CN112633188A - Wall body identification method, device, equipment and medium of house type graph - Google Patents
Wall body identification method, device, equipment and medium of house type graph Download PDFInfo
- Publication number
- CN112633188A CN112633188A CN202011577948.5A CN202011577948A CN112633188A CN 112633188 A CN112633188 A CN 112633188A CN 202011577948 A CN202011577948 A CN 202011577948A CN 112633188 A CN112633188 A CN 112633188A
- Authority
- CN
- China
- Prior art keywords
- house type
- closed
- area
- type area
- house
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 74
- 238000012545 processing Methods 0.000 claims abstract description 37
- 238000007781 pre-processing Methods 0.000 claims abstract description 21
- 238000005520 cutting process Methods 0.000 claims description 38
- 230000008569 process Effects 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 abstract description 3
- 238000009435 building construction Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 9
- 238000001514 detection method Methods 0.000 description 4
- 230000002708 enhancing effect Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000007789 sealing Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 235000017166 Bambusa arundinacea Nutrition 0.000 description 1
- 235000017491 Bambusa tulda Nutrition 0.000 description 1
- 241001330002 Bambuseae Species 0.000 description 1
- 235000015334 Phyllostachys viridis Nutrition 0.000 description 1
- 239000011425 bamboo Substances 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/42—Document-oriented image-based pattern recognition based on the type of document
- G06V30/422—Technical drawings; Geographical maps
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention relates to the technical field of house type graph data processing, and discloses a wall body identification method, a device, equipment and a medium of a house type graph, wherein the method comprises the following steps: obtaining a copy picture to be processed; carrying out image preprocessing on the copy picture to be processed to obtain a simplified image; performing wall polygon recognition on the simplified image through a house type area recognition model to recognize a plurality of house type areas; dredging each house type area to obtain a wall body area corresponding to each house type area; and combining all the wall body areas to generate the wall body of the house-type picture corresponding to the copy picture to be processed. The method and the device realize automatic identification of the wall body area of the copy picture to be processed, automatically combine and generate the wall body of the house type picture, reduce labor cost, improve the wall body identification efficiency of the house type picture, improve the accuracy and quality of the wall body identification of the house type picture, provide accurate house type pictures for subsequent building construction and ensure the construction progress.
Description
Technical Field
The invention relates to the technical field of house type graph data processing, in particular to a wall body identification method, a wall body identification device, wall body identification equipment and a wall body identification medium of a house type graph.
Background
At present, with the rapid development of real estate economy in China, more and more house buildings need to be designed like bamboo shoots in spring after rain, most of building designers design on paper with pens, copy drawings of paper files are output after the design is finished, professional drawing workers draw on a computer according to the copy drawings to draw a house type picture and determine the wall body of the house type picture, in the process, the professional drawing workers spend a great amount of time reading the copy drawings and draw by means of drawing experience of the professional workers, the situation that the wall body of the house type picture is inconsistent or misunderstood with the house type picture designed by the copy drawings exists, the drawn house type picture is incorrect, the wall body with the house type picture is inconsistent, the wall body is a main framework of the house type picture, layout planning among all rooms is determined, the foundation of a building of a construction unit is provided, and if the building is carried out according to the wall body of the incorrect house type picture, a large amount of capital cost is required to be invested for reworking, so that huge loss is caused, and the construction progress and cost of the house are seriously influenced.
Disclosure of Invention
The invention provides a wall body identification method and device of a house type picture, computer equipment and a storage medium, which realize the automatic identification of the wall body area of the copy picture to be processed and the automatic combination to generate the wall body of the house type picture without manual drawing, improve the wall body identification efficiency of the house type picture and improve the accuracy and quality of the wall body identification of the house type picture.
A wall identification method of a house type graph comprises the following steps:
acquiring a copy picture to be processed;
carrying out image preprocessing on the to-be-processed copy picture to obtain a simplified image;
performing wall polygon recognition on the simplified image through a house type area recognition model to recognize a plurality of house type areas;
dredging each house type area to obtain a wall body area corresponding to each house type area;
and combining all the wall body areas to generate a wall body of the house type picture corresponding to the copy picture to be processed.
A wall recognition apparatus for a house layout, comprising:
the acquisition module is used for acquiring a copy picture to be processed;
the preprocessing module is used for preprocessing the image of the copy picture to be processed to obtain a simplified image;
the identification module is used for carrying out wall polygon identification on the simplified image through a house type area identification model to identify a plurality of house type areas;
the dredging module is used for dredging each house type area to obtain a wall body area corresponding to each house type area;
and the generating module is used for combining all the wall body areas to generate a wall body of the house-type drawing corresponding to the copy drawing to be processed.
A computer device comprising a memory, a processor and a computer program stored in said memory and executable on said processor, said processor implementing the steps of the wall identification method of the above-mentioned house map when executing said computer program.
