CN104821011A - Method of generating 3D house type model by 2D house type model based on camera shooting - Google Patents
Method of generating 3D house type model by 2D house type model based on camera shooting Download PDFInfo
- Publication number
- CN104821011A CN104821011A CN201510259082.6A CN201510259082A CN104821011A CN 104821011 A CN104821011 A CN 104821011A CN 201510259082 A CN201510259082 A CN 201510259082A CN 104821011 A CN104821011 A CN 104821011A
- Authority
- CN
- China
- Prior art keywords
- house type
- camera shooting
- model
- door
- image
- 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.)
- Pending
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method of generating a 3D house type model by a 2D house type model based on camera shooting. The method comprises steps: 1, a 2D house type picture is acquired through camera shooting; 2, an essential matrix reduction method is used for correcting the 2D house type picture acquired in the first step; 3, image enhancement processing is carried out on the2D house type picture after processing of the second step; 4, a contour line of the 2D image after processing of the third step is extracted; 5, a door and window model base is built, matching is carried out according to the contour line extracted in the fourth step, and door and window positions are recognized; 6, a wall structure is stretched to a fixed height position, and generation of a 3D house type model is completed. The method has the following advantages that automatic generation of the 3D house type model from the 2D house type model is realized, the generation method is simple, applicability is universal, the generation method can be embedded in a portable mobile device to form APP application software to be combined with a camera of the portable mobile device, and practicability is provided.
Description
Technical field
The present invention relates to a kind of method generating 3D house type model based on 2D house type photo, particularly relate to a kind of method that 2D house type photo obtained based on camera shooting generates 3D house type model.
Background technology
Based on the three-dimensional reconstruction of two-dimentional house type figure according to the difference of input format, be mainly divided into two large classes: based on sweeping the three-dimensional reconstruction of image and the three-dimensional reconstruction based on vector house type drawing.Method based on the three-dimensional reconstruction sweeping image mainly comprises: 1) pre-treatment scan image, comprises denoising, Text Feature Extraction and vector quantization; 2) drawing after vector quantization is analyzed and identifying signature (wall, door, window, balcony etc.); 3) three-dimensional reconstruction
How to analyze the floor plan after vector quantization, correctly resolving and extracting building element geometry and semantic information and its layout information represented is rebuild the vital step of scintigram.Current most of technique study all concentrates on this part.More representational have: 1, the work of Siu-hang etc., lay particular emphasis on the geometric representation extracting each several part Constracture unit from vector floor plan, thus Reconstruction of three-dimensional model, propose a kind of method of matching based on parallel opposite vector in literary composition and detect body of wall, in the polar plot that they think after the pre-treatment, the body of wall of bandwidth is made up of paired opposite vector.2, the people such as Sheraz to propose a kind of method wide to distinguish in floor plan, medium, narrow straight line, and effectively remove the interference polygon outside wall, thus improve the accuracy rate to room identification.3, Lluis-Pere etc. propose a kind of method of automatic division body of wall for the identification of wall in scanning floor plan, and the method described in literary composition represents have good robustness and do not need pre-enter or train identification sets to any Wall Symbol.The method is acquiescence body of wall is a kind of element repeated in floor plan, and naturally balanced being distributed in whole floor plan, and normally represent with the form of parallel lines.Can find out, the method is also based on a large amount of supposed premise.4, the team of Lluis-Pere within nearly 2 years, propose again some Corpus--based Method divide and in advance learning sample file the method obtaining character representation glossary of symbols to improve the universality of feature identification.
3D synthetic method described in the prior art has following defect above: 1, too strict to the quality requirements of the original input picture of floor plan; 2, bad to the universality of characteristic information identification, in Existing methods, often kind of method is basic only for the floor plan in a certain house type storehouse, and the characteristic information symbol table in different house type storehouse shows and differs greatly, and does not also have ripe method generally can be applicable to the floor plan of various different sink at present.The method adopting the method for Corpus--based Method analysis to form special semantic base via sample in advance can improve this problem to a certain extent, but sample learning in advance still adds algorithm complexity, increases consuming time, and effect is not very good; 3) for complicated floor plan, except the building original paper of necessity, body of wall, door, window, balcony, if also with other furniture in floor plan, bathroom, the diagrams such as decoration, then can increase identification difficulty.
