85 results about "Profile diagram" patented technology

Methods and systems for generating contextual user-profile image on a webpage include capturing textual content provided by a user at the webpage. The textual content is parsed to identify keywords related to context. The keywords are contextually analyzed to identify one or more mood indicators. Current mood of the user is identified based on the one or more mood indicators. One or more modifiers for applying to the user-profile image are determined. The user-profile image is updated to incorporate the modifiers so as to reflect the current mood of the user. The updated user-profile image is returned to the webpage for rendering, in response to the textual content received from the user.

The invention discloses a method for automatically designing and optimizing a railway vertical profile. The method comprises the steps of carrying out ground line smoothening processing to an original ground line, fitting an initial slope to the smoothened ground line, carrying out vertical profile design constraint condition processing to the initial slope, forming a vertical profile automatic slope design scheme, optimizing the vertical profile based on a differential evolution algorithm, setting optimization control parameters, initializing the populations according to the vertical profile automatic slope design scheme, using a target function to assess the advantages and disadvantages of the individual vertical profile scheme, calculating an individual target function value, carrying out evolution among the populations by using a mutation operation, an interlace operation, a restoring operation, setting of railway tunnel and a selecting operation until the final evolution condition is reached, and outputting a vertical profile diagram and a standard check table. The method for automatically designing and optimizing railway vertical profile has the advantages of high automation degree, strong practicality, fast computing speed, and high promotion and application value in design and optimization of the railway vertical profile.

The invention provides an automatic hydraulic model establishment method based on CAD drainage network drawing information, and belongs to the crossing field of the municipal engineering information technology and the geographic information system technology. The method starts from the hydraulic model establishment and is based on the storage situation of the CAD drainage network drawing information, complex layering does not need to be conducted on CAD engineering drawings, the manual one-by-one attribute data recording work is greatly simplified, the CAD profile diagram attribute data are converted to a GIS database in batches through TrueTable software, data can be automatically recorded in batches, the complex operation of the manual one-by-one data recording is greatly reduced, the data recording work efficiency is improved, the quality of the model data is ensured, and the quality of an established hydraulic model is improved.

The invention provides an unmanned aerial vehicle hybrid propulsion system energy management and control method based on flight data, and the method comprises the steps: building a profile diagram ofenergy and power based on the flight historical data of an unmanned aerial vehicle, and dividing a flight stage into finite states through a kernel fuzzy c clustering algorithm; establishing flight mission parameters and flight environment parameters and energy by using a BP neural network based on the historical flight data; establishing an energy prediction model and a required power time sequence model required by each stage of flight according to the mapping relationship between the requirements and the power requirements; carrying out global planning of energy according to the profile diagram, and determining the working mode of the hybrid propulsion system in each stage; in the flight process, according to real-time power requirements of different flight states, achieving optimal control over instantaneous power through efficiency MAP graphs of key subsystems such as an engine, a motor and a power battery. Fusion optimization control over global planning and power instantaneous optimization of hybrid propulsion unmanned aerial vehicle energy is achieved, so that the fuel economy of a hybrid propulsion system in a whole flight mission plane is improved.

The invention discloses a broad spectrum insect situation automatic forecasting method based on the computer vision technology. According to the method, insect images of captured target insects are obtained at regular time; an obtained current insect image and a yesterday insect image are subjected to filtering treatment so as to obtain a current insect profile diagram and a yesterday insect profile diagram; the current insect profile diagram and the yesterday insect profile diagram are subjected to subtraction treatment so as to obtain an increment diagram; an insect characteristic spectrum is established and updated as per the increment diagram; the increment count value of insect quantity of this time is computed as per the increment diagram; the area count value of insect quantity is computed as per the insect characteristic spectrum; and further, the weighted average of the increment count value of insect quantity of this time and the area count value of insect quantity is obtained, and then the total amount of insects can be obtained through calculation. The broad spectrum insect situation automatic forecasting method combines machine vision, pattern recognition and biological chemistry methods, automatically forecasts the injurious insects as needed, obtains the population density of the injurious insects in the field, and provides scientific decision bases for early warning and comprehensive control of insect damage.

