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 the basis 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 extracts satisfactory 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 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-generated news information in the news web pages from a fixed website.

The invention discloses a remote-sensing image building detection method based on multi-scale and multi-characteristic fusion. The method comprises steps that through high resolution remote-sensing image downsampling, an image pyramid formed by images in different scales is acquired; edge images of the image pyramid are calculated; a characteristic model is established through multi-set characteristic calculation and fusion of the edge images in different scales; according to the characteristic model and neighborhood local non-maximum inhibition, window selection is carried out to acquire a target window; small-scope expansion/contraction calculation of the target window is carried out to acquire a rectangular window; the rectangular window is turned according to a main direction of the target window to acquire an optimal target window, and a building is extracted according to the optimal target window. The method is advantaged in that multi-scale building detection on the Gaussian pyramid image is carried out, universality of detection on buildings different in sizes, shapes and directions is realized, and automatic building detection precision and efficiency are effectively improved.

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.

Embodiments of the invention provide a data extraction method and apparatus. The method comprises the steps of obtaining data extraction demand information input by a user; generating task description information in a computer readable form according to the data extraction demand information; obtaining a calculation script corresponding to a to-be-extracted data source according to the task description information, and determining a calculation platform corresponding to the data source; and scheduling the calculation script by utilizing the calculation platform to obtain an extraction result. According to the method and the apparatus provided by the embodiments of the invention, quick and automatic data extraction can be realized.

The invention discloses a method and a system for vehicle-mounted rapid navigation and positioning of land planning supervision implementation. The method for vehicle-mounted rapid navigation and positioning of land planning supervision implementation comprises the following steps of: carrying out analysis treatment on the traditional basic land data ( such as a current situation chart or a planning chart of land utilization ) for rapidly and automatically extracting road network data from initial data suitable for generating a road network; selecting planning paths; and automatically matching GPS (Global Position System) track points collected in the running process of a vehicle with roads on the road network. The system comprises a data management unit, a road network extracting unit, a path planning unit, a vehicle navigation unit and a land illegal information collection unit. In the method for vehicle-mounted rapid navigation and positioning of land planning supervision implementation, the GPS position and navigation system is applied in land supervising and inspection businesses, the illegal land utilization can be discovered and restrained earlier, and the system improves the working efficiency of land supervision as well as the efficiency and timeliness of law enforcement.

The invention discloses an ABAQUS crack propagation data extraction method and system, and a computer readable storage medium, and belongs to the field of data extraction. The ABAQUS crack propagationdata extraction method comprises the steps: generating and outputting a first function template through determining to-be-extracted data information; receiving an instruction for modifying the file format of the first function template, and converting the first function template into a second function template; extracting a field variable value and a data matrix of unit and node number information in the second function template, wherein the unit and node number information is specifically node numbers and node and node coordinate information corresponding to units; and processing the fracture unit data, and establishing a data extraction function library so as to complete the extraction of the crack propagation data. The ABAQUS crack propagation data extraction method is simple in operation, can achieve the quick and automatic extraction of the ABAQUS crack propagation data, and can greatly improve the extraction efficiency of the ABAQUS crack propagation related data.

The invention discloses an automatic dosing device for an injector. The automatic dosing device comprises a drug loading platform, a tri-axial moving mechanism, an injector push-pull control mechanism and a lower computer, wherein a plurality of circular holes which are matched with the sizes of medical ampoules and medical normal saline bottles are formed in the drug loading platform; the tri-axial moving mechanism is arranged above the drug loading platform; the tri-axial moving mechanism comprises three steering engines, an X axial screw rod, a Y axial screw rod and a Z axial screw rod; the three steering engines are respectively arranged at one ends of the X axial screw rod, the Y axial screw rod and the Z axial screw rod; the injector push-pull control mechanism is arranged at one end of the Y axial screw rod with a steering engine; an injector extracting controller, a spring and an injector fixing device arranged at the lower end of the spring are arranged on the injector push-pull control mechanism; the lower computer is respectively connected with the three steering engines and the injector extracting controller; and position coordinates of each medical ampoule and each medical normal saline bottle on the drug loading platform are stored in the lower computer.