A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the wall identification method of a floor plan as described above.
The wall body identification method, the wall body identification device, the computer equipment and the storage medium of the house type picture provided by the invention acquire the copy picture to be processed; carrying out image preprocessing on the to-be-processed copy picture to obtain a simplified image; performing wall polygon recognition on the simplified image through a house type area recognition model to recognize a plurality of house type areas; dredging each house type area to obtain a wall body area corresponding to each house type area; and combining all the wall body areas to generate a wall body of the house type graph corresponding to the copy picture to be processed, so that image preprocessing and polygon recognition of the copy picture to be processed are realized, the house type areas are automatically recognized, dredging processing is carried out on all the house type areas to obtain the wall body areas, and finally the wall body of the house type graph corresponding to the copy picture to be processed is generated in a combined mode.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
FIG. 1 is a schematic diagram of an application environment of a wall recognition method for a house type diagram according to an embodiment of the present invention;
FIG. 2 is a flow chart of a wall identification method for a floor plan in accordance with an embodiment of the present invention;
FIG. 3 is a flowchart illustrating step S20 of the wall identification method of the floor plan according to an embodiment of the present invention;
FIG. 4 is a flowchart of step S20 of the wall identification method of the floor plan according to another embodiment of the present invention;
FIG. 5 is a flowchart illustrating step S30 of the wall identification method of the floor plan according to an embodiment of the present invention;
FIG. 6 is a functional block diagram of a conversion module of the wall identification appliance of the house layout according to one embodiment of the present invention;
FIG. 7 is a schematic diagram of a computer device in an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The wall identification method of the house type graph provided by the invention can be applied to the application environment shown in figure 1, wherein a client (computer equipment) is communicated with a server through a network. The client (computer device) includes, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server may be implemented as a stand-alone server or as a server cluster consisting of a plurality of servers.
In an embodiment, as shown in fig. 2, a wall identification method of a house type graph is provided, which mainly includes the following steps S10-S50:
and S10, acquiring a copy picture to be processed.
Understandably, the copy to be processed is an image obtained by photographing or scanning a copy made by a user through hand drawing, and the copy to be processed needs to be converted into a user-type image and needs to identify a wall in the user-type image.
And S20, performing image preprocessing on the copy picture to be processed to obtain a simplified image.
Understandably, the image preprocessing is to perform processing procedures such as graying, noise removal, line enhancement in an image, line drawing, image filtering and the like on the to-be-processed copy image, the to-be-processed copy image is subjected to the image preprocessing, so that effective lines of the to-be-processed copy image can be extracted and enhanced, useful information in the to-be-processed copy image is retained, noise is removed, and the simplified image is obtained and is the to-be-processed copy image after the image preprocessing.
In an embodiment, as shown in fig. 3, in step S20, the image preprocessing on the to-be-processed copy map to obtain a simplified image includes:
s201, carrying out edge denoising processing on the to-be-processed copy image to obtain a denoised image.
Understandably, the edge denoising processing process may be to perform graying processing on the to-be-processed copy image, convert a color image into a grayscale image, apply fourier transform to perform denoising in the converted grayscale image to obtain a process image, and perform denoising processing on a line edge in the process image by an eight-field denoising method to remove edge noise of the line, thereby obtaining the denoised image, where the principle of the eight-field denoising method is to sequentially traverse all non-white points in the image, calculate the number of non-white points in the adjacent eight points around the image, and if the number is less than a preset fixed value, the point is a noise point, and the denoised image is an image from which noise in the to-be-processed copy image is removed.
S202, performing line enhancement processing on the de-noised image to obtain an enhanced image.
Understandably, the line enhancement processing process is a process of enhancing the sharpness of the lines by applying a sharpening filter to increase the contrast between adjacent pixel points in the de-noised image, so as to make the image clearer and improve the contrast, and particularly for the surrounding of the lines, the contrast of the pixel points around the lines is improved, so as to enhance the sharpness of the lines, and the enhanced image is an image which enhances the lines in the de-noised image.
And S203, performing linearization processing on the lines in the enhanced image by using a straight line generation algorithm to obtain a basic image.
Understandably, because a straight line drawn by the drawn copy picture can be bent to a certain degree, a line in the copy picture needs to be subjected to linearization processing, that is, the straight line with the certain degree of bending is converted into a straight line, the straight line generation algorithm is an algorithm for identifying pixel points which are approximate to straight lines in an image and generating the straight line, the straight line generation algorithm can be set according to requirements, for example, the straight line generation algorithm can be a numerical differentiation algorithm (DDA algorithm) or a Bresenham straight line algorithm (Bresenham algorithm), the linearization processing is to identify pixel points which are approximate to straight lines in the enhanced image, identify straight line pixel points in a certain direction, generate a processing process of the straight line according to the straight line pixel points, and the base image is the enhanced image after the linearization processing.