The invention discloses a Revit software-based rapid drawing method for a prefabricated stair detail drawing. The method sequentially comprises the following steps of S1, setting sharing parameters; S2, pre-creating a parameterized family; S3, creating a prefabricated stair project file, designing a view template, loading each parameterized family, setting prefabricated stair parameters, and adding placement embedded parts; S4, drawing a prefabricated stair template drawing section and a detail drawing; S5, drawing reinforcing steel bars; S6, creating a detail list; S7, drawing a reinforcementdiagram and a profile diagram of the shape of the steel bar; S8, carrying out size marking; S9, carrying out typesetting; S10, printing a drawing. According to the Revit software-based rapid drawingmethod for the prefabricated stair detail drawing, modification is in instant linkage, information extraction is simple and convenient, data statistics is efficient, and the drawing speed is high.

The invention discloses a vehicle identification method based on a single frame image. The method is used in the intelligent traffic field and is used to solve problems that identification kinds are less and an identification rate is low in the current vehicle identification. The method comprises the following steps: according to the collected single frame image, carrying out initial road calibration and acquiring scale information of vehicles at different positions; when current time is daytime, detecting a vehicle bottom area and a vehicle window area respectively and acquiring the vehicle position information; if the current time is night, detecting a car light area and a vehicle window position and acquiring the vehicle position information; according to the scale information and the position information, using a symmetry to acquire a profile diagram of the object vehicle; according to the profile diagram, carrying out vehicle type identification. According to the embodiments of the invention, various types of the vehicles can be rapidly and high-efficiently identified and a demand of road traffic law enforcement can be satisfied.

The invention provides an establishment method for a fracture-cave distribution diagram of a fracture-cave carbonate reservoir, a model and an application. The method comprises the following steps ofbased on a built geological model of a target well group region, marking fractures, karst caves and underground rivers, and obtaining a three-dimensional profile structure diagram of the geological model of the target well group region; based on the three-dimensional profile structure diagram, performing layered display on the geological model, and selecting a most representative path between wells of the target well group region to perform two-dimensional cutting connection on the wells, thereby obtaining a two-dimensional profile diagram between the wells; based on the two-dimensional profile diagram, delineating regions of the karst caves and the underground rivers, taking a whole of the delineated closed region as the karst cave region, and obtaining a two-dimensional profile fracture-cave structure depiction diagram; and restoring middle-scale fractures around large-scale fractures in the two-dimensional profile fracture-cave structure depiction diagram, so as to obtain the fracture-cave distribution diagram of the fracture-cave carbonate reservoir.

The invention provides a method and a device reconstructing three-dimensional surfaces of potatoes by using fixed-axis rotation profile diagrams. The method comprises the steps of collecting side images of a potato sample via a camera; acquiring three-dimensional skeleton data of the potato sample via image processing; further forming the curved surface of the model surface of the potato sample through further processing of the three-dimensional skeleton data of the potato sample to finish the reconstruction of the three-dimensional surface. The device comprises an annular light source, a camera, a rotary table controller and an electric rotary table; a potato sample is installed on an output shaft of the electric rotary table; the electric rotary table is connected with the rotary table controller; the camera faces right downward and captures the side images of the potato sample; the rotary table controller and the camera are connected with a computer via cables; the annular light source is installed between the potato sample and the camera. The three-dimensional surface is reconstructed based on multiple profile diagrams collected when a potato rotates around a fixed axis, so that the accuracy of potato shape detection is improved. The detection apparatus is simple.

The invention discloses a three-dimensional model searching method based on a sketching. The three-dimensional model searching method based on the sketching comprises the following steps: (1) generating multi-perspective profile diagrams; (2) extracting a placeholder diagram characteristic, a distance conversion characteristic, a profile signature characteristic, a Fourier descriptor, a Hu moment characteristic and a Poisson characteristic of each multi-perspective profile diagram; (3) obtaining a form of a novel characteristic; (4) by means of the form of the novel characteristic, extracting characteristics of a corresponding dimension from all the characteristics of the multi-perspective profile diagrams obtained in the step 2 to form a novel characteristic; (5) extracting a sketching characteristic as the step 2; (6) obtaining a novel characteristic of the sketching from characteristics of a sketching profile diagram in the same mode as the step 4 by means of the form of the novel characteristic obtained from the step 3 in an off-line period; and (7) finding out a novel characteristic of the profile diagram most similar to the novel characteristic of the sketching through a k-d tree characteristic matching method and determining a three-dimensional model generating the profile diagram. The three-dimensional model searching method based on the sketching lowers sensitiveness on setting of parameters, and improves the searching effect.

