CN106651803A - House type data identification method and device - Google Patents
House type data identification method and device Download PDFInfo
- Publication number
- CN106651803A CN106651803A CN201611226344.XA CN201611226344A CN106651803A CN 106651803 A CN106651803 A CN 106651803A CN 201611226344 A CN201611226344 A CN 201611226344A CN 106651803 A CN106651803 A CN 106651803A
- Authority
- CN
- China
- Prior art keywords
- wall body
- body area
- floor plan
- candidate
- target
- 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 33
- 238000001914 filtration Methods 0.000 claims description 18
- 210000000746 body region Anatomy 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 5
- 238000013139 quantization Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
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 house type data identification method and device; the method comprises the following steps: using a preset vector filter group to filter house type graphs; using an image processing algorithm to identify an object wall body area from candidate wall body areas; using a preset wall body vector filter to filter the object wall body area; outputting extracted result data. The house type data identification method and device can automatically identify wall bodies in the house type graphs.
Description
Technical field
The present embodiments relate to technical field of image processing, more particularly to a kind of recognition methods and the dress of house type data
Put.
Background technology
CAD house types file content identification demand is growing, and in household design tool, two big international popular technical grades are soft
Part Autodesk Revit and chief architect each provides the body of wall of CAD house type files, the identification of forms and door
Solution.But, the house type file analysis function of this two fatware can not accomplish the full-automatic identification that prosthetic is supervised, its
Disadvantage is that can carry out the identification of body of wall after manually body of wall is layered.
The content of the invention
For above-mentioned technical problem, recognition methods and the device of a kind of house type data are embodiments provided, with certainly
The dynamic identification for completing body of wall in floor plan.
On the one hand, a kind of recognition methods of house type data is embodiments provided, methods described includes:
Using default vector filter group, floor plan is filtered, to identify the floor plan in candidate
Wall body area;
Based on image processing algorithm, by identification target wall body area in candidate's wall body area;
Using default body of wall vector filter, the target wall body area is filtered, with by the target body of wall
Form region, door body region, and cylinder region are extracted in region;
By the result data output extracted.
On the other hand, the embodiment of the present invention additionally provides a kind of identifying device of house type data, and described device includes:
Group's filtering module, for using default vector filter group, filtering to floor plan, to identify
State the candidate's wall body area in floor plan;
Target area identification module, for based on image processing algorithm, by identification target wall in candidate's wall body area
Body region;
Filtering module, for using default body of wall vector filter, filtering to the target wall body area, with by
Form region, door body region, and cylinder region are extracted in the target wall body area;
Output module, for the result data output that will be extracted.
The recognition methods of house type data provided in an embodiment of the present invention and device, by using default vector filter group
Group, filters to floor plan, sharp by target wall body area is recognized in candidate's wall body area based on image processing algorithm
With default body of wall vector filter, the target wall body area is filtered, and the result data for extracting is exported, from
The dynamic identification for completing body of wall in floor plan.
Description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, other of the invention
Feature, objects and advantages will become more apparent upon:
Fig. 1 is the flow chart of the recognition methods of the house type data that first embodiment of the invention is provided;
Fig. 2 is the flow chart of the recognition methods of the house type data that second embodiment of the invention is provided;
Fig. 3 be third embodiment of the invention provide house type data recognition methods in target area identification operation flow process
Figure;
Fig. 4 be fourth embodiment of the invention provide house type data recognition methods in output function flow chart;
Fig. 5 is the structure chart of the identifying device of the house type data that fifth embodiment of the invention is provided.
Specific embodiment
With reference to the accompanying drawings and examples the present invention is described in further detail.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that, in order to just
Part related to the present invention rather than entire infrastructure are illustrate only in description, accompanying drawing.
First embodiment
Present embodiments provide a kind of technical scheme of the recognition methods of house type data.
Referring to Fig. 1, the recognition methods of house type data includes:
S11, using default vector filter group, filters to floor plan, to identify the floor plan in
Candidate's wall body area.
In the present embodiment, constructing in advance carries out the vector filter group of filter operation to floor plan.So-called vector
Group of filters, is collectively formed by one group of vector filter.Therefore, above-mentioned vector filter group be otherwise known as cluster formula vector filter
Ripple device.