The invention discloses a method for processing railway subgrade detecting radar data with sleeper interference eliminated, which comprises the following steps: finding out a position of a sleeper reflecting surface event of a railway subgrade detecting radar original data and extracting a sleeper reflected signal; performing low-pass filtering on the reflected signal to obtain a logic rule representing a sleeper position; and selecting the subgrade detecting original data by taking the logic rule as a reference, and obtaining the railway subgrade detecting radar data with the sleeper interference eliminated. The method extracts the relevant information of a sleeper according to a sleeper interference signal and eliminates the sleeper interference signal so as to facilitate the further processing of the railway subgrade detecting radar data. The method has the characteristics of safety, high efficiency and strong applicability.

The invention discloses a large-space-range oil storage tank extraction method, and the method comprises the steps: reading whether oil storage tanks are contained in a satellite image or not, monitoring the number, scale and spatial distribution of the oil storage tanks, and achieving the precise positioning of a VOCs emission source, thereby providing an effective technical support for the treatment of ozone and volatile organic compounds. The oil storage tank in the image is quickly identified by constructing an oil storage tank extraction model, and in the process of constructing the oil storage tank extraction model, the number of samples is increased through overturning transformation, random cutting and noise interference methods, so that the accuracy, practicability and universality of the model are improved.

The embodiment of the invention discloses a logging curve automatic tracking method and device based on pixel optimization and electronic equipment. The method comprises the steps that S1, pixel information of each pixel point in a logging image is acquired; s2, giving an initial tracking point on a logging curve in the logging image, and performing transverse tracking according to the initial tracking point, a given color threshold and a given transverse tracking distance; s3, obtaining the current optimal point in the next row of pixels, and carrying out the lateral tracking according to thecurrent optimal point, the color threshold and the lateral tracking distance; and S4, the step S3 is repeated until the distance between the initial tracking point and the current optimal point exceeds the given longitudinal tracking distance, and a final logging curve is obtained. According to the method, the logging curve can be quickly, accurately and automatically extracted from the logging image, and the anti-interference effect is good.

The invention provides a period extraction method and device, computer equipment and a readable storage medium. The method comprises the following steps: acquiring an image of a display panel to be detected; wherein the image comprises characteristic areas which are distributed periodically; the feature area comprises a key structure on the display panel to be detected; preprocessing the image to obtain a binary image; wherein the binary image comprises a first pixel point and a second pixel point; the second pixel point corresponds to the feature area; and performing autocorrelation analysis on all the second pixel points, and extracting the period of the feature area. Compared with the mode of manually setting the period in the prior art, the period of the image can be rapidly, accurately and automatically extracted based on self-phase analysis of key features in the image, the complexity of manually setting the period is avoided, the extraction efficiency is improved, and the invention is suitable for different to-be-detected display panels.

The invention provides a multi-task learning strategy-based multi-instrument visual tracking method in a laparoscope visual field, and the method comprises the steps: constructing a light-weight image segmentation network and a target regression network based on a light-weight LinkNet-18 neural network architecture, synchronously and rapidly extracting regions of all parts (a rod shaft and an end executor) of surgical instruments in a laparoscope image, and carrying out the recognition of all parts (a rod shaft and an end executor) of the surgical instruments in the laparoscope image; accurately positioning the joint position of the surgical instrument in the laparoscopic image in real time; on the basis of a multi-task learning strategy, an image segmentation network and a target regression network are coupled in an iterative interaction mode, a lightweight image segmentation and target regression task joint model is constructed, regions of all parts (a rod shaft and an end effector) of a surgical instrument in a laparoscopic image are synchronously and rapidly extracted, and meanwhile the joint position of the surgical instrument is accurately positioned. And calculating a visual tracking target point in the laparoscope image, and finally realizing real-time accurate tracking of multiple instruments in the field of view of the laparoscope.