35results about How to "Quick and automatic extraction" patented technology

The invention relates to a remote sensing image road extracting method based on stereo constraint, which comprises the following steps: extracting and refining the edge of the left image of a stereo pair, thereby obtaining a binary image of the single pixel edge; carrying out shape constraint and vectorization on the binary image of the single pixel edge by using an improved phase grouping method; carrying out edge line node matching on the basis of grey scale correlations, thereby determining the homonymous image point of the edge line node on the right image; resolving node elevation on thebasis of an image pair RPC model parameter or interior / exterior orientation element forward intersection method; and determining the road extraction result on the basis of the road edge line constrained by the node elevation. Starting with the stereo image, the invention extracts the elevation information of the road edge line, which is obtained after edge extraction, refining, shape constraint and vectorization, and establishes a model by which the branch nodes of the candidate road edge lines can be matched and the elevation information can be acquired by carrying out forward intersection on the homonymous point information; and according to the elevation characteristic of the road, the invention establishes elevation constraint conditions, carries out elevation constraint, and extractssatisfactory road edge lines from the candidate road edge lines, thereby realizing quick automatic extraction of road thematic information on the remote sensing image.

The invention discloses a metamaterial simulation data processing method and a metamaterial simulation data processing device. The metamaterial simulation data processing method includes the steps of obtaining N transferring samples through a simulation algorithm, wherein each transferring sample comprises structural parameters characterizing metamaterial units and N is a natural number, obtaining distance values respectively comparing electromagnetic response characteristics of metamaterial units expressed by the N transferring samples with an electromagnetic response characteristic of a metamaterial unit expressed by a target sample, sequencing the N obtained distance values according to a heap sort algorithm, obtaining the transferring samples corresponding to the N distance values which are smaller in the sequenced distance values, and treating the transferring samples corresponding to the N distance values as designed samples, wherein n is a natural number less than N. The metamaterial simulation data processing method and the metamaterial simulation data processing device has the advantages of being capable of achieving automatic processing of metamaterial simulation data and improving data processing efficiency.

The invention belongs to the technical field of remote sensing, and in particular relates to an extraction method of water body thematic information of remote sensing images based on sequential nonlinear filtering. The method comprises the following four steps: preprocessing remote sensing images and completing sequential nonlinear filtering; calibrating filtering result image areas and calculating the feature values of each calibrated area; establishing the selection criteria of water body target areas; and carrying out automatic extraction of water body areas and post-processing of water body thematic extraction information based on morphology so as to generate thematic information vector data meeting the requirements of common GIS software finally. The extraction method, starting with the basic operation of grey-scale mathematical morphology, establishes a sequential nonlinear filtering model to directly carry out nonlinear filtering and extract water body areas in remote sensing images; according to relevant knowledge of water body, feature values of different water body areas extracted through sequential nonlinear filtering are calculated; according to water body imaging characteristics and relevant knowledge of water body areas, the selection criteria of the water body target areas are established to realize automatic and quick extraction of water body thematic information on remote sensing images. The extraction method is less influenced by noise and error and has strong robustness; moreover, the method realizes fully automatic processing of extraction water body without manual intervention, can process extensive data, and has less time consumption.

The invention relates to a method for automatically extracting a detection area of ​​a large offset printing image, which comprises the following steps: selecting a large offset printing image and preprocessing the offset printing large image; extracting one of the small single image areas in the offset printing large image, And automatically extract the positioning nucleus area in the small single image area; scale the large offset printing image, and obtain other small single image areas in the large offset printing image according to one of the extracted small single image areas, and perform Preliminary positioning: Accurately locate the positions of all small single-sheet image areas according to the automatically extracted positioning core area, and obtain all detection areas of offset printing large-sheet images. The present invention adopts an algorithm for automatically extracting positioning points, combined with image-based cross-correlation matching algorithms, feature point extraction and other methods, and achieves good results in automatic product area extraction in most application scenarios, and satisfies the needs of visual inspection in the offset printing industry. The need to automatically extract the product area of ​​a large image.

The invention relates to a method for extracting the text information in a new webpage, belonging to the field of webpage information analyzing and processing technique. The existing technique ordinarily adopts a packer to extract the interesting data from the web pages and the obtaining of information mode recognition knowledge of the packer is a time-taking and laborious, higher intelligence-demanding operation. The invention uses a stack data structure to convert the hiberarchy information of webpage data into vectors, constructs and analyzes Html tree, then making compression on the data of various layers of the Html tree, making data filtration, thinning, recognition and recombination to extract the needed data information. The invention is applied to extracting the template-generatednews information in the news web pages from a fixed website.

The present invention relates to the technical field of computer software. Disclosed are a knowledge graph automatic construction method and system for massive unstructured text. A named entity recognition problem is abstracted into one sequence labeling problem: one sentence is given, each word in a sentence sequence is labeled; an effective feature is designed on the basis of training data, various classification models are learned, a trained classifier is used to predict relations; multiple pieces of existing knowledge are linked, one large-scale unified knowledge network is created from the top level; and entity information are grabbed from three major online encyclopedias, open websites, relevant knowledge bases or search engine logs and integrated. The present invention significantly increases the speed of constructing a knowledge graph, increases time efficiency, reduces costs for labor resource by 30% or more. At the same time, the present invention provides improved domain portability, when constructing the knowledge graph, optimization is only required for entities and a relational extraction algorithm in the present invention for rapid implementation.

The invention discloses a method and a device for metamaterial simulation data. The method comprises that N transfer samples are obtained through a simulation algorithm, the transfer samples comprise structure parameters representing metamaterial units, N is a natural number; distance values generated by respectively comparing electromagnetic response characteristics of the metamaterial units represented by the N transfer samples and electromagnetic response characteristics of the metamaterial units represented by target samples are obtained; the obtained N distance values are subjected to Shell sort, the transfer samples corresponding to n small distance values in the sort are obtained, the transfer samples corresponding to the n distance values are used as design samples, and n is a natural number smaller than N. Automatic processing of the metamaterial simulation data can be achieved, and efficiency of data processing can be improved.