And S204, performing linear connection on the basic images to obtain the simplified images.
Understandably, the straight line connection is a processing procedure of connecting the straight line generated in the basic image and connecting two ends of the generated straight line with adjacent surrounding pixel points, and the simplified image is the basic image after the straight line connection.
The invention realizes the edge denoising treatment of the to-be-treated copy image to obtain a denoised image; performing line enhancement processing on the de-noised image to obtain an enhanced image; performing linearization processing on the lines in the enhanced image by using a straight line generation algorithm to obtain a basic image; and carrying out linear connection on the basic images to obtain the simplified images, thus realizing the relevant operation of image preprocessing on the copy picture to be processed, enhancing the useful information of the copy picture to be processed, enhancing the lines in the copy picture to be processed, and improving the identification accuracy and reliability for subsequent wall identification.
And S30, performing wall polygon recognition on the simplified image through the house type area recognition model, and recognizing a plurality of house type areas.
Understandably, the house type area recognition model is a model for realizing the recognition of closed or non-closed polygonal areas containing rectangular house type features for the input image, wherein the house type area recognition model is a trained neural network model, the wall body polygon recognition process is to extract the rectangular house type features and the features of a closed or non-closed polygon area through the house type area recognition model, identifying a region having closed or non-closed polygons containing rectangular house type features according to the extracted rectangular house type features and the closed or non-closed polygon features, thereby obtaining the house type area, wherein the rectangular house type characteristic is a characteristic with a rectangular characteristic and two adjacent parallel straight lines in the same direction, the house type area is a polygonal area with closed or non-closed rectangular house type characteristics.
In an embodiment, as shown in fig. 4, in step S30, the performing wall polygon recognition on the simplified image through the dwelling area recognition model to recognize a plurality of dwelling areas includes:
s301, performing rectangular house type feature on the simplified image through the house type area identification model.
Understandably, the simplified image is subjected to feature extraction through the house type area identification model, the rectangular house type features are features which have rectangular features and are provided with two adjacent parallel straight lines in the same direction, the rectangular features are related features with similar rectangles, such as four intersection points, features with mutually perpendicular lines and the like, and because most house type structures are rectangular structures and the edges of the rectangular house type are mostly used as walls, the walls in the house type graph can be identified more accurately by extracting the rectangular house type features.
S302, carrying out rectangular region identification on the simplified image according to the extracted rectangular house type features, and identifying a rectangular region in the simplified image.
Understandably, according to the extracted rectangular house type features, a rectangular region in the simplified image is identified, where the process of identifying the rectangular region may be an identification process of a target detection model based on FASTER R-CNN or an identification process of a target detection model based on SSD, that is, the house type region identification model includes a network structure of the target detection model, and the network structure of the target detection model may be a network structure of FASTER R-CNN or a network structure of SSD, so that the rectangular region having the rectangular house type features in the simplified image may be identified.
And S303, performing edge filtering processing on all the rectangular areas to obtain the house type areas corresponding to the rectangular areas one by one.
Understandably, the edge filtering processing is performed on the identified rectangular region to obtain the house type region, the house type region indicates a rectangular house type region in the copy image, the edge filtering processing is to extract the rectangular region from the simplified image and mark the corresponding position of the rectangular region in the simplified image, and the line of the edge of the extracted rectangular region is smoothed, namely, a short suspended line in an intersection is removed, and the short suspended line is a line of which the distance from the other end of the line to the intersection is smaller than a preset value and the other end of the line is not connected with other lines.
The invention realizes the rectangular house type characteristic of the simplified image through the house type area identification model; performing rectangular region identification on the simplified image according to the extracted rectangular house type features, and identifying a rectangular region in the simplified image; the method comprises the steps of carrying out edge filtering processing on all the rectangular areas to obtain the house type areas corresponding to the rectangular areas one by one, so that the rectangular areas in the simplified image are identified through extraction and identification of rectangular house type features, the house type areas are obtained through edge filtering processing, the house type areas with the rectangles are automatically and quickly identified, manual identification is not needed, a foundation is laid for follow-up wall body identification in the house type image more accurately, and accuracy and quality of wall body identification are improved.
S40, dredging each house type area to obtain a wall body area corresponding to each house type area;
understandably, the dredging process is to determine whether the house type area is a surrounding closed polygon, if the house type area is the surrounding closed polygon, the house type area is subjected to the closed dredging process to obtain a wall body area corresponding to the house type area, if the house type area is not the surrounding closed polygon, the house type area is subjected to the non-closed dredging process to obtain the wall body area corresponding to the house type area, so that the wall body areas corresponding to the house type areas one to one can be obtained through the dredging process, and the wall body area is the house type area subjected to the dredging process.