The invention discloses a tire section structure surveying instrument and a tire section structure surveying method. The tire section structure surveying instrument comprises a two-dimensional measurement mechanism and an image processing and controlling mechanism, wherein the two-dimensional measurement mechanism comprises a stander, a base, a transparent scanning platform, a tire section clamp and a scanning component; the stander is arranged on the base; the transparent scanning platform is arranged above the stander; the scanning component is arranged below the transparent scanning platform; the tire section clamp is arranged above the transparent scanning platform; and the scanning component is electrically connected with the image processing and controlling mechanism. The surveying method comprises the following steps that: the scanning component shoots a tire section arranged on the transparent scanning platform according to a photographic route; and the image processing and controlling mechanism splices each acquired image and performs computer-aided design (CAD) conversion. The tire section structure surveying instrument is novel equipment in the field of tire measurementand is applicable to tire section detection and section structure data analysis, so that a profile diagram of the tire section, a steel wire distribution diagram and a rubber layer distribution diagram can be acquired accurately; and data is provided for design and detection of the tire section.

The invention discloses an intelligent positioning method for small ceramic files based on multi-feature fusion. The intelligent positioning method comprises the steps of S1, image acquisition; S2, image preprocessing; S3, feature extraction, S4, image target determination; and S5, ceramic file positioning. In the step of image acquisition, an image is acquired through a high-speed linear array CCD camera. In the step of image preprocessing, gray processing is firstly performed on the image, then filtering and denoising processing is carried out, the filtered image is segmented by adopting an edge detection algorithm, the profile of the small ceramic tile is extracted, and then a profile diagram of the ceramic tile is acquired. In the step of feature extraction, corresponding primitive features are generated based on geometric features of the ceramic tile profile in the profile diagram in the step S2; and a logical AND operation is performed by using a filtered image and the profile mask diagram in the step S2, transferring an operation result diagram into an HSV color space, and color features are generated; and combination features are generated according to the primitive features and the color features. The intelligent positioning method realizes high-precision positioning for the small ceramic tiles at a large FOV (Field of View), thereby providing accurate positioning data for visual inspection and robot grasping. In addition, multiple segmentation units can operate concurrently in a multi-threaded system, and the real-time performance of the system is improved.

The embodiment of the present invention discloses an automatic focusing method and device used for a microscope. The method comprises the steps of adjusting the microscope on a or a plurality of training planes to shoot a training image containing at least one focusing line, finding out the focusing line from the image, and determining a corresponding training focusing line gradient profile diagram for each training plane; arranging the at least one focusing line on the bottom surface of a counting pool; adjusting the microscope to a first plane to shoot an actual image, finding out the focusing line from the image, and calculating a or a plurality of actual measurement focusing line gradient profile diagrams of the first plane; determining a training focusing line gradient profile diagram matching the one or the plurality of actual measurement focusing line gradient profile diagrams, and adjusting the microscope from the first plane to an accurate focusing plane according to the relative position relation of a second plane corresponding to the matched training focusing line gradient profile diagram and the accurate focusing plane.

The invention discloses a method for accurately identifying flue-cured tobacco flavor types. According to the invention, a smoking and evaluating group is organized, wherein the members in the group are good at sensing the scents of flue-cured tobaccos; 8 characteristic scent components are evaluated and quantified with a blind-review method, wherein the 8 scents are tobacco scent, fragrant scent, sweet scent, fruit scent, flower scent, spicy scent, wood scent, and coke scent; scent score data is adopted as a basis, and a flavor style characteristic profile diagram is drawn; with the profile diagram as a basis, flue-cured tobacco scent area index S is obtained with a calculation formula S=1 / 2*sinC*a*b, wherein a and b are two adjacent flavor style characteristic values, and C is an included angle of a and b. If S is smaller than 25.0, the flue-cured tobacco is strong-flavored flue-cured tobacco. If S is 26.0-30.0, the flue-cured tobacco is middle-flavored flue-cured tobacco. If S is greater than 30.0, the flue-cured tobacco is light-flavored flue-cured tobacco. The flue-cured tobacco flavor type identifying method provided by the invention is practicable, accurate, convenient, and visual.