Specific to each vector filter in vector filter group, it is made up of some vector filtering rules.Jing
The process of above-mentioned vector filter group is crossed, the figure of the vector filtering rule configured in vector filter group is met in floor plan
Shape region is identified, and is identified as candidate's wall body area.
It should be noted that the floor plan for being filtered should be polar plot.That is, in the present embodiment, original family
Graphic element in type figure is by vector representation.
S12, based on image processing algorithm, by identification target wall body area in candidate's wall body area.
It is understood that due to the process error of vector filter, tentatively recognizing that the candidate's wall body area for obtaining may
And it is inaccurate.Therefore, after candidate's wall body area is obtained, also floor plan should be carried out further using image processing algorithm
Process, so as to from candidate's wall body area identification obtain target wall body area.For candidate's wall body area, mesh
Mark wall body area is more accurate recognition result.
S13, using default body of wall vector filter, filters, with by the target to the target wall body area
Form region, door body region, and cylinder region are extracted in wall body area.
It is understood that in the target wall body area difficult to understand of identification, including:Form region, door body region, and
Cylinder region.In order to further be segmented to the target wall body area for recognizing, in addition it is also necessary to by entering one in target wall body area
What is walked distinguishes form region, door body region, and cylinder region.
Specific RM is identified using the body of wall vector filter for building in advance.So-called body of wall vector filtering
Device is a vector filter, includes some vector filtering rules.Such as, the body of wall area of some parallel segments is painted with inside body of wall
Domain is judged as form region;The thickness wall body area slightly thinner than other adjacent parts is judged as door body area in wall body area
Domain;Between different wall parts, area occupied is judged as cylinder region less than the wall body area of predetermined area threshold value.
S14, by the result data output extracted.
Preferably, the result data is exported in the form of structural data.
It should be noted that the technical scheme be given according to the present embodiment carries out the process of floor plan, can greatly improve
The recognition efficiency of floor plan.Preresearch estimates, according to the treatment effeciency of existing computing device, can be processed comprising 30,000 in 10 seconds
The CAD house type files of basis vector element.
The present embodiment utilizes default vector filter group, and floor plan is filtered, based on image processing algorithm, by
It is parted by death in candidate's wall body area target wall body area, using default body of wall vector filter, to the target body of wall area
Domain is filtered, and by the result data output extracted, automatically completes the identification of body of wall in floor plan.
Second embodiment
The present embodiment based on the above embodiment of the present invention, the further recognition methods there is provided house type data it is another
A kind of technical scheme.In the technical scheme, the recognition methods of house type data also includes:Using default vector filter group
Group, filters to floor plan, to identify the floor plan in candidate's wall body area before, to be input into floor plan carry out
Standardization.
Referring to Fig. 2, the recognition methods of house type data includes:
S21, the floor plan to being input into is standardized.
Because original floor plan may not be standard two-dimensional polar plot, and, be likely to occur on its picture be stained, line
Bar dimness etc. may affect the problem of the confidence level of final wall body area recognition result, need to carry out original floor plan
Process.Floor plan after standardization be picture understand, the polar plot of svelteness.
Specifically, for the standardization of the floor plan of input includes:With unit distance yardstick, in the floor plan
Lines be normalized;Lines to normalizing later carry out vector quantization.Specifically, unit distance yardstick can be 1 millimeter.
S22, using default vector filter group, filters to floor plan, to identify the floor plan in
Candidate's wall body area.
S23, based on image processing algorithm, by identification target wall body area in candidate's wall body area.
Specifically, can be according to image processing algorithm, from original, possible without recognizing in standardized floor plan
Wall body area, then the possible wall body area obtained using aforesaid way identification is obtained into candidate with by identification in vector floor plan
Wall body area is merged, and obtains target wall body area.It is understood that the target wall body area for finally giving be compared to
The more accurate wall body area data of candidate's wall body area.
S24, using default body of wall vector filter, filters, with by the target to the target wall body area
Form region, door body region, and cylinder region are extracted in wall body area.
S25, by the result data output extracted.
The present embodiment by using default vector filter group, before filtering to floor plan, to input
Floor plan is standardized so that before various identification operations are carried out to floor plan, the floor plan first to being input into is entered
Go standardization, eliminated the input noise of floor plan so that more credible to the recognition result of floor plan, improve knowledge
The robustness of other process.
3rd embodiment
The present embodiment further provides mesh in the recognition methods of house type data based on the above embodiment of the present invention
A kind of technical scheme of mark region recognition operation.In the technical scheme, based on image processing algorithm, by candidate's body of wall area
Recognize that target wall body area includes in domain:Rasterizing is carried out to the floor plan;Based on recognition rule, by the house type after rasterizing
Possible wall body area is recognized in figure;The possible wall body area is merged with candidate's wall body area, it is described to obtain
Target wall body area.
Referring to Fig. 3, based on image processing algorithm, included by identification target wall body area in candidate's wall body area:
S31, to the floor plan rasterizing is carried out.
Rasterizing is carried out to the floor plan, is exactly, using the grid cell with unit area, original floor plan to be entered
Row is divided, and obtains several grating images arranged in arrays.
It should be noted that the floor plan after rasterizing is no longer polar plot, but there is one to belong to bitmap
The bitmap images that grating image is collectively constituted.
S32, based on recognition rule, by recognizing possible wall body area in the floor plan after rasterizing.
Specifically, above-mentioned recognition rule can be the recognition rule based on default average gray threshold value.To a rasterizing
The concrete grid cell of later one whether the judgement of wall body area when, it is necessary first to carry out the identification of lines.When a grid
When the average gray value of unit is higher than default average gray threshold value, it is possible to judge that this grid cell is that lines are passed through
Grid cell.
By identifying after lines in the grating image after rasterizing, lines delimited, length, width parameter are predetermined
Parameter area in rectangular area, be identified as possible wall body area.
S33, the possible wall body area is merged with candidate's wall body area, to obtain the target body of wall area
Domain.
So-called fusion, can be by various convergence strategies.It is the most typical, can wall body area and candidate's wall
The region occurred in body region, as the target wall body area of final identification.This have the advantage that, can effectively disappear
In operating in standardization, the error introduced because vector recognizes operation improves the accuracy of identification of target wall body area.
In addition, above-mentioned fusion can also be between possible wall body area and candidate's wall body area, according to allocating in advance
Weight parameter merged.Such as, weight parameter p can be distributed for possible wall body area, is the distribution of candidate's wall body area
Weight parameter 1-p, and merge according to above-mentioned weight parameter.
No matter which kind of convergence strategy is adopted, and final purpose is to improve the confidence level of the final wall body area extracted,
Ensure the credible of the final wall body area for recognizing.
The present embodiment by carrying out rasterizing to the floor plan, based on recognition rule, by the floor plan after rasterizing
Possible wall body area is recognized, and the possible wall body area is merged with candidate's wall body area, so as to obtain
Target wall body area.
Fourth embodiment
The present embodiment is defeated in the further recognition methods there is provided house type data based on the above embodiment of the present invention
Go out a kind of technical scheme of operation.In the technical scheme, the result data output of extraction is included:With the shape of structural data
Formula, by the result data for extracting output;The structural data of output is shown to into user in the form of chart, word.
Referring to Fig. 4, the result data output of extraction is included:
S41, in the form of structural data, by the result data for extracting output.
So-called structural data, refers to that data itself have the institutional framework for determining, the data element tool included in data
There is the implication of determination.For example, one group of XML file label can be pre-defined, then in the form of an xml-file, output is extracted
Result data.
S42, user is shown in the form of chart, word by the structural data of output.
After being exported to result data in the form of structural data, can be with the structural data with output
Foundation, the result data of above-mentioned output is shown in the form of chart, word, so that user can more get information about
The recognition result of floor plan.
The present embodiment by the form of structural data, by the result data for extracting output, and with chart, word
Form the structural data of output is shown to into user, it is achieved thereby that the output of the recognition result to floor plan.
5th embodiment
Present embodiments provide a kind of technical scheme of the identifying device of house type data.In technical scheme, house type data
Identifying device include:Group's filtering module 52, target area identification module 53, filtering module 54, and output module 55.
Group's filtering module 52 is used to utilize default vector filter group, and floor plan is filtered, to know
The candidate's wall body area not gone out in the floor plan.
The target area identification module 53 is used to be based on image processing algorithm, by recognizing mesh in candidate's wall body area
Mark wall body area.
The filtering module 54 is used to utilize default body of wall vector filter, and the target wall body area was carried out
Filter, with by extraction form region, door body region, and cylinder region in the target wall body area.
The output module 55 is used for the result data output that will be extracted.
Further, the identifying device of house type data also includes:Standardized module 51.
The standardized module 51 is used for using default vector filter group, and floor plan is filtered, to know
Before the candidate's wall body area not gone out in the floor plan, the floor plan to being input into is standardized.
Further, the standardized module 51 includes:Normalization unit, and vectoring unit.
The normalization unit is used for unit distance yardstick, and the lines in the floor plan are normalized.
The vectoring unit is used to carry out vector quantization to normalizing later lines.
Further, the target area identification module 53 includes:Rasterizing unit, recognition unit, and integrated unit.
The rasterizing unit is used to carry out rasterizing to original floor plan.
The recognition unit is used to be based on recognition rule, by recognizing possible wall body area in the floor plan after rasterizing.
The integrated unit is used to merge the possible wall body area with candidate's wall body area, described to obtain
Target wall body area.
Further, the output module 55 includes:Output unit, and display unit.
The output unit is used in the form of structural data, by the result data for extracting output.
The display unit is used to that the structural data of output to be shown to into user in the form of chart, word.
Will be appreciated by those skilled in the art that above-mentioned each module of the invention or each step can be with general meters
Calculate device to realize, they can be concentrated on single computing device, or are distributed in the network that multiple computing devices are constituted
On, alternatively, they can be realized with the executable program code of computer installation, such that it is able to be stored in storage
Performed by computing device in device, or they are fabricated to respectively each integrated circuit modules, or will be many in them
Individual module or step are fabricated to single integrated circuit module to realize.So, the present invention be not restricted to any specific hardware and
The combination of software.
The preferred embodiments of the present invention are the foregoing is only, the present invention is not limited to, for those skilled in the art
For, the present invention can have various changes and change.All any modification, equivalents made within spirit and principles of the present invention
Replace, improve etc., should be included within the scope of the present invention.
Claims (10)
1. a kind of recognition methods of house type data, it is characterised in that include:
Using default vector filter group, floor plan is filtered, to identify the floor plan in candidate's body of wall
Region;
Based on image processing algorithm, by identification target wall body area in candidate's wall body area;
Using default body of wall vector filter, the target wall body area is filtered, with by the target wall body area
Middle extraction form region, door body region, and cylinder region;
By the result data output extracted.
2. method according to claim 1, it is characterised in that also include:
Using default vector filter group, floor plan is filtered, to identify the floor plan in candidate's wall
Before body region, the floor plan to being input into is standardized.
3. method according to claim 2, it is characterised in that the floor plan to being input into be standardized including:
With unit distance yardstick, the lines in the floor plan are normalized;
Lines to normalizing later carry out vector quantization.
4. method according to claim 2, it is characterised in that based on image processing algorithm, by candidate's wall body area
Middle identification target wall body area includes:
Rasterizing is carried out to the floor plan;
Based on recognition rule, by recognizing possible wall body area in the floor plan after rasterizing;
The possible wall body area is merged with candidate's wall body area, to obtain the target wall body area.
5. method according to claim 1, it is characterised in that include the result data output of extraction:
In the form of structural data, by the result data for extracting output;
The structural data of output is shown to into user in the form of chart, word.
6. a kind of identifying device of house type data, it is characterised in that include:
Group's filtering module, for using default vector filter group, filtering to floor plan, to identify the family
Candidate's wall body area in type figure;
Target area identification module, for based on image processing algorithm, by identification target body of wall area in candidate's wall body area
Domain;
Filtering module, for using default body of wall vector filter, filtering to the target wall body area, with by described
Form region, door body region, and cylinder region are extracted in target wall body area;
Output module, for the result data output that will be extracted.
7. device according to claim 6, it is characterised in that also include:
Standardized module, for using default vector filter group, filtering to floor plan, to identify the family
Before candidate's wall body area in type figure, the floor plan to being input into is standardized.