In an embodiment, in the step S40, that is, performing dredging processing on each house type area to obtain a wall area corresponding to each house type area, the method includes:
s401, detecting whether each house type area is a closed polygon.
Understandably, the enclosed polygon is that the house type area contains an enclosed inner edge and an enclosed outer edge, all the enclosed inner edges form an enclosed polygon, all the enclosed outer edges form an enclosed polygon, and the enclosed outer edges enclose the enclosed inner edges, that is, the polygon area formed by the enclosed inner edges is enclosed in the polygon area formed by the enclosed outer edges, and whether the house type area meets the requirement of enclosing the enclosed polygon is judged, the enclosed outer edges are the edges of the outermost polygon in the house type area, the enclosed inner edges are the edges of the house type area except the enclosed outer edges, and can form the polygon edges, because the user drawing the copy diagram often draws a rectangle similar to the enclosed rectangle to represent a house type or a room, and the drawn rectangle similar to the enclosed rectangle contains an inner wall and an outer wall, therefore, the enclosing closed polygon needs to be recognized, the condition that the closed polygon does not belong to a house type or a room is avoided, missing recognition is avoided, and the wall body can be accurately recognized.
S402, when the house type area is detected to be a closed polygon, the house type area is subjected to closed dredging treatment, and the wall body area corresponding to the house type area is obtained.
Understandably, if the house type area is detected to be a closed polygon, the house type area is subjected to closed dredging treatment, the closed dredging treatment is to judge the closed type of the house type area through an internal and external covering method, a dredging process of a corresponding cutting treatment mode is carried out according to different closed types, and the house type area subjected to the closed dredging treatment obtains a wall body area corresponding to the house type area.
In an embodiment, as shown in fig. 5, in the step S402, that is, performing a closing and dredging process on the house type area to obtain the wall area corresponding to the house type area, the method includes:
s4021, judging the closed outer edge and the closed inner edge of the house type area in the same direction by an inner and outer covering method, and identifying the closed type of the house type area.
Understandably, the inside-outside covering method is a method for judging the closed type of the house type area according to the length of the closed outside edge and the closed inside edge in the house type area and the length of the movement intersection, wherein the closed type comprises an outside covering inside type, an inside covering outside type and a non-covering type.
Wherein, it does to remove intersection length seal the outside to seal the interior limit remove to with seal interior limit coincidence back, with there is the length of intersection in the interior limit of sealing.
In an embodiment, the step S4021, namely, the determining the same direction of the closed outer edge and the closed inner edge of the house type area by the inside and outside covering method, and identifying the closed type of the house type area includes:
s40211, if the lengths of the closed outer edges in the house type area are all larger than the length of the closed inner edge parallel to the closed outer edges, determining the closed type of the house type area as an outer coverage inner type.
Understandably, if the lengths of the closed outer sides in the house type area are all larger than the lengths of the closed inner sides parallel to the closed outer sides, the polygons formed by all the closed outer sides can cover the polygons formed by all the closed inner sides, and the closed type of the house type area is determined as an outer-covering inner type.
S40212, if the length of any closed outer edge in the house type area is less than the length of the closed inner edge parallel to the closed outer edge, and the length of the moving intersection of the closed outer edge and the closed inner edge is equal to the length of the closed outer edge, determining the closed type of the house type area as an inner covering outer type; remove intersection length does seal the outside to seal the interior limit remove to with after the interior limit coincidence is sealed, with there is the length of intersection in the interior limit of sealing.
Understandably, if one closed outer edge exists in the house type area, the length of the closed outer edge is smaller than that of the closed inner edge parallel to the closed outer edge, and the length of the movement intersection of the closed outer edge and the closed inner edge is equal to that of the closed outer edge, the closed type of the house type area is determined as an inner covering outer type, wherein the length of the movement intersection is that the closed outer edge moves to the closed inner edge to coincide with the closed inner edge, and then the closed inner edge has the length of the intersection.
S40213, if the length of any of the closed outer edges in the house type area is less than the length of the closed inner edge parallel to the closed outer edge, and the length of the movement intersection of the closed outer edge and the closed inner edge is less than the length of the closed outer edge, determining the closed type of the house type area as a non-overlapping type.
Understandably, if the length of one closed outer edge in the house type area is smaller than that of the closed inner edge parallel to the closed outer edge, and the length of the moving intersection of the closed outer edge and the closed inner edge is smaller than that of the closed outer edge, the closed type of the house type area is determined to be a non-coverage type.
S4022, according to the closed type of the house type area, performing cutting identification on all closed outer edges and all closed inner edges in the house type area, and identifying the cut outer edges and the cut inner edges of the house type area.
Understandably, aiming at the closed type corresponding to the house type area, cutting and identifying all closed outer edges and all closed inner edges in the house type area, identifying the cut outer edges and the cut inner edges which need to be cut, and determining the identification process of the cut outer edges and the cut inner edges which need to be cut according to the conditions of the closed type and the similar spacing.
