CN106651803B - Method and device for identifying house type data - Google Patents
Method and device for identifying house type data Download PDFInfo
- Publication number
- CN106651803B CN106651803B CN201611226344.XA CN201611226344A CN106651803B CN 106651803 B CN106651803 B CN 106651803B CN 201611226344 A CN201611226344 A CN 201611226344A CN 106651803 B CN106651803 B CN 106651803B
- Authority
- CN
- China
- Prior art keywords
- house type
- wall body
- body area
- area
- identifying
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 239000013598 vector Substances 0.000 claims abstract description 49
- 238000001914 filtration Methods 0.000 claims abstract description 31
- 238000010606 normalization Methods 0.000 claims description 12
- 230000004927 fusion Effects 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
Abstract
The embodiment of the invention discloses a method and a device for identifying house type data. The method comprises the following steps: filtering the house type graph by using a preset vector filter group; identifying a target wall body area based on an image processing algorithm; filtering the target wall body area by using a preset wall body vector filter; and outputting the extracted result data. The method and the device for identifying the house type data provided by the embodiment of the invention can automatically complete the identification of the wall in the house type graph.
Description
Technical Field
The embodiment of the invention relates to the technical field of image processing, in particular to a method and a device for identifying house type data.
Background
The content identification requirement of the CAD house type files is increasing day by day, and in a house design tool, two international popular industrial-grade software Autodesk Revit and chief architec respectively provide identification solutions for walls, windows and doors of the CAD house type files. However, the house type file analysis functions of the two software cannot achieve full-automatic identification without manual supervision, and the disadvantage is that the wall body can be identified after the wall body is layered manually.
Disclosure of Invention
In view of the above technical problems, embodiments of the present invention provide a method and an apparatus for identifying house type data, so as to automatically complete identification of a wall in a house type graph.
In one aspect, an embodiment of the present invention provides a method for identifying house type data, where the method includes:
filtering the house type graph by using a preset vector filter group to identify a candidate wall body area in the house type graph;
identifying a target wall body area based on an image processing algorithm;
filtering the target wall body area by using a preset wall body vector filter so as to extract a window body area, a door body area and a column body area from the target wall body area;
and outputting the extracted result data.
On the other hand, an embodiment of the present invention further provides an apparatus for identifying house type data, where the apparatus includes:
the group filtering module is used for filtering the house type graph by utilizing a preset vector filter group so as to identify a candidate wall body area in the house type graph;
the target area identification module is used for identifying a target wall area based on an image processing algorithm;
the filtering module is used for filtering the target wall body area by using a preset wall body vector filter so as to extract a window body area, a door body area and a column body area from the target wall body area;
and the output module is used for outputting the extracted result data.
According to the method and device for identifying the house type data, provided by the embodiment of the invention, the house type graph is filtered by using the preset vector filter group, the target wall body area is identified based on the image processing algorithm, the target wall body area is filtered by using the preset wall body vector filter, and the extracted result data is output, so that the identification of the wall body in the house type graph is automatically completed.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments made with reference to the following drawings:
fig. 1 is a flowchart of a method for identifying house type data according to a first embodiment of the present invention;
fig. 2 is a flowchart of a method for identifying house type data according to a second embodiment of the present invention;
fig. 3 is a flowchart of a target area recognition operation in the method for recognizing house type data according to the third embodiment of the present invention;
fig. 4 is a flowchart of an output operation in the identification method of the house type data according to the fourth embodiment of the present invention;
fig. 5 is a block diagram of a device for recognizing house type data according to a fifth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
First embodiment
The embodiment provides a technical scheme of a method for identifying house type data.
Referring to fig. 1, the identification method of the house type data includes:
s11, filtering the house type graph by using a preset vector filter group to identify candidate wall body areas in the house type graph.
In this embodiment, a vector filter group for performing a filtering operation on the house pattern is constructed in advance. The vector filter group is composed of a group of vector filters. Therefore, the above vector filter group is also called a clustered vector filter.