The invention discloses a spacecraft classifying and identifying method based on generalized Hough transformation, which comprises the following steps of: drawing a radar cross-section (RCS) sequence image aiming at the RCS sequence of a certain radar observation arc section, calculating the compactness of the pixels of the RCS sequence image, carrying out initial classification, filtering the RCS sequence image, also generating a profile diagram and determining the image of a coarse positioning area by using generalized Hough transformation; extracting the skeleton characteristics of the image of the coarse positioning area and carrying out fine matching with the skeleton characteristic of the image of a template; and finally, carrying out matching verification based on the compactness degree of the pixels. According to the spacecraft classifying and identifying method based on the generalized Hough transformation, the aim of automatic target identification can be realized, and the identification rate is also enhanced.

The invention belongs to the field of digital modeling display, and particularly relates to a method and system for generating a plane profile diagram based on a building model and a storage medium. In the prior art, a plane profile diagram generated according to a building model generally contains all primitives, three-dimensional and two-dimensional synchronous rendering inevitably adds additional pressure to a rendering engine, and height cutting is difficult to realize accurately. Based on a building model as a rendering object, attributes of all primitives are obtained through file analysis corresponding to a rendering object, or the primitives in a building model are classified through a method of customizing extended data by a user, and then the filtered primitives are rendered fromthe perspective of a top view to generate a plane contour map through a filtering rule customized by the user. The method does not increase the pressure of three-dimensional rendering, does not entangle the problem of plane generation height, does not need to worry about the problem of splitting from the middle of a primitive, and supports two-dimensional and three-dimensional linkage.

The invention discloses a bottle cap gap width estimation method by using a transmission type illuminating and imaging system. The bottle cap gap width estimation method comprises the following steps: (1) constructing the transmission type illuminating and imaging system to obtain an illumination detected image of a bottle cap gap region; (2) automatically determining a bottom cap region by using a regional marking algorithm; (3) using a canny edge detection algorithm to obtain a profile diagram of the bottle cap region, and using a growth type straight line detection algorithm to obtain a straight line profile of the upper edge of a gap; (4) using a black and white binarization algorithm to determine the straight line profile of the lower edge of the gap to obtain a pixel region of the whole bottle cap gap; and (5) using a pixel-actual distance conversion relation to obtain an estimated width value of the bottle cap gap. According to the bottle cap gap width estimation method disclosed by the invention, the transmission type illuminating and imaging system is used, thereby being capable of effectively avoiding the interference of the reflecting property of a material to the detected image; and by combining with an optimized visual detection algorithm, the width profile of the bottle cap gap can be accurately detected, so that the maximum value of the width of the bottle cap gap can be estimated.

The embodiment of the invention discloses an electronic map slope data generation method. The method includes: obtaining original slope data in a line profile diagram, and generating an original slopedata table according to a preset original slope data structure and the original slope data; inputting the original slope data table to a trackside signal device arrangement diagram, and traversing line, turnout, section and device kilometer post information of the trackside signal device arrangement diagram according to the data in the original slope data table; and generating electronic map slope data according to a preset target slope data structure in a traversal process. According to the method, the original slope data in the line profile diagram is obtained, the original slope data tableis generated, then the trackside signal device arrangement diagram is input, and the electronic map slope data can be automatically generated according to the preset target slope data structure so that the manpower consumption of projects is greatly reduced, the cost is lowered, and the accuracy and the work efficiency of the manufacture of the electronic map data can be effectively improved.

The invention discloses an intelligent table lamp. The table lamp comprises a table lamp body, a camera, a control module and a reminding module, wherein the control module is used for receiving a video image acquired by a camera, generating a human body profile diagram of a user according to a preset rule, judging the positions of a head and the shoulders, calculating the difference between the positions of the head and the shoulders, judging that a myopia sitting posture occurs if the difference meets a preset threshold value, and controlling a reminding module to output reminding information. The intelligent table lamp calculates the relative positions of the head and shoulders of the human body through the control module to judge whether the sitting posture of the user is accurate or not. The sitting posture detection method overcomes the sitting posture detection error caused by inconsistent requirements of individual difference on the height of the camera when specific features such as eyes or mouth of a user are directly collected. The lamp has the advantages of high sitting posture detection accuracy, strong practicability, safety, reliability and the like, and can well help the user to prevent myopia. The invention further discloses a sitting posture detection method and electronic equipment.