In an embodiment, the step S4022, that is, the identifying the cut outer edge and the cut inner edge of the subscriber area by performing the cut identification on all the closed outer edges and all the closed inner edges in the subscriber area according to the closed type of the subscriber area includes:
s40221, when the closed type of the house type region is an outer cover inner type, determining the closed outer edge and the closed inner edge corresponding to the smallest congeneric distance as the cut outer edge and the cut inner edge, respectively; the same-class distance is the distance between the closed outer edge and the closed inner edge which are adjacent and parallel in the same direction.
Understandably, the closed outside and the closed inside corresponding to the minimum closed interval in most house type drawings can not be used as a wall body due to thinness, and the closed inside and the closed outside need to be cut, therefore, if the closed type of the house type area is the type in the outer cover, the closed outside corresponding to the minimum closed interval is determined as the cut outside, and the closed inside corresponding to the minimum closed interval is determined as the cut inside, wherein, the closed interval is parallel to the closed outside and the distance between the closed inside.
S40222, when the closed type of the dwelling area is an inner-covering outer type, determining the closed outer edge and the closed inner edge corresponding to the same-type distance in which the length of the closed outer edge is less than that of the closed inner edge and is the smallest as the cutting outer edge and the cutting inner edge, respectively.
Understandably, most of the window areas in the house type drawings can present the sunken area of the outer wall, namely, a certain part of the outer wall can be lower than the outer wall of the adjacent area, the outer wall at the position is closer to the inner wall relative to the adjacent outer wall, the position can not be used as a wall body, because the window needs to be opened at the position, the window areas in the house type drawings can present the sunken area of the outer wall similar to the type of the inner covering, the closed outer edge corresponding to the similar interval that the length of the closed outer edge is smaller than that of the closed inner edge and is the minimum is determined as the cut outer edge, and the closed inner edge corresponding to the similar interval that the length of the closed outer edge is smaller than that of the closed inner edge and is the minimum is determined as the cut inner edge.
S40223, when the closed type of the dwelling area is a non-overlapping type, determining the closed outer edge having a length less than that of the closed inner edge as the cut outer edge, and determining the closed inner edge parallel to the cut outer edge as the cut inner edge.
Understandably, in most house type drawings, the placement area of the air conditioner outdoor unit is in a convex area close to the edge of the outer wall, namely the edge-close area of the outer wall is higher than the outer wall of an adjacent area, and the area cannot be used as a wall body, so that the area is similar to the area without covering each other, the closed outer edge with the length of the movement intersection of the closed inner edge being smaller than the length of the closed inner edge needs to be determined as the cutting outer edge, and the closed inner edge parallel to the cutting outer edge is determined as the cutting inner edge.
S4023, cutting and connecting the house type areas according to the cut outer edges and the cut inner edges of the house type areas to obtain the wall body areas corresponding to the house type areas.
Understandably, it is right the house type region perpendicular with the cutting outside with the parallel direction of cutting in the limit cuts, cuts out the cutting outside with there is the cutting region of intersection in the limit in the cutting, the cutting region contains the cutting outside with the region of cutting in the limit, then to after the cutting point of house type region carries out corresponding connection, after having cut the cutting region promptly, in the cutting the limit with the cutting point that can exist after being cut in the cutting outside carries out corresponding connection with adjacent cutting point, seals its cutting point, will cut and connect after the house type region is determined to correspond with this house type region the wall body is regional.
The invention realizes that the same direction judgment is carried out on the closed outer edge and the closed inner edge of the house type area through an inner and outer covering method, and the closed type of the house type area is identified; according to the closed type of the house type area, all closed outer edges and all closed inner edges in the house type area are cut and identified, and the cut outer edges and the cut inner edges of the house type area are identified; according to the cutting outer edge and the cutting inner edge of the house type area, the house type area is cut and connected, the wall body area corresponding to the house type area is obtained, therefore, the closed type is automatically identified through an inner and outer covering method, corresponding cutting and connection are carried out according to the closed type, the wall body area corresponding to the house type area surrounding the closed polygon is automatically generated, the manual identification and cutting processes are reduced, and the accuracy and the reliability of wall body identification are improved.
And S403, when the house type area is detected not to be the enclosed polygon, carrying out non-enclosed dredging treatment on the house type area to obtain the wall body area corresponding to the house type area.
Understandably, if it is detected that the house type area is not a closed polygon, performing non-closed dredging processing on the house type area, wherein the non-closed dredging processing is to cut a non-closed opening and cut an area, in the house type area, of which the distance between two adjacent sides is not smaller than a preset distance value, because the areas are not suitable for serving as a wall body, the house type area subjected to the non-closed dredging processing is determined to be the wall body area corresponding to the house type area.