Specific to each vector filter in the vector filter group, it consists of several vector filtering rules. After the vector filter group processing, the graph area in the user-type graph, which meets the vector filtering rule configured in the vector filter group, is identified and is identified as a candidate wall area.
It should be noted that the filtered house pattern should be a vector pattern. That is, in the present embodiment, the graphic elements in the original floor plan are represented by vectors.
And S12, identifying the target wall area based on the image processing algorithm.
It is understood that the preliminary identified candidate wall regions may not be accurate due to processing errors of the vector filter. Therefore, after the candidate wall regions are obtained, the house pattern should be further processed by using an image processing algorithm, so as to be able to identify and obtain the target wall region from the candidate wall regions. The target wall region is a more accurate identification result relative to the candidate wall region.
And S13, filtering the target wall area by using a preset wall vector filter to extract a window area, a door area and a column area from the target wall area.
It can be understood that, in the identified target wall area, there are included: a window region, a door region, and a column region. In order to further subdivide the identified target wall body area, a window body area, a door body area and a column body area need to be further distinguished from the target wall body area.
The specific identification mode is to use a pre-constructed wall vector filter for identification. The wall vector filter is a vector filter and contains a plurality of vector filtering rules. For example, a wall area with a plurality of parallel line segments drawn inside the wall is determined as a window area; the wall body area with the thickness slightly thinner than other adjacent parts in the wall body area is judged as a door body area; wall regions between different wall portions having an area of occupancy less than a predetermined area threshold are determined to be column regions.
And S14, outputting the extracted result data.
Preferably, the result data is output in the form of structured data.
It should be noted that, by performing the processing on the house type graph according to the technical solution provided in this embodiment, the efficiency of identifying the house type graph can be greatly improved. Preliminary estimates, in terms of the processing efficiency of existing computing devices, can process CAD layout files containing 3 ten thousand base vector elements in 10 seconds.
In this embodiment, a preset vector filter group is used to filter the house type graph, a target wall area is identified based on an image processing algorithm, a preset wall vector filter is used to filter the target wall area, and extracted result data is output, so that the identification of the wall in the house type graph is automatically completed.
Second embodiment
The present embodiment further provides another technical solution of the method for identifying house type data based on the above embodiments of the present invention. In this technical solution, the method for identifying house type data further includes: before filtering the house type graph by using a preset vector filter group to identify a candidate wall body area in the house type graph, carrying out standardization processing on the input house type graph.
Referring to fig. 2, the identification method of the house type data includes:
and S21, standardizing the input house type graph.
Because the original house type diagram may not be a standard two-dimensional vector diagram, and the problem that defiling, dark lines and the like may occur on the screen and may affect the reliability of the final wall body area identification result, the original house type diagram needs to be processed. The house type graph after the standardization processing is a vector graph with clear picture and clear lines.
Specifically, the normalization process for the input house type graph includes: normalizing the lines in the floor plan according to a unit distance scale; and vectorizing the line after normalization. In particular, the unit distance scale may be 1 millimeter.
S22, filtering the house type graph by using a preset vector filter group to identify candidate wall body areas in the house type graph.
And S23, identifying the target wall area based on the image processing algorithm.
Specifically, possible wall regions can be identified from an original floor plan which is not standardized according to an image processing algorithm, and then the possible wall regions identified by the method are fused with candidate wall regions identified from a vector floor plan to obtain a target wall region. It will be appreciated that the resulting target wall region is more accurate wall region data than the candidate wall regions.
And S24, filtering the target wall area by using a preset wall vector filter to extract a window area, a door area and a column area from the target wall area.
And S25, outputting the extracted result data.
In the embodiment, before the preset vector filter group is used for filtering the house type graph, the input house type graph is standardized, so that before various identification operations are performed on the house type graph, the input house type graph is firstly standardized, input noise of the house type graph is removed, the identification result of the house type graph is more credible, and the robustness of the identification process is improved.