The invention relates to a two-stage expression animation generation method based on double generative adversarial networks. The method comprises the following steps of: firstly, extracting expressionfeatures in a target expression profile diagram by utilizing an expression migration network FaceGAN in a first stage, and migrating the expression features to a source face to generate a first-stageprediction graph; in a second stage, supplementing and enriching the details of eye and mouth regions which contribute much to expression changes in the prediction graph in the first stage by using adetail generation network FineGAN; and generating a fine-grained second-stage prediction graph and synthesizing a face video animation, wherein an expression migration network FaceGAN and the detailgeneration network FineGAN are both realized by adopting a generative adversarial network. According to the method, the two-stage generative adversarial network is provided for expression animation generation, expression conversion is carried out in the first stage, image detail optimization is carried out in the second stage, the designated area of the image is extracted through a mask vector, emphasis optimization is carried out, and meanwhile, a local discriminator is combined for use, so the generation effect of important parts is better.

The invention provides an assembly and construction process of a steel skeleton light roof. The assembly and construction process comprises the steps of building a wall on the ground, drawing a wall profile diagram according to the wall, preparing a light steel skeleton and roof panels, drawing a construction layout drawing, marking and numbering the roof panels and the construction layout drawing, hoisting the light steel skeleton to the wall, hoisting the roof panels according to the marking order, welding the roof panels, and filling and compacting the gaps between the roof panels. By adopting the assembly and construction process, components which make up the steel structure roof are pre-processed by using standardized machining processes, the dimensional accuracy of the components isimproved, the assembly error is reduced, the gap size between the adjacent roof panels during assembly is strictly controlled, and filling, compacting and other operations are conducted on the gaps after assembly, so that the building roof has the advantages of high structural strength, good waterproof and thermal insulation performance, low manufacturing cost, simple construction and the like, and the construction quality and the construction efficiency are improved.

The invention discloses a method for locating circular algae in a microimage and relates to the location of algae. The invention provides a method for locating the circular algae in the microimage. The method comprises the following steps: creating an original microalgae image database by a microscope and an image acquisition device and installing the database in a computer, wherein the resolution ratio of each original algae image at least reaches 100*100; extracting a region where the target algae locates approximately by adopting general computer image-segmentation technologies, such as threshold segmentation, canny edge detection, and the like to obtain a pre-locating profile A; judging the circularity of the profile A by adopting general circularity judgment methods and a perimeter-area ratio method, wherein the general circularity judgment methods are a profile diagramming method, and the like; and if the circularity of the profile A is within a tolerance range, carrying out hough conversion or curve fitting on the base of the profile A to obtain a corrected profile B which is final location of the circular algae.

The invention provides an adhesive corn ear segmentation method and device used in cell corn ear species testing. The method comprises the steps of: obtaining a two-dimensional colored picture of cell corn ears collected by a two-dimensional image collection device, and processing the two-dimensional colored picture into a binary picture including at least two binary sub-images (hereinafter referred to as sub-images); obtaining a blank profile diagram of any one sub-image, and calculating the perimeter and area of the blank profile diagram; according to the perimeter and area, calculating the adhesive coefficient of the sub-image; if the adhesive coefficient is no more than a preset value or the area is no less than a preset value, generating an image and a background mark line; and according to the mark line and the binary picture, generating a mask for segmenting the sub-images, the segmenting the sub-images according to the mask, and obtaining profile diagrams of the sub-images. The device comprises a binary processing unit, a profile diagram obtaining unit, a calculation unit, a mark line generation unit, a mask generation unit and an image segmentation unit. According to the invention, the speed is high, the efficiency is high, and the adhesive corn ear segmentation method and device are applicable to species testing of various kinds of adhesive corn ears and are universal.

The invention relates to a rapid mass spectrometry method for indentifying unknown sesquiterpenes pyridine alkaloids in thunder god vine, which belongs to the pharmacy field. The method comprises the following steps: processing Chinese fevervine herb by a pre-treatment process of a sample through solvent ultrasonic extraction; using an electro-spray, a quadrupole and a time-of-flight mass spectrometer for analyzing fragment ions of the known single sesquiterpenes pyridine alkaloid, especially analyzing the fragment ions through frame cracking; using a high performance liquid chromatography, the electro-spray and the quadrupole and the time-of-flight mass spectrometer to obtain a secondary mass spectrum of sesquiterpenes pyridine alkaloids in a complex system to obtain the fragment ions of an unknown compound, wherein a profile diagram of the fragment ions of sesquiterpenes pyridine alkaloid in the complex system can be respectively obtained by using two methods; comparing the profile diagram of the fragment ions of the sesquiterpenes pyridine alkaloid in the known complex system and the complex system and comparing the characteristic fragment ions, and performing a rapid structural analysis on the unknown sesquiterpenes pyridine alkaloid in the complex system.