Summary of the invention
The invention provides a kind of method that 2D house type photo based on camera shooting generates 3D house type model, which overcome the deficiencies in the prior art described in background technology.
The technical solution adopted for the present invention to solve the technical problems is:
2D house type photo based on camera shooting generates the method for 3D house type model, and it comprises:
Step 1, obtains 2D house type photo by camera shooting;
Step 2, is revised the 2D house type photo that step 1 obtains by essential matrix reducing process, to obtain a 2D floor plan picture rational in infrastructure;
Step 3, carries out image enhancement processing to the 2D floor plan picture after processing through step 2;
Step 4, extract the outline line of the 2D image after step 3 processes, obtain two outline lines be parallel to each other of body of wall, the starting point of every wall body outline line and terminating point and door, curtain runner profile, by the starting point wall body structure that be connected to form house corresponding to terminating point of every adjacent two wall body outline lines;
Step 5, sets up door, window model bank, and the door extracted according to step 4, the wide wired-AND gate of curtain runner, window model bank are mated, so recognitiion gate, the position of window in building structure;
Step 6, the height and position that stretching wall body structure to is fixing.
Among one embodiment: described step 5 also comprises calibrates the door identified, the position of window in building structure.
Among one embodiment: being obtained by the camera on portable mobile apparatus by the 2D floor plan of camera shooting acquisition described in step 1.
Among one embodiment: image enhancement processing described in step 3 comprises the part or all of disposal route in histogram equalization process, colour correction process, threshold value sampling process, Image erosion process, the Swelling and contraction process of image and denoising.
Among one embodiment: the image enhancement processing described in step 3 is successively through Swelling and contraction process and the denoising of histogram equalization process, colour correction process, threshold value sampling process, Image erosion process, image.
Among one embodiment: the outline line described in step 4 extracts and adopts Canny contours extract method.
Among one embodiment: the door in the wide wired-AND gate of the door described in step 5, curtain runner, window model bank, window model are mated by invariant moment features and/or surf unique point.
Among one embodiment: the starting point of the line of wall contour described in step 4 and terminating point are the extending line intersection point of the stifled neighboring walls of two after contours extract.
Among one embodiment: described portable mobile apparatus comprises any one in mobile phone, hand held camera, flat board.
The technical program is compared with background technology, and its tool has the following advantages:
1, achieve by the automatic generation of 2D house type photo to 3D house type model, generation method is simple, there is general applicability, the 3D house type model generated accurately can reflect the script structural information in house, comprises the positional information etc. of the structural information (comprising the thickness information of body of wall) of body of wall, each room unit formed, number information and door and window.
2,2D house type photo of the present invention is mainly obtained by instantly popular and conventional portable mobile apparatus camera, obtain manner is very convenient, also this generation method can be embedded the camera use in conjunction forming a APP application software and portable mobile apparatus in portable mobile apparatus simultaneously, this generation method is made to possess practicality, easy for people to use.
3, the method step that the 2D house type photo based on camera shooting of the present invention generates 3D house type model comprises essence reduction to 2D image, image enhancement processing, employing Canny contours extract method Extracting contour and employing and the extending line intersection point of the adjacent two wall bodies after contours extract has all been done larger contribution and guarantee to the degree of accuracy of the 3D house type model generated by generation method of the present invention as the starting point of wall contour line and terminating point method.
Accompanying drawing explanation
Below in conjunction with drawings and Examples, the invention will be further described.
Fig. 1 is the house type primitive figure on page.
Fig. 2 is the 2D house type photo being obtained house type primitive figure by camera.
Fig. 3 carries out the 2D image after image enhancement processing to the 2D floor plan picture in step 2 in step 3.
Fig. 4 carries out the contour images after contours extract to the 2D image in step 3 in step 4.
Fig. 5 is according to the body of wall 2D image that contour images obtains in step 4.
Fig. 6 is after door and window adaptation and the 3D floor plan picture of acquisition after body of wall stretching.