8. device according to claim 7, it is characterised in that the standardized module includes:
Normalization unit, for unit distance yardstick, being normalized to the lines in the floor plan;
Vectoring unit, for carrying out vector quantization to normalizing later lines.
9. device according to claim 7, it is characterised in that the target area identification module includes:
Rasterizing unit, for carrying out rasterizing to the floor plan;
Recognition unit, for based on recognition rule, by recognizing possible wall body area in the floor plan after rasterizing;
Integrated unit, for the possible wall body area to be merged with candidate's wall body area, to obtain the target wall
Body region.
10. device according to claim 6, it is characterised in that the output module includes:
Output unit, in the form of structural data, by the result data for extracting output;
Display unit, for the structural data of output to be shown to into user in the form of chart, word.
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 true CN106651803A (en) | 2017-05-10 |
CN106651803B 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) |
Cited By (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 |
CN109615679A (en) * | 2018-12-05 | 2019-04-12 | 江苏艾佳家居用品有限公司 | A kind of recognition methods 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 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009211198A (en) * | 2008-02-29 | 2009-09-17 | Sumitomo Forestry Co Ltd | Presentation display and presentation display program |
CN101981582A (en) * | 2008-04-04 | 2011-02-23 | 富士胶片株式会社 | Method, apparatus, and program for detecting object |
CN105975675A (en) * | 2016-05-04 | 2016-09-28 | 杭州群核信息技术有限公司 | Method for generating housing type by editing imported local file on line |
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
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009211198A (en) * | 2008-02-29 | 2009-09-17 | Sumitomo Forestry Co Ltd | Presentation display and presentation display program |
CN101981582A (en) * | 2008-04-04 | 2011-02-23 | 富士胶片株式会社 | Method, apparatus, and program for detecting object |
CN105975675A (en) * | 2016-05-04 | 2016-09-28 | 杭州群核信息技术有限公司 | Method for generating housing type by editing imported local file on line |
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 |
Cited By (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 |
CN109615679A (en) * | 2018-12-05 | 2019-04-12 | 江苏艾佳家居用品有限公司 | A kind of recognition methods 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 |
Also Published As
Publication number | Publication date |
---|---|
CN106651803B (en) | 2020-04-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111008597B (en) | Space identification method and device for CAD drawing, electronic equipment and storage medium | |
US11455805B2 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
EP3321887A1 (en) | Urban road recognition method, apparatus, storage medium and device based on laser point cloud | |
US9142011B2 (en) | Shadow detection method and device | |
CN105975913B (en) | Road network extraction method based on adaptive cluster learning | |
CN102855459B (en) | For the method and system of the detection validation of particular prospect object | |
CN105005760A (en) | Pedestrian re-identification method based on finite mixture model | |
CN110910445B (en) | Object size detection method, device, detection equipment and storage medium | |
CN105469380A (en) | Method and device for detecting shielding against object | |
CN106651803A (en) | House type data identification method and device | |
CN113537070B (en) | Detection method, detection device, electronic equipment and storage medium | |
CN111295666A (en) | Lane line detection method, device, control equipment and storage medium | |
WO2021248269A1 (en) | High-precision identification method and system for transformer device | |
CN113936210A (en) | Anti-collision method for tower crane | |
CN116363319B (en) | Modeling method, modeling device, equipment and medium for building roof | |
Shen et al. | An automatic framework for pylon detection by a hierarchical coarse-to-fine segmentation of powerline corridors from UAV LiDAR point clouds | |
Ha et al. | Improved Optical Flow Estimation In Wrong Way Vehicle Detection. | |
CN114037912A (en) | Method and device for detecting change of remote sensing image and computer readable storage medium | |
CN112270357A (en) | VIO vision system and method | |
CN111612890A (en) | Method and device for automatically generating three-dimensional model from two-dimensional house type diagram and electronic equipment | |
CN111985497B (en) | Crane operation identification method and system under overhead transmission line | |
Chalup et al. | A method for cityscape analysis by determining the fractal dimension of its skyline | |
CN104282016B (en) | Embedded image data processing method | |
CN113139975B (en) | Road feature-based pavement segmentation method and device | |
CN115802013B (en) | Video monitoring method, device and equipment based on intelligent illumination and storage medium |
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 |