The invention discloses a depth image super-resolution method based on a multidirectional dictionary. The method comprises the following steps: 1) extracting color image features and obtaining a profile diagram; 2) carrying out interpolation on a low-resolution depth image, and expressing features thereof through high-pass filtering; 3) carrying out block segmenting on the low-resolution depth image, and calculating geometric direction of each image block; 4) carrying out dictionary training; and 5) selecting a dictionary according to the geometric direction obtained in the step 3) and reconstructing a depth image. According to the technical scheme, resolution of the depth image is allowed to be enhanced, and boundary texture region is clear.

The invention discloses a thickness measuring method for insulating and sheathing materials of a cable and an optical cable. The method is characterized in that: after an appropriate amplification factor of an optical microscope and an appropriate resolution of a digital image collector (like an industrial camera) are set, digital image collection is carried out; a collected digital image is transmitted to a computer or a digital processor; binarization processing and edge detection are carried out to extract a profile diagram; and then automatic processing is carried out by a program in a digital processor; thicknesses of insulating and sheathing materials of a cable and an optical cable are calculated and obtained and measurement results are displayed; at last, a record report is generated according to measurement result data and a marked picture. According to the invention, the method can be realized simply; the measuring speed is fast; the measuring results are reliable and have high precisions. And a method of rapid and accurate measurement on thicknesses of insulating and sheathing materials of a cable and an optical cable is provided for correlated metering and detection industries in China.

The invention relates to the technical field of bridge maintenance, in particular to an image-based bridge BIM model crack visualization creation method, which comprises the following steps of S1, collecting crack information, and shooting a crack picture; S2, importing the photo into a three-dimensional model, adjusting the size of the photo, drawing a crack extension sketch and converting the crack extension sketch into multiple lines; S3, extracting a three-dimensional model of the bridge member, and establishing a local coordinate system at a crack endpoint position; s4, transferring the multi-segment line into a local coordinate system to obtain a lofting path; s5, drawing a crack cross section profile diagram to obtain a lofting profile; s6, generating a crack solid model; and S7, importing the crack solid model generated in the step S6 into a three-dimensional model of the bridge member to obtain a bridge member BIM model with cracks. The method has the substantive effects thatthe crack information is collected on site, the bridge component BIM model with cracks can be obtained through simple processing, modeling is simple and rapid, and bridge maintenance can be assisted.

The invention discloses an aircraft engine tail profile measurement device and method based on machine vision. The device comprises a computer, two CCD cameras, two linear array semiconductor lasers and modulators. The output of the computer is connected with a pulse generator, the pulse generator is connected with the CCD cameras and the linear array semiconductor lasers, the linear array semiconductor lasers are connected with laser emission heads through the modulators, and the CCD cameras capture linear array profiles and upload the linear array profiles to the computer through image acquisition cards. The measurement method includes the steps that the CCD cameras capture images respectively, profile diagrams are acquired from strong light in a laser lock-on imaging mode, and after the profiles are corrected, the images acquired by the two CCD cameras are fused. According to the aircraft engine tail profile measurement device and method based on machine vision, the two CCD cameras are used for partially capturing the profile diagrams of the linear arrays of the tail of an engine in the field of view and capture flames on the tail in the field of view, the working conditions of the engine are studied in the aspect of tail flame images and the aspect of tail profile changes, and thus the reliability of detection is improved.

The invention provides a house type image processing method, system and device and a computer readable storage medium. The house type image processing method comprises the steps: acquiring a plane contour image of a house type, wherein the plane contour image comprises contour images of a plurality of rooms of the house type, and the contour image of each room comprises a plurality of edges and aplurality of vertexes; for at least one vertex of the contour map of each room, selecting vertexes meeting a first condition from the contour maps of other rooms as associated vertexes of the at leastone vertex to obtain associated point pairs in the contour map of the house type; determining a correction offset of at least one room in the plurality of rooms based on the associated point pair; and correcting the profile diagram of the at least one room according to the determined correction offset of the at least one room.