Third embodiment
The present embodiment is based on the above embodiments of the present invention, and further provides a technical solution of the target area identification operation in the identification method of the house type data. In the technical scheme, based on the image processing algorithm, the step of identifying the target wall body area comprises the following steps: rasterizing the house type graph; based on the identification rule, identifying possible wall body areas in the rasterized floor plan; and fusing the possible wall body area and the candidate wall body area to obtain the target wall body area.
Referring to fig. 3, identifying the target wall region based on the image processing algorithm includes:
and S31, rasterizing the floor plan.
And rasterizing the house pattern, namely dividing the original house pattern by using a grid unit with a unit area to obtain a plurality of grid images arranged in a matrix.
It should be noted that the rasterized house pattern is not a vector diagram, but a bitmap image composed of raster images belonging to the bitmap.
And S32, based on the identification rule, identifying possible wall body areas in the rasterized floor plan.
Specifically, the identification rule may be an identification rule based on a preset average gray threshold. When judging whether a specific grid cell after rasterization is a wall body area, firstly, the identification of lines is needed. When the average gray value of one grid cell is higher than a preset average gray threshold value, the grid cell is judged to be the grid cell through which lines pass.
After the lines are identified from the rasterized raster image, the rectangular area defined by the lines and having length and width parameters within the preset parameter range is identified as a possible wall area.
And S33, fusing the possible wall body area and the candidate wall body area to obtain the target wall body area.
The fusion may be achieved by a variety of fusion strategies. Most typically, the areas that are present in both the possible wall area and the candidate wall area may be used as the final identified target wall area. The method has the advantages that errors caused by vector identification operation in the standardization processing operation can be effectively eliminated, and the identification precision of the target wall body area is improved.
In addition, the fusion can be performed between the possible wall body area and the candidate wall body area according to a pre-assigned weight parameter. For example, a weight parameter p may be assigned to a possible wall region, and weight parameters 1-p may be assigned to candidate wall regions, and fused according to the weight parameters.
No matter what fusion strategy is adopted, the final purpose is to improve the credibility of the finally extracted wall body area and ensure the credibility of the finally identified wall body area.
In this embodiment, the target wall area is obtained by rasterizing the house type map, identifying a possible wall area from the rasterized house type map based on an identification rule, and fusing the possible wall area and the candidate wall area.
Fourth embodiment
The present embodiment further provides a technical solution of an output operation in the method for identifying house type data based on the above embodiments of the present invention. In the technical scheme, outputting the extracted result data comprises: outputting the extracted result data in a structured data form; and displaying the output structured data to a user in the form of graphs and characters.
Referring to fig. 4, outputting the extracted result data includes:
s41, outputting the extracted result data in the form of structured data.
Structured data means that the data itself has a definite organization structure, and data elements included in the data have definite meanings. For example, a set of XML file tags may be predefined and then the extracted result data may be output in the form of an XML file.
And S42, displaying the output structured data to the user in the form of graphs and characters.
After the result data is output in the form of the structured data, the output result data can be displayed in the form of graphs and characters according to the output structured data, so that a user can more intuitively know the recognition result of the user-type graph.
The embodiment outputs the extracted result data in the form of the structured data, and displays the output structured data to the user in the form of the chart and the characters, thereby realizing the output of the identification result of the house type chart.
Fifth embodiment
The embodiment provides a technical scheme of a device for identifying house type data. In the technical scheme, the device for identifying the house type data comprises: a group filtering module 52, a target area identifying module 53, a filtering module 54, and an output module 55.
The group filtering module 52 is configured to filter the house type map by using a preset vector filter group, so as to identify a candidate wall area in the house type map.
The target area identification module 53 is configured to identify a target wall area based on an image processing algorithm.
The filtering module 54 is configured to filter the target wall area by using a preset wall vector filter, so as to extract a window area, a door area, and a column area from the target wall area.
The output module 55 is configured to output the extracted result data.
Further, the device for identifying house type data further comprises: a normalization module 51.
The normalization module 51 is configured to normalize the input house type map before filtering the house type map by using a preset vector filter group to identify candidate wall regions in the house type map.
Further, the normalization module 51 includes: a normalization unit, and a vectorization unit.