Embodiment
Please refer to Fig. 1 to Fig. 6, have a lot for the method for 2D floor plan generation 3D house type model in prior art, a kind of 2D house type photo based on camera shooting of the present invention generates the method for 3D house type model, and it comprises:
Step 1, obtains 2D house type photo by camera shooting; The 2D house type photo that this shooting obtains obtains by the camera on portable mobile apparatus, and portable mobile apparatus can be any one in mobile phone, hand held camera, flat board.
Step 2, by essential matrix reducing process, the 2D house type photo that step 1 obtains is revised, four angular coordinates chosen in image restore a series of information such as focal length, image taking angle, shooting distance of camera according to essential matrix reducing process, can revise the error of the distortion of captured 2D figure, upright position or shooting angle according to these information, thus obtain a 2D floor plan picture rational in infrastructure.
Step 3, carries out image enhancement processing to the 2D floor plan picture after processing through step 2, described image enhancement processing comprises histogram equalization process, colour correction process, threshold value sampling process, Image erosion process, whole disposal route in the Swelling and contraction process of image and denoising or part disposal route, in the present embodiment, image enhancement processing described in step 3 is successively through histogram equalization process, colour correction process, threshold value sampling process, Image erosion process, the Swelling and contraction process of image and denoising, parameter adjustment wherein in variety of processes can realize carrying out parameter adjustment by abundant Different Plane figure and test in the hope of a best parameter configuration, and then in the variety of processes being applied in step 2, 2D image after process can meet the image definition requirements of successive image treatment step and the requirement of image characteristics extraction.A large amount of test
Step 4, extract the outline line of the 2D image after step 3 processes, two outline lines be parallel to each other of acquisition body of wall, the starting point of every wall body outline line and terminating point and door, curtain runner profile, by the starting point wall body structure that be connected to form house corresponding to terminating point of every adjacent two wall body outline lines, the starting point of wall contour line can distinguish corresponding a starting point and a terminating point by the extending line intersection points extracting two stifled neighboring walls after contours extract as these adjacent two wall bodies with terminating point here.The present invention program preferably adopts the outline line of Canny contours extract method to this 2D image to extract, and ensures higher contours extract precision.
Step 5, sets up door, window model bank, and the door extracted according to step 4, the wide wired-AND gate of curtain runner, window model bank are mated, so recognitiion gate, the position of window in building structure; Adopt comparatively fixing model pattern to express because door and window are general in floor plan, the location recognition therefore adopting the mode of Model Matching to carry out door and window still can have higher discrimination.But changed the Model Identification brought and mate difficulty by the change in size of door and window with rotation to overcome in door and window Model Matching process, the present invention adopts invariant moment features and/or surf unique point to mate, to reach higher matching precision.After door, window coupling, whether correct in order to determine the matched position of door, window position, also can calibrate according to the mating situation opposite house of door, window and wall body structure, the correctness of window position further, here the mating situation of door, window and wall body structure such as: door must be positioned at the blank space of the adjacent position of body of wall, if the door that door matches is positioned within body of wall, then door matching error is described; And window can only be embedded among body of wall or be positioned at body of wall medium position, if the window matched is positioned at the large stretch of white space outside body of wall, then matching error is described.
Step 6, the height and position that stretching wall body structure to is fixing, completes the structure of 3D house type model.
Can developing based on OpenCV computer vision storehouse of increasing income of the inventive method, is then transplanted on portable electric appts and applies.
The inventive method achieves by the automatic generation of 2D house type photo to 3D house type model, generation method is simple, there is general applicability, the 3D house type model generated accurately can reflect the script structural information in house, comprises the positional information etc. of the structural information (comprising the thickness information of body of wall) of body of wall, each room unit formed, number information and door and window.
Because 2D house type photo of the present invention is mainly obtained by instantly popular and conventional portable mobile apparatus camera, obtain manner is very convenient, in practical application, this generation method can be embedded the camera use in conjunction forming a APP application software and portable mobile apparatus in portable mobile apparatus, this generation method is made to possess practicality, simultaneously the routine use of also very convenient people.