The invention realizes that whether each house type area is a closed polygon is detected; when the house type area is detected to be a closed polygon, carrying out closed dredging treatment on the house type area to obtain the wall body area corresponding to the house type area; when the house type area is not detected to be the enclosed closed polygon, the house type area is subjected to non-enclosed dredging processing to obtain the wall body area corresponding to the house type area, so that whether the house type area is the enclosed closed polygon is judged, when the house type area is detected to be the enclosed closed polygon, the house type area is subjected to enclosed dredging processing, and when the house type area is detected not to be the enclosed closed polygon, the house type area is subjected to non-enclosed dredging processing to obtain the wall body area corresponding to each house type area, the wall body identification is more targeted, the accuracy of the wall body identification is improved, the processing of the house type area enclosing the enclosed polygon is avoided being omitted, and the quality of the wall body identification is improved.
And S50, combining all the wall areas to generate a wall of the house-type drawing corresponding to the copy drawing to be processed.
Understandably, the process of generating the combination is to splice the house type areas corresponding to the wall area at corresponding positions marked in the simplified image, that is, the wall area is placed in the simplified image at the corresponding position, and the placed wall area and lines in the simplified image are subjected to smooth transition connection processing, that is, suspended points between the wall area and the simplified image are connected to realize the operation of splicing, and the spliced simplified image is determined as the wall of the house type image corresponding to the copy image to be processed.
The invention realizes the purpose of obtaining the copy picture to be processed; carrying out image preprocessing on the to-be-processed copy picture to obtain a simplified image; performing wall polygon recognition on the simplified image through a house type area recognition model to recognize a plurality of house type areas; dredging each house type area to obtain a wall body area corresponding to each house type area; and combining all the wall body areas to generate a wall body of the house type graph corresponding to the copy picture to be processed, so that image preprocessing and polygon recognition of the copy picture to be processed are realized, the house type areas are automatically recognized, dredging processing is carried out on all the house type areas to obtain the wall body areas, and finally the wall body of the house type graph corresponding to the copy picture to be processed is generated in a combined mode.
In an embodiment, a wall recognition apparatus of a house type diagram is provided, and the wall recognition apparatus of the house type diagram corresponds to the wall recognition method of the house type diagram in the above embodiment one to one. As shown in fig. 6, the wall recognition apparatus of the house-type figure includes an acquisition module 11, a preprocessing module 12, a recognition module 13, a dredging module 14 and a generation module 15. The functional modules are explained in detail as follows:
an obtaining module 11, configured to obtain a copy diagram to be processed;
the preprocessing module 12 is configured to perform image preprocessing on the to-be-processed copy image to obtain a simplified image;
the identification module 13 is configured to perform wall polygon identification on the simplified image through a house type area identification model, and identify a plurality of house type areas;
the dredging module 14 is used for dredging each house type area to obtain a wall body area corresponding to each house type area;
and the generating module 15 is configured to combine all the wall regions to generate a wall of the house-type drawing corresponding to the copy drawing to be processed.
For the specific definition of the wall identification device of the house map, reference may be made to the above definition of the wall identification method of the house map, and details are not described here. All or part of each module in the wall identification device of the house type figure can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a wall identification method for a house layout.
In one embodiment, a computer device is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the wall identification method of the user graph in the above embodiments is implemented.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when being executed by a processor, implements the wall identification method of the floor plan of the above-described embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, databases, or other media used in embodiments provided herein may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A wall body identification method of a house type graph is characterized by comprising the following steps:
acquiring a copy picture to be processed;
carrying out image preprocessing on the to-be-processed copy picture to obtain a simplified image;
performing wall polygon recognition on the simplified image through a house type area recognition model to recognize a plurality of house type areas;
dredging each house type area to obtain a wall body area corresponding to each house type area;
and combining all the wall body areas to generate a wall body of the house type picture corresponding to the copy picture to be processed.
2. The wall recognition method of the house-type drawing according to claim 1, wherein the image preprocessing of the copy to be processed to obtain a simplified image comprises:
carrying out edge denoising processing on the to-be-processed copy image to obtain a denoised image;
performing line enhancement processing on the de-noised image to obtain an enhanced image;
performing linearization processing on the lines in the enhanced image by using a straight line generation algorithm to obtain a basic image;
and carrying out linear connection on the basic images to obtain the simplified image.
3. The wall recognition method of a house type map as claimed in claim 1, wherein the wall polygon recognition of the simplified image by the house type area recognition model to identify a plurality of house type areas comprises:
performing rectangular house type characteristics on the simplified image through the house type area identification model;
performing rectangular region identification on the simplified image according to the extracted rectangular house type features, and identifying a rectangular region in the simplified image;
and performing edge filtering processing on all the rectangular areas to obtain the house type areas corresponding to the rectangular areas one to one.