The normalization unit is used for normalizing the lines in the floor plan according to the unit distance scale.
And the vectorization unit is used for vectorizing the normalized lines.
Further, the target area identifying module 53 includes: the device comprises a rasterizing unit, a recognition unit and a fusion unit.
The rasterizing unit is used for rasterizing the original house type graph.
The identification unit is used for identifying possible wall body areas from the rasterized floor plan based on identification rules.
The fusion unit is used for fusing the possible wall body area and the candidate wall body area to obtain the target wall body area.
Further, the output module 55 includes: an output unit, and a display unit.
The output unit is used for outputting the extracted result data in a structured data form.
The display unit is used for displaying the output structured data to a user in the form of graphs and characters.
It will be understood by those skilled in the art that the modules or steps of the invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of computing devices, and optionally they may be implemented by program code executable by a computing device, such that it may be stored in a memory device and executed by a computing device, or it may be separately fabricated into various integrated circuit modules, or it may be fabricated by fabricating a plurality of modules or steps thereof into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A method for identifying house type data is characterized by comprising the following steps:
filtering the house type graph by using a preset vector filter group to identify a candidate wall body area in the house type graph;
identifying a target wall body area based on an image processing algorithm;
filtering the target wall body area by using a preset wall body vector filter so as to extract a window body area, a door body area and a column body area from the target wall body area;
outputting the extracted result data;
based on the image processing algorithm, identifying the target wall area comprises:
rasterizing the house type graph;
based on the identification rule, identifying possible wall body areas in the rasterized floor plan; fusing the possible wall body area with the candidate wall body area to obtain the target wall body area;
the identification rule is based on an average gray threshold, and the identification of possible wall areas from the rasterized floor plan comprises the following steps:
for each grid unit in the rasterized floor plan, if the average gray value of the grid unit is higher than a preset average gray threshold value, determining that the grid unit is a grid unit through which lines pass;
and identifying lines from the grid cells through which the lines pass, and identifying a rectangular area with parameters defined by the lines within a preset parameter range as a possible wall body area.
2. The method of claim 1, further comprising:
before filtering the house type graph by using a preset vector filter group to identify a candidate wall body area in the house type graph, carrying out standardization processing on the input house type graph.
3. The method of claim 2, wherein normalizing the input house type graph comprises:
normalizing the lines in the floor plan according to a unit distance scale;
and vectorizing the line after normalization.
4. The method of claim 1, wherein outputting the extracted result data comprises:
outputting the extracted result data in a structured data form;
and displaying the output structured data to a user in the form of graphs and characters.
5. An apparatus for recognizing house type data, comprising:
the group filtering module is used for filtering the house type graph by utilizing a preset vector filter group so as to identify a candidate wall body area in the house type graph;
the target area identification module is used for identifying a target wall area based on an image processing algorithm;
the filtering module is used for filtering the target wall body area by using a preset wall body vector filter so as to extract a window body area, a door body area and a column body area from the target wall body area;
the output module is used for outputting the extracted result data;
the target area identification module includes:
the rasterizing unit is used for rasterizing the house type graph;
the identification unit is used for identifying possible wall body areas from the rasterized floor plan based on identification rules;
a fusion unit, configured to fuse the possible wall region with the candidate wall region to obtain the target wall region;
wherein the identification rule is an identification rule based on an average gray threshold, and the identification unit is specifically configured to:
for each grid unit in the rasterized floor plan, if the average gray value of the grid unit is higher than a preset average gray threshold value, determining that the grid unit is a grid unit through which lines pass;
and identifying lines from the grid cells through which the lines pass, and identifying a rectangular area with parameters defined by the lines within a preset parameter range as a possible wall body area.
6. The apparatus of claim 5, further comprising:
and the normalization module is used for performing normalization processing on the input house type graph before filtering the house type graph by using a preset vector filter group so as to identify a candidate wall body area in the house type graph.
7. The apparatus of claim 6, wherein the normalization module comprises:
the normalization unit is used for normalizing the lines in the floor-type graph according to a unit distance scale;
and the vectorization unit is used for vectorizing the normalized lines.
8. The apparatus of claim 5, wherein the output module comprises:
the output unit is used for outputting the extracted result data in a structured data form;
and the display unit is used for displaying the output structured data to a user in the form of graphs and characters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611226344.XA CN106651803B (en) | 2016-12-27 | 2016-12-27 | Method and device for identifying house type data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611226344.XA CN106651803B (en) | 2016-12-27 | 2016-12-27 | Method and device for identifying house type data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106651803A CN106651803A (en) | 2017-05-10 |
| CN106651803B true CN106651803B (en) | 2020-04-24 |
Family
ID=58832704
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611226344.XA Active CN106651803B (en) | 2016-12-27 | 2016-12-27 | Method and device for identifying house type data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106651803B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108388577A (en) * | 2018-01-17 | 2018-08-10 | 链家网（北京）科技有限公司 | A kind of method and system automatically generating house floor plan syntax tree |
| CN109615679B (en) * | 2018-12-05 | 2022-07-08 | 江苏艾佳家居用品有限公司 | Identification method of house type component |
| CN110909602A (en) * | 2019-10-21 | 2020-03-24 | 广联达科技股份有限公司 | Two-dimensional vector diagram sub-domain identification method and device |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5047006B2 (en) * | 2008-02-29 | 2012-10-10 | 住友林業株式会社 | Presentation display device and presentation display program |
| JP5227639B2 (en) * | 2008-04-04 | 2013-07-03 | 富士フイルム株式会社 | Object detection method, object detection apparatus, and object detection program |
| CN105975675B (en) * | 2016-05-04 | 2019-11-22 | 杭州群核信息技术有限公司 | A method of it importing local file online editing and generates house type |
| CN106156438A (en) * | 2016-07-12 | 2016-11-23 | 杭州群核信息技术有限公司 | Body of wall recognition methods and device |
-
2016
- 2016-12-27 CN CN201611226344.XA patent/CN106651803B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106651803A (en) | 2017-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10762376B2 (en) | Method and apparatus for detecting text | |
| CN110660066B (en) | Training method of network, image processing method, network, terminal equipment and medium | |
| CN108446698B (en) | Method, device, medium and electronic equipment for detecting text in image | |
| CN109325954B (en) | Image segmentation method and device and electronic equipment | |
| US11455805B2 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
| US20160259995A1 (en) | Image recognition method, image recognition device, and recording medium | |
| CN112016438A (en) | Method and system for identifying certificate based on graph neural network | |
| CN112949710A (en) | Image clustering method and device | |
| CN110910445B (en) | Object size detection method, device, detection equipment and storage medium | |
| CN106651803B (en) | Method and device for identifying house type data | |
| CN112200081A (en) | Abnormal behavior identification method and device, electronic equipment and storage medium | |
| CN105302413A (en) | UI test method and system for control | |
| CN113592886A (en) | Method and device for examining architectural drawings, electronic equipment and medium | |
| CN110555339A (en) | target detection method, system, device and storage medium | |
| CN108830184A (en) | Black eye recognition methods and device | |
| CN108021863B (en) | Electronic device, age classification method based on image and storage medium | |
| US20220343642A1 (en) | High-precision identification method and system for substations | |
| CN113537070A (en) | Detection method, detection device, electronic equipment and storage medium | |
| CN114429637A (en) | Document classification method, device, equipment and storage medium | |
| US10679098B2 (en) | Method and system for visual change detection using multi-scale analysis | |
| CN116363319B (en) | Modeling method, modeling device, equipment and medium for building roof | |
| CN112396060A (en) | Identity card identification method based on identity card segmentation model and related equipment thereof | |
| CN116310568A (en) | Image anomaly identification method, device, computer readable storage medium and equipment | |
| EP3076370B1 (en) | Method and system for selecting optimum values for parameter set for disparity calculation | |
| CN117011532A (en) | Image processing method, apparatus, device, storage medium, and program product |
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 |