The above, be only present pre-ferred embodiments, therefore can not limit scope of the invention process according to this, the equivalence change namely done according to the scope of the claims of the present invention and description with modify, all should still belong in scope that the present invention contains.
Claims (9)
1., based on the method for the 2D house type photo generation 3D house type model of camera shooting, it is characterized in that: comprising:
Step 1, obtains 2D house type photo by camera shooting;
Step 2, is revised the 2D house type photo that step 1 obtains by essential matrix reducing process, to obtain a 2D floor plan picture rational in infrastructure;
Step 3, carries out image enhancement processing to the 2D floor plan picture after processing through step 2;
Step 4, extract the outline line of the 2D image after step 3 processes, obtain two outline lines be parallel to each other of body of wall, the starting point of every wall body outline line and terminating point and door, curtain runner profile, by the starting point wall body structure that be connected to form house corresponding to terminating point of every adjacent two wall body outline lines;
Step 5, sets up door, window model bank, and the door extracted according to step 4, the wide wired-AND gate of curtain runner, window model bank are mated, so recognitiion gate, the position of window in building structure;
Step 6, the height and position that stretching wall body structure to is fixing.
2. the 2D house type photo based on camera shooting according to claim 1 generates the method for 3D house type model, it is characterized in that: described step 5 also comprises calibrates the door identified, the position of window in building structure.
3. the 2D house type photo based on camera shooting according to claim 1 generates the method for 3D house type model, it is characterized in that: being obtained by the camera on portable mobile apparatus by the 2D floor plan of camera shooting acquisition described in step 1.
4. the 2D house type photo based on camera shooting according to claim 1 generates the method for 3D house type model, it is characterized in that: image enhancement processing described in step 3 comprises the part or all of disposal route in histogram equalization process, colour correction process, threshold value sampling process, Image erosion process, the Swelling and contraction process of image and denoising.
5. the 2D house type photo based on camera shooting according to claim 4 generates the method for 3D house type model, it is characterized in that: the image enhancement processing described in step 3 is successively through Swelling and contraction process and the denoising of histogram equalization process, colour correction process, threshold value sampling process, Image erosion process, image.
6. the 2D house type photo based on camera shooting according to claim 1 generates the method for 3D house type model, it is characterized in that: the outline line described in step 4 extracts and adopts Canny contours extract method.
7. the 2D house type photo based on camera shooting according to claim 1 generates the method for 3D house type model, it is characterized in that: the door in the wide wired-AND gate of the door described in step 5, curtain runner, window model bank, window model are mated by invariant moment features and/or surf unique point.
8. the 2D house type photo based on camera shooting according to claim 1 generates the method for 3D house type model, it is characterized in that: the starting point of the line of wall contour described in step 4 and terminating point are the extending line intersection point of the stifled neighboring walls of two after contours extract.
9. the 2D house type photo based on camera shooting according to claim 3 generates the method for 3D house type model, it is characterized in that: described portable mobile apparatus comprises any one in mobile phone, hand held camera, flat board.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510259082.6A CN104821011A (en) | 2015-05-20 | 2015-05-20 | Method of generating 3D house type model by 2D house type model based on camera shooting |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510259082.6A CN104821011A (en) | 2015-05-20 | 2015-05-20 | Method of generating 3D house type model by 2D house type model based on camera shooting |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104821011A true CN104821011A (en) | 2015-08-05 |