4. The wall identification method of a house type map as claimed in claim 1, wherein the dredging process for each house type area to obtain the wall area corresponding to each house type area comprises:
detecting whether each house type area is a surrounding closed polygon;
when the house type area is detected to be a closed polygon, carrying out closed dredging treatment on the house type area to obtain the wall body area corresponding to the house type area;
and when the house type area is detected not to be the enclosed polygon, carrying out non-enclosed dredging treatment on the house type area to obtain the wall body area corresponding to the house type area.
5. The wall identification method of a house type map as claimed in claim 4, wherein said performing a close-clearing process on the house type area to obtain the wall area corresponding to the house type area comprises:
judging the closed outer edge and the closed inner edge of the house type area in the same direction by an inner and outer covering method, and identifying the closed type of the house type area;
according to the closed type of the house type area, all closed outer edges and all closed inner edges in the house type area are cut and identified, and the cut outer edges and the cut inner edges of the house type area are identified;
and cutting and connecting the house type area according to the cutting outer edge and the cutting inner edge of the house type area to obtain the wall body area corresponding to the house type area.
6. The wall body recognition method of a house type map according to claim 5, wherein the recognizing the closed type of the house type area by performing the same direction judgment on the closed outer edge and the closed inner edge of the house type area through an inner and outer covering method comprises:
if the lengths of the closed outer edges in the house type area are all larger than the length of the closed inner edge parallel to the closed outer edges, determining the closed type of the house type area as an outer covering inner type;
if the length of any closed outer edge in the house type area is smaller than the length of the closed inner edge parallel to the closed outer edge, and the length of the moving intersection of the closed outer edge and the closed inner edge is equal to the length of the closed outer edge, determining the closed type of the house type area as an inner covering outer type; the length of the moving intersection is the length of the intersection between the moving outer edge and the closed inner edge after the moving outer edge moves towards the closed inner edge to be overlapped with the closed inner edge;
and if the length of any closed outer edge in the house type area is less than that of the closed inner edge parallel to the closed outer edge, and the length of the moving intersection of the closed outer edge and the closed inner edge is less than that of the closed outer edge, determining the closed type of the house type area as a non-coverage type.
7. The wall identification method of a house type map as claimed in claim 6, wherein said identifying all the closed outer edges and all the closed inner edges of the house type area according to the closed type of the house type area, and identifying the cut outer edges and the cut inner edges of the house type area comprises:
when the closed type of the house type area is an outer covering inner type, respectively determining the closed outer edge and the closed inner edge corresponding to the minimum same-class spacing as the cutting outer edge and the cutting inner edge; the same-class spacing is the distance between the closed outer edge and the closed inner edge which are adjacent and parallel in the same direction;
when the closed type of the house type area is an inner covering outer type, respectively determining the closed outer edge and the closed inner edge corresponding to the same-class interval in which the length of the closed outer edge is smaller than that of the closed inner edge and is the smallest as the cutting outer edge and the cutting inner edge;
and when the closed type of the house type area is a non-overlapping type, determining the closed outer edge with the length of the moving intersection of the closed inner edge smaller than the length of the closed inner edge as the cutting outer edge, and determining the closed inner edge parallel to the cutting outer edge as the cutting inner edge.
8. A wall body recognition device of house type picture is characterized by comprising:
the acquisition module is used for acquiring a copy picture to be processed;
the preprocessing module is used for preprocessing the image of the copy picture to be processed to obtain a simplified image;
the identification module is used for carrying out wall polygon identification on the simplified image through a house type area identification model to identify a plurality of house type areas;
the dredging module is used for dredging each house type area to obtain a wall body area corresponding to each house type area;
and the generating module is used for combining all the wall body areas to generate a wall body of the house-type drawing corresponding to the copy drawing to be processed.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the wall identification method of a house graph according to any of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out a wall identification method of a floor plan according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011577948.5A CN112633188B (en) | 2020-12-24 | 2020-12-24 | Wall identification method, device, equipment and medium for house type map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011577948.5A CN112633188B (en) | 2020-12-24 | 2020-12-24 | Wall identification method, device, equipment and medium for house type map |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112633188A true CN112633188A (en) | 2021-04-09 |
