set, and according to multiple geometrical characteristics, all the point cloud data are split into a plurality of subsets. From local sampling, the method constructs candidate geometrical models from a first grid unit, and determines an optimal model from the candidate geometrical models, so that a geometrical characteristic is extracted, thus the problem of fitting models not existing in reality is prevented; and the method is more efficient.
Owner:北京建筑工程学院
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products