Family
ID=53731294
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510259082.6A Pending CN104821011A (en) | 2015-05-20 | 2015-05-20 | Method of generating 3D house type model by 2D house type model based on camera shooting |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104821011A (en) |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105913485A (en) * | 2016-04-06 | 2016-08-31 | 北京小小牛创意科技有限公司 | Three-dimensional virtual scene generation method and device |
| CN106504335A (en) * | 2016-10-28 | 2017-03-15 | 国网电力科学研究院武汉南瑞有限责任公司 | Realization method and system based on 2D, 3D mixing augmented reality of mobile device |
| CN107067461A (en) * | 2016-12-24 | 2017-08-18 | 上海与德信息技术有限公司 | The construction method and device of indoor stereo figure |
| 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 |
| CN107229231A (en) * | 2017-06-07 | 2017-10-03 | 青岛海信移动通信技术股份有限公司 | Home equipment management method and device |
| CN107452055A (en) * | 2017-08-09 | 2017-12-08 | 北京我易家网络科技发展有限公司 | Three-dimensional house type drawing generating method and device |
| CN107632285A (en) * | 2017-09-19 | 2018-01-26 | 北京小米移动软件有限公司 | Map building and amending method and device |
| WO2018027553A1 (en) * | 2016-08-09 | 2018-02-15 | 盛玉伟 | Method and system for drawing style during refurbishment |
| CN108399644A (en) * | 2018-02-05 | 2018-08-14 | 北京居然之家家居连锁集团有限公司 | A kind of wall images recognition methods and its device |
| CN108470377A (en) * | 2018-03-12 | 2018-08-31 | 万维云视（上海）数码科技有限公司 | AR sees room device |
| CN108664670A (en) * | 2017-03-27 | 2018-10-16 | 长沙眸瑞网络科技有限公司 | House type CAD automatically generates the implementation method of 3D house type models |
| CN108763606A (en) * | 2018-03-12 | 2018-11-06 | 江苏艾佳家居用品有限公司 | A kind of floor plan element extraction method and system based on machine vision |
| CN108804815A (en) * | 2018-06-08 | 2018-11-13 | 杭州群核信息技术有限公司 | A kind of method and apparatus assisting in identifying wall in CAD based on deep learning |
| CN109218524A (en) * | 2018-08-27 | 2019-01-15 | 山东大唐宅配家居有限公司 | The cell phone application and method that house measurement generates floor plan are carried out based on video recording of taking pictures |
| CN109241635A (en) * | 2018-09-12 | 2019-01-18 | 深圳市彬讯科技有限公司 | House type analysis method and device |
| CN109858185A (en) * | 2019-03-08 | 2019-06-07 | 广东岭南职业技术学院 | A kind of interior decoration design method based on AR virtual reality technology |
| CN109903369A (en) * | 2019-01-17 | 2019-06-18 | 平安城市建设科技(深圳)有限公司 | Three-dimensional house type model building method, device, equipment and readable storage medium storing program for executing |
| CN110096949A (en) * | 2019-03-16 | 2019-08-06 | 平安城市建设科技(深圳)有限公司 | Floor plan intelligent identification Method, device, equipment and computer readable storage medium |
| CN110136244A (en) * | 2019-04-12 | 2019-08-16 | 平安城市建设科技(深圳)有限公司 | Three-dimensional house type model generating method, device, equipment and storage medium |
| CN110176057A (en) * | 2019-04-12 | 2019-08-27 | 平安城市建设科技(深圳)有限公司 | Three-dimensional house type model generating method, device, equipment and storage medium |
| CN110189398A (en) * | 2019-04-12 | 2019-08-30 | 平安城市建设科技(深圳)有限公司 | House type drawing generating method, device, equipment and storage medium based on off-the-air picture |
| CN110458927A (en) * | 2019-08-02 | 2019-11-15 | 广州彩构网络有限公司 | A kind of information processing method that picture is generated to three-dimensional house type model automatically |
| CN113313761A (en) * | 2021-07-28 | 2021-08-27 | 盎锐(常州)信息科技有限公司 | Site acquisition method, scanning device and system for actual measurement |