| CN112633188B CN112633188B (en) | 2024-03-15 |
Family
ID=75326092
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011577948.5A Active CN112633188B (en) | 2020-12-24 | 2020-12-24 | Wall identification method, device, equipment and medium for house type map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112633188B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114022895A (en) * | 2021-10-27 | 2022-02-08 | 上海品览数据科技有限公司 | Method for accurately identifying house type in building professional residential plan |
| CN114022895B (en) * | 2021-10-27 | 2024-05-10 | 上海品览数据科技有限公司 | Accurate identification method for house type in building professional residence plan |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007115238A (en) * | 2005-09-20 | 2007-05-10 | Fukui Computer Kk | Device, method, program for processing two-dimensional cad data and closed area identification method |
| CN107122528A (en) * | 2017-04-13 | 2017-09-01 | 广州乐家数字科技有限公司 | A kind of floor plan parametrization can edit modeling method again |
| CN107330979A (en) * | 2017-06-30 | 2017-11-07 | 电子科技大学中山学院 | Vector diagram generation method and device for building house type and terminal |
| CN109118022A (en) * | 2018-09-18 | 2019-01-01 | 东易日盛家居装饰集团股份有限公司 | A kind of layout method and device |
| CN109753918A (en) * | 2018-12-29 | 2019-05-14 | 江苏艾佳家居用品有限公司 | Wall recognition methods and system in a kind of floor plan |
| CN111340954A (en) * | 2020-02-18 | 2020-06-26 | 广东三维家信息科技有限公司 | House type wall drawing method and model training method and device thereof |
-
2020
- 2020-12-24 CN CN202011577948.5A patent/CN112633188B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007115238A (en) * | 2005-09-20 | 2007-05-10 | Fukui Computer Kk | Device, method, program for processing two-dimensional cad data and closed area identification method |
| CN107122528A (en) * | 2017-04-13 | 2017-09-01 | 广州乐家数字科技有限公司 | A kind of floor plan parametrization can edit modeling method again |
| CN107330979A (en) * | 2017-06-30 | 2017-11-07 | 电子科技大学中山学院 | Vector diagram generation method and device for building house type and terminal |
| CN109118022A (en) * | 2018-09-18 | 2019-01-01 | 东易日盛家居装饰集团股份有限公司 | A kind of layout method and device |
| CN109753918A (en) * | 2018-12-29 | 2019-05-14 | 江苏艾佳家居用品有限公司 | Wall recognition methods and system in a kind of floor plan |
| CN111340954A (en) * | 2020-02-18 | 2020-06-26 | 广东三维家信息科技有限公司 | House type wall drawing method and model training method and device thereof |
Non-Patent Citations (2)
| Title |
|---|
| KRISHNENDRA SHEKHAWAT等: ""Rectilinear Floor Plans"", 《COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE》, 18 June 2017 (2017-06-18) * |
| 江州: ""基于形状与边缘特征的户型图识别研究"", 《中国优秀硕士学位论文全文数据库》, 15 February 2018 (2018-02-15) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114022895A (en) * | 2021-10-27 | 2022-02-08 | 上海品览数据科技有限公司 | Method for accurately identifying house type in building professional residential plan |
| CN114022895B (en) * | 2021-10-27 | 2024-05-10 | 上海品览数据科技有限公司 | Accurate identification method for house type in building professional residence plan |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112633188B (en) | 2024-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111428581B (en) | Face shielding detection method and system | |
| CN110796082B (en) | Nameplate text detection method and device, computer equipment and storage medium | |
| US20220215557A1 (en) | Edge detection method and device, electronic equipment, and computer-readable storage medium | |
| CN111242126A (en) | Irregular text correction method and device, computer equipment and storage medium | |
| WO2023065792A1 (en) | Image processing method and apparatus, electronic device, and computer-readable storage medium | |
| WO2021169102A1 (en) | Text image processing method and apparatus, and computer device and storage medium | |
| CN112116540B (en) | Gear identification method and system for knob switch | |
| CN112348836A (en) | Method and device for automatically extracting building outline | |
| CN110414649B (en) | DM code positioning method, device, terminal and storage medium | |
| CN110751149A (en) | Target object labeling method and device, computer equipment and storage medium | |
| CN111915541B (en) | Image enhancement processing method, device, equipment and medium based on artificial intelligence | |
| CN111079730A (en) | Method for determining area of sample image in interface image and electronic equipment | |
| CN110942455A (en) | Method and device for detecting missing of cotter pin of power transmission line and computer equipment | |
| CN111260564A (en) | Image processing method and device and computer storage medium | |
| CN110110697B (en) | Multi-fingerprint segmentation extraction method, system, device and medium based on direction correction | |
| CN113963353A (en) | Character image processing and identifying method and device, computer equipment and storage medium | |
| US10451407B2 (en) | System and method of analyzing a curved surface | |
| KR101674802B1 (en) | Method and apparatus for real time detection of airborne fibers by image processing program | |
| CN112633188B (en) | Wall identification method, device, equipment and medium for house type map | |
| CN111598917B (en) | Data embedding method, device, equipment and computer readable storage medium | |
| CN113177941A (en) | Steel coil edge crack identification method, system, medium and terminal | |
| CN114255352A (en) | River channel extraction method and device and computer readable storage medium | |
| CN111768406A (en) | Cell image processing method, device, equipment and storage medium | |
| CN111783561A (en) | Picture examination result correction method, electronic equipment and related products | |
| CN116631003A (en) | Equipment identification method and device based on P & ID drawing, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |