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

41results about How to "Flexible segmentation" patented technology

Method and device for segmenting point cloud data, storage medium and electronic equipment

ActiveCN110706238AFlexible segmentationAssisted driving decision-makingImage enhancementImage analysisData setPoint cloud
The embodiment of the invention discloses a method and device for segmenting point cloud data, a storage medium and electronic equipment. The method comprises the steps of determining a local area where each point cloud data point in a to-be-processed point cloud data set is located, and dividing the local area into a predetermined number of sub-areas; sorting the point cloud data points in each subarea to obtain a predetermined number of point cloud data sets in the same order; determining a dependency relationship between each point cloud data point in each same-order point cloud data set and the corresponding adjacent point cloud data point, thereby obtaining a predetermined number of dependency relationship sets; determining a probability value of each point cloud data point belongingto the prediction category based on a predetermined number of dependency sets; and segmenting the to-be-processed point cloud data set according to the probability value of each point cloud data pointbelonging to the prediction category. The embodiment of the invention can be applied to object identification of an outdoor environment in an unmanned scene so as to better assist in driving decision, and is also applied to identification of indoor objects with more complex scenes.
Owner:NANJING INST OF ADVANCED ARTIFICIAL INTELLIGENCE LTD

Malignant nodule edge detection image processing method based on benign thyroid template

ActiveCN112215842AIncrease workloadAbility to make good use of prior knowledgeImage enhancementImage analysisImaging processing3d image
The invention provides a malignant nodule edge detection image processing method based on a benign thyroid template. The method comprises the steps: learning an obtained thyroid three-dimensional image data set through a neural network, and forming a parameterized benign thyroid template; matching with the benign thyroid template according to the labeling information and the image information of the thyroid nodule ultrasonic image to be recognized, and performing coarse positioning on the nodule by combining the three-dimensional image and the feature information of the benign thyroid templateto obtain an initial contour curve of the nodule; adopting a local binary fitting model to iterate and evolve the initial contour curve to obtain an evolved contour curve; and performing effective contour selection on the evolved contour curve to obtain a final peripheral contour curve and a segmentation result, and performing fine positioning on the position of the nodule. The method is higher in autonomous recognition capability, better in adaptability to input of different thyroid images, better in segmentation effect, more accurate in numerical value implementation and higher in segmentation adaptability to images with uneven gray levels.
Owner:上海市瑞金康复医院

Key frame screening method based on interested target distribution

The invention discloses a key frame screening method based on interested target distribution, and belongs to the technical field of image processing. The method comprises the following steps: carrying out feature extraction on each video frame image by adopting a plurality of feature extraction modes, and carrying out normalization processing on extracted feature vectors; calculating the feature distance between adjacent frames under each feature vector, and obtaining the difference between the adjacent frames through the weighted sum of all the feature distances; based on the difference curve between adjacent frames, realizing shot segmentation according to local adaptive dual thresholds, and performing target detection processing on each video frame image based on a neural network; detecting the obtained video frame in the shot, and obtaining the type and position of a target and the area of a detection frame; further segmenting the video frame image in the shot into sub-shots according to the target distribution and quantity difference in the video frame based on the target detection result; and selecting a frame with the highest target information richness in the sub-shot boundary as a key frame. The invention can be applied to monitoring videos and movie and television videos.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

Image classification method based on noise reduction sparse automatic encoder and density space sampling

ActiveCN108416389ALearning robustnessSolve the problem that requires a large number of manually labeled samplesCharacter and pattern recognitionHidden layerData set
The invention discloses an image classification method based on a noise reduction sparse automatic encoder and density space sampling. The image classification method based on a noise reduction sparseautomatic encoder and density space sampling includes the steps: constructing an image block training set; constructing a noise reduction sparse automatic encoder of single hidden layer, inputting the image block training set, and training the noise reduction sparse automatic encoder; performing density space sampling on each image in a training image data set and a test image data set; using thenoise reduction sparse automatic encoder to extract local characteristic set information from the space area obtained by performing density space sampling on each image; using two layers of laminatedFisher Vector to encode the characteristic set information, so as to obtain the final Fisher vector of each image; and training a classifier by means of the Fisher vector, so as to realize image classification. The image classification method based on a noise reduction sparse automatic encoder and density space sampling can accurately acquire the image information, can improve the classificationaccuracy of images, and can be used for construction of a large scale image classification and retrieval system.
Owner:YANCHENG TEACHERS UNIV

A multi-axis additive manufacturing and forming sequence optimization method

The invention discloses a multi-axis additive manufacturing forming sequence optimization method, which comprises the following steps of obtaining triangular mesh model feature points based on interactive selection, and generating an initial segmentation line by utilizing a tracking projection algorithm; preliminarily segmenting the model into a plurality of sub-blocks by utilizing a region growing algorithm based on the initial segmentation line, and preliminarily sorting the sub-blocks according to the segmentation boundary information; taking the minimum support and the step effect as optimization objective functions, and using a multi-objective optimization algorithm to solve the optimal forming direction of the sub-block; establishing an optimized segmentation plane through the initial segmentation line and the optimal forming direction of the sub-block to smooth the segmentation boundary of the sub-block; and taking the optimization constraint as an optimization objective function, and optimizing the multi-axis additive manufacturing forming sequence of the segmented sub-blocks by utilizing a multi-objective optimization algorithm on the premise of meeting the physical constraint. According to the method, the flexible and optimized segmentation of the triangular mesh model can be achieved, and the forming surface quality and the forming efficiency are improved.
Owner:HUAQIAO UNIVERSITY

Method for determining and segmenting grounding pole field domain of direct current (DC) transmission system

The invention discloses a method for determining and segmenting a grounding pole field domain of a direct current (DC) transmission system. The method comprises the following steps of: (1) determining a field domain of a grounding pole according to the shape of the grounding pole; and (2) performing three-dimensional segmentation on the field domain of the grounding pole by using a fan segmentation method or a rectangle segmentation method according to the shape of the grounding pole so as to obtain a plurality of unit blocks. In the method for determining and segmenting the grounding pole field domain, the range of the grounding pole field domain is determined according to the shape of the grounding pole, a current field calculating area is defined in a certain range, the analysis of an open field in an actual system is avoided, and a computation model is simplified on the premise of guaranteeing the precision; meanwhile, non-uniform segmentation is adopted under the conditions of different depths and ranges, the segmentation is denser close to an electrode and is sparse away from the electrode, the computational accuracy and speed are considered, the field domain is finely determined and segmented, and the method is simple and high in university; therefore, the computed result of the grounding pole current meets the high-precision requirement.
Owner:ZHEJIANG UNIV +1

Insurance customer list screening method and device based on health medical big data

PendingCN112183113ARealize intelligent and precise screeningSolve the problem of incapable of comprehensive and accurate customer screeningFinanceSemantic analysisData sourceCustomer information
The invention discloses an insurance customer list screening method and device based on health medical big data, belongs to the technical field of semantic processing and semantic analysis of medicalbig data, and aims to solve the technical problem that clients cannot be accurately screened in multiple dimensions due to that fact of single index analysis based on a single data source during userscreening analysis in the prior art. According to the adopted technical scheme, the method specifically comprises the following steps: inputting insurance customer information; searching and extracting medical data, namely searching the medical data of a client from the medical health big data through the client information, and extracting the medical data of the client; performing semantic standardization processing, namely performing semantic standardization processing on the found client medical data to generate client standardized data with a semantic relationship, thereby forming a clientmedical semantic network; performing semantic matching, namely performing semantic matching on the screening rule base and the client medical semantic network; and obtaining client screening results.
Owner:山东健康医疗大数据有限公司

Planning and greening integrated multifunctional building

The invention relates to a planning and greening integrated multifunctional building which comprises a building external wall, a parapet, an entrance, a stair, a partition, a door, a lighting window, a horizontal floor slab, a roof cambered top plate, roofing soil, a greening vegetation stratum and the like. The soil and the greening vegetation stratum (2) cover on the roof cambered top plate (1), the soil and the greening vegetation stratum (2) cover on an entrance cornice top plate (11) and the outdoor ground (12), a hook edge is arranged on the surface of the roof cambered top plate (1) along the longitudinal direction of a section, the bodies of the building external wall (3) and the roof cambered top plate (1) are made of waterproof concrete, an outer waterproof layer is respectively arranged at the outer sides of a wall body and the top plate, and an inner waterproof layer is respectively arranged at the inner sides of the wall body and the top plate; and the entrance cornice top plate (11) is supported by an entrance cornice doorpost (4), and the stair (10) is an upper and lower layer vertical passage. The planning and greening integrated multifunctional building can be used for a plurality of building types, such as park commercial and matched service facilities, green residences, sightseeing and shopping galleries and the like.
Owner:郭禹辰

Three-generation house design

The invention relates to a three-generation house design. The three-generation house design comprises a hallway, a primary public space, a secondary public space, a primary rest area, a secondary restarea and a landscape balcony, wherein the primary public space and the secondary public space are located in the northwest-southeast direction or the southwest-northeast direction of the hallway separately; the primary rest area is arranged at the west side or the east side of the primary public space; the secondary rest area is arranged at the south side of the secondary public space; the landscape balcony is arranged at the south side of the secondary public space and connected with the secondary public space; hinge doors are formed in the south direction and the north direction of the hallway separately to communicate the primary public space with the secondary public space; a sliding door is formed in the landscape balcony to communicate the primary public space with the secondary public space; and the movement direction of a sliding door in the primary public space and the movement direction of a sliding door in the secondary public space are mutually vertical, so that interference is reduced. The three-generation house design has the advantages of being flexible in space division, providing higher space use possibility, facilitating elderly people and young adults to care for life with each other, and reducing the mutual interference degree to be the lowest.
Owner:广州越欣房地产开发有限责任公司

Parallel partition electromagnetic transient digital simulation method of AC and DC power system

ActiveCN101719182BFlexible segmentationRealize electromagnetic transient simulationSpecial data processing applicationsTransient stateMix network
The invention discloses a parallel partition electromagnetic transient digital simulation method of an AC and DC power system. The method comprises the following steps of: partitioning a target AC and DC power system into a plurality of subnets comprising an AC network subnet, a current converter subnet, a DC network subnet or an AC and DC mixed network subnet; acquiring equivalent impedance matrix and equivalent potential at port point of each subnet; acquiring current of the tie-line between the subnets; acquiring node voltages of each subnet according to the current of the tie-line betweenthe subnets; solving differential equations of a generator, a control system, and the like of each subnet; processing a user self-defined model, an MATLAB model and input and output information of a physical device; processing input and output information of an electromagnetic transient interface. The simulation method has the advantages of flexible net partition mode, high computation speed, andthe like. The simulation method can be simultaneously suitable for electromagnetic transient net partition parallel computation of an AC and DC system, parallel computation of electromechanical transient, accessing a user self-defined model, processing an MATLAB model and a physical device and the like, thereby realizing digital simulation of various transient and dynamic processes of the AC and DC power system.
Owner:CHINA ELECTRIC POWER RES INST +1

Method and device for segmenting point cloud data, storage medium and electronic equipment

ActiveCN110706238BFlexible segmentationAssisted driving decision-makingImage enhancementImage analysisData setPoint cloud
The embodiment of the present disclosure discloses a method and device for segmenting point cloud data, a storage medium, and an electronic device, wherein the method includes: determining the local area where each point cloud data point in the point cloud data set to be processed is located and dividing it into A predetermined number of sub-regions; sort the point cloud data points in each sub-region to obtain a predetermined number of point cloud data groups of the same order; determine that each point cloud data point in each point cloud data group of the same order corresponds to the corresponding The dependency relationship between adjacent point cloud data points, so as to obtain a predetermined number of dependency relationship sets; based on a predetermined number of dependency relationship sets, determine the probability value of each point cloud data point belonging to the predicted category; according to each point cloud data point The probability values ​​assigned to the predicted categories are used to segment the point cloud dataset to be processed. The embodiments of the present disclosure can be applied to object recognition in an outdoor environment in an unmanned driving scene, so as to better assist driving decision-making, and can also be used for recognition of indoor objects in more complex scenes.
Owner:NANJING INST OF ADVANCED ARTIFICIAL INTELLIGENCE LTD

Medicine cooling cabinet for medical treatment

The invention belongs to the field of medicines, and specifically provides a medicine cooling cabinet for medical treatment. According to problems that the positions of conventional separating platescannot be adjusted and a heat radiation screen cannot be cleaned, a following scheme is proposed. The medicine cooling cabinet comprises a cooling cabinet, a plurality of separating plates are arranged in the cooling cabinet, a refrigerating unit is arranged in the cooling cabinet, an inner wall of one side of the cooling cabinet is provided with a heat radiation opening, a heat radiation screen is arranged in the heat radiation opening, the bottom side of the separating plate is fixedly provided with an installation box, inner walls of two sides of the installation box are both provided withmoving holes, moving rods are both movably arranged in the two moving holes, and one ends, far from each other, of the two moving rods are both fixedly provided with ejecting blocks. According to themedicine cooling cabinet, the positions of the separating plates can be flexibly adjusted so that the space in the cooling cabinet can be flexibly segmented according to the requirement, and the utilization rate of the space in the cooling cabinet can be increased; besides, through active cleaning of the heat radiation screen, the heat radiation effect of the refrigerating unit is guaranteed, andthe demand of people can be satisfied.
Owner:隋永
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products