| CN116342604A (en) * | 2023-05-30 | 2023-06-27 | 长沙泛一参数信息技术有限公司 | Method and system for achieving contour similarity matching based on shear wall appearance |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110181589A1 (en) * | 2010-01-28 | 2011-07-28 | The Hong Kong University Of Science And Technology | Image-based procedural remodeling of buildings |
| CN102750397A (en) * | 2011-04-21 | 2012-10-24 | 北京七十二炫信息技术有限公司 | System capable of automatically generating colorful three-dimensional scene construction drawing |
-
2015
- 2015-05-20 CN CN201510259082.6A patent/CN104821011A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110181589A1 (en) * | 2010-01-28 | 2011-07-28 | The Hong Kong University Of Science And Technology | Image-based procedural remodeling of buildings |
| CN102750397A (en) * | 2011-04-21 | 2012-10-24 | 北京七十二炫信息技术有限公司 | System capable of automatically generating colorful three-dimensional scene construction drawing |
Non-Patent Citations (2)
| Title |
|---|
| 朱俊芳: "基于结构构件识别的户型图三维重建算法研究", 《中国优秀硕士学位论文全文数据库》 * |
| 赵锦艳: "面向安全预演的建筑平面图识别与场景语义生成方法的研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10740963B2 (en) | 2016-04-06 | 2020-08-11 | Beijing Xiaoxiaoniu Creative Technologies Ltd | 3D virtual environment generating method and device |
| CN105913485A (en) * | 2016-04-06 | 2016-08-31 | 北京小小牛创意科技有限公司 | Three-dimensional virtual scene generation method and device |
| WO2018027553A1 (en) * | 2016-08-09 | 2018-02-15 | 盛玉伟 | Method and system for drawing style during refurbishment |
| CN106504335A (en) * | 2016-10-28 | 2017-03-15 | 国网电力科学研究院武汉南瑞有限责任公司 | Realization method and system based on 2D, 3D mixing augmented reality of mobile device |
| CN107067461A (en) * | 2016-12-24 | 2017-08-18 | 上海与德信息技术有限公司 | The construction method and device of indoor stereo figure |
| CN108664670B (en) * | 2017-03-27 | 2021-07-20 | 长沙眸瑞网络科技有限公司 | Method for realizing automatic generation of 3D house type model by house type CAD |
| CN108664670A (en) * | 2017-03-27 | 2018-10-16 | 长沙眸瑞网络科技有限公司 | House type CAD automatically generates the implementation method of 3D house type models |
| CN107122528B (en) * | 2017-04-13 | 2021-11-19 | 广州乐家数字科技有限公司 | House type graph parameterization re-editable modeling 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 |
| CN107229231A (en) * | 2017-06-07 | 2017-10-03 | 青岛海信移动通信技术股份有限公司 | Home equipment management method and device |
| CN107229231B (en) * | 2017-06-07 | 2021-03-30 | 青岛海信移动通信技术股份有限公司 | Household equipment management method and device |
| CN107452055A (en) * | 2017-08-09 | 2017-12-08 | 北京我易家网络科技发展有限公司 | Three-dimensional house type drawing generating method and device |
| CN107452055B (en) * | 2017-08-09 | 2020-08-14 | 北京我易家网络科技发展有限公司 | Three-dimensional house type graph generation method and device |
| CN107632285A (en) * | 2017-09-19 | 2018-01-26 | 北京小米移动软件有限公司 | Map building and amending method and device |
| CN108399644A (en) * | 2018-02-05 | 2018-08-14 | 北京居然之家家居连锁集团有限公司 | A kind of wall images recognition methods and its device |
| CN108763606A (en) * | 2018-03-12 | 2018-11-06 | 江苏艾佳家居用品有限公司 | A kind of floor plan element extraction method and system based on machine vision |
| CN108470377A (en) * | 2018-03-12 | 2018-08-31 | 万维云视（上海）数码科技有限公司 | AR sees room device |
| CN108804815A (en) * | 2018-06-08 | 2018-11-13 | 杭州群核信息技术有限公司 | A kind of method and apparatus assisting in identifying wall in CAD based on deep learning |
| CN109218524A (en) * | 2018-08-27 | 2019-01-15 | 山东大唐宅配家居有限公司 | The cell phone application and method that house measurement generates floor plan are carried out based on video recording of taking pictures |
| CN109218524B (en) * | 2018-08-27 | 2021-04-13 | 山东大唐宅配家居有限公司 | Mobile phone APP and method for generating house type graph through house measurement based on photographing and video recording |
| CN109241635B (en) * | 2018-09-12 | 2023-05-26 | 深圳市彬讯科技有限公司 | House type analysis method and device |
| CN109241635A (en) * | 2018-09-12 | 2019-01-18 | 深圳市彬讯科技有限公司 | House type analysis method and device |
| CN109903369A (en) * | 2019-01-17 | 2019-06-18 | 平安城市建设科技(深圳)有限公司 | Three-dimensional house type model building method, device, equipment and readable storage medium storing program for executing |
| CN109858185A (en) * | 2019-03-08 | 2019-06-07 | 广东岭南职业技术学院 | A kind of interior decoration design method based on AR virtual reality technology |
| CN109858185B (en) * | 2019-03-08 | 2022-09-02 | 广东岭南职业技术学院 | Indoor decoration design method based on AR virtual reality technology |
| CN110096949A (en) * | 2019-03-16 | 2019-08-06 | 平安城市建设科技(深圳)有限公司 | Floor plan intelligent identification Method, device, equipment and computer readable storage medium |
| CN110176057A (en) * | 2019-04-12 | 2019-08-27 | 平安城市建设科技(深圳)有限公司 | Three-dimensional house type model generating method, device, equipment and storage medium |
| CN110189398A (en) * | 2019-04-12 | 2019-08-30 | 平安城市建设科技(深圳)有限公司 | House type drawing generating method, device, equipment and storage medium based on off-the-air picture |
| CN110136244A (en) * | 2019-04-12 | 2019-08-16 | 平安城市建设科技(深圳)有限公司 | Three-dimensional house type model generating method, device, equipment and storage medium |
| CN110458927A (en) * | 2019-08-02 | 2019-11-15 | 广州彩构网络有限公司 | A kind of information processing method that picture is generated to three-dimensional house type model automatically |
| CN113313761A (en) * | 2021-07-28 | 2021-08-27 | 盎锐(常州)信息科技有限公司 | Site acquisition method, scanning device and system for actual measurement |
| CN113313761B (en) * | 2021-07-28 | 2022-04-01 | 盎锐(常州)信息科技有限公司 | Site acquisition method, scanning device and system for actual measurement |
| CN116342604A (en) * | 2023-05-30 | 2023-06-27 | 长沙泛一参数信息技术有限公司 | Method and system for achieving contour similarity matching based on shear wall appearance |
| CN116342604B (en) * | 2023-05-30 | 2023-08-08 | 长沙泛一参数信息技术有限公司 | Method and system for achieving contour similarity matching based on shear wall appearance |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104821011A (en) | Method of generating 3D house type model by 2D house type model based on camera shooting | |
| CN110147721B (en) | Three-dimensional face recognition method, model training method and device | |
| CN108038420B (en) | Human behavior recognition method based on depth video | |
| AU2017302250A1 (en) | Optical character recognition in structured documents | |
| CN102622593B (en) | Text recognition method and system | |
| CN106920206B (en) | Steganalysis method based on antagonistic neural network | |
| CN102324042B (en) | Visual recognition system and method | |
| CN106156684B (en) | A kind of two-dimensional code identification method and device | |
| CN103679147A (en) | Method and device for identifying model of mobile phone | |
| CN110570481A (en) | calligraphy word stock automatic repairing method and system based on style migration | |
| US20150356372A1 (en) | Character recognition method | |
| CN102930277A (en) | Character picture verification code identifying method based on identification feedback | |
| CN104167003A (en) | Method for fast registering remote-sensing image | |
| KR102158799B1 (en) | Method, computer program and apparatus for recognition of building by using deep neural network model | |
| CN103927016A (en) | Real-time three-dimensional double-hand gesture recognition method and system based on binocular vision | |
| TWI711980B (en) | Facial expression recognition training system and facial expression recognition training method | |
| Sonth et al. | OCR based facilitator for the visually challenged | |
| CN106504225A (en) | A kind of recognition methodss of regular polygon and device | |
| JP2022133378A (en) | Face biological detection method, device, electronic apparatus, and storage medium | |
| CN109886274A (en) | Social security card identification method and system based on opencv and deep learning | |
| CN104392229A (en) | Handwriting identification method based on stroke fragment direction distribution characteristics | |
| CN110516527B (en) | Visual SLAM loop detection improvement method based on instance segmentation | |
| CN108764230A (en) | A kind of bank's card number automatic identifying method based on convolutional neural networks | |
| CN104978583B (en) | The recognition methods of figure action and device | |
| CN111680577A (en) | Face detection method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150805 |
|
| WD01 | Invention patent application deemed withdrawn after publication |