CN103218849A - Image modeling system - Google Patents
Image modeling system Download PDFInfo
- Publication number
- CN103218849A CN103218849A CN2012100165289A CN201210016528A CN103218849A CN 103218849 A CN103218849 A CN 103218849A CN 2012100165289 A CN2012100165289 A CN 2012100165289A CN 201210016528 A CN201210016528 A CN 201210016528A CN 103218849 A CN103218849 A CN 103218849A
- Authority
- CN
- China
- Prior art keywords
- image
- modeled
- target
- cameras
- analyzing unit
- 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
Images
Landscapes
- Studio Devices (AREA)
Abstract
The invention relates to an image modeling system which comprises a modeled target platform, an image acquisition device and an image processing analyzing unit, wherein the modeled target platform can be used for placing a modeled object, the image acquisition device acquires and stores pictures or videos of the modeled target, the image processing analyzing unit processes and analyzes the pictures or the videos, and the image acquisition device is connected with the image processing analyzing unit. According to the image modeling system, a plurality of cameras are simultaneously utilized to acquire the pictures and the videos of variation of a modeled target at different angles and under different illuminations, and model parameters are extracted. The image modeling system has the advantages of being high in speed, targeted, low in cost, high in precision and small in splicing accumulation error. The image modeling system can also be used for scanning a modeled target with special feature points, data analyzing and processing are simple, fast and convenient, a scanned image has color features, and saw teeth caused by triangular mapping in a later period are avoided.
Description
Technical field
The present invention relates to field of image recognition, more specifically, relate to a kind of image modeling system.
Background technology
Image recognition technology is meant utilizes computing machine that image is handled, analyzed and understands, with the target of discerning various different modes and the technology of object.In the image recognition technology field, image to be identified and known image be compared, could realize re-recognizing image.Before identifying, the image recording of target to be identified (people or thing) need be got off, promptly obtain picture or video, and set up the model of target to be identified by technological means by camera head.
In the prior art, laser three-dimensional scanning system adopts laser to being modeled the scanning that target surface carries out dot matrix, and the data that collect are the point cloud datas that do not have color information, and then operational data is handled restore target.The point that this laser three-dimensional scanning system need scan is more, and is consuming time longer, only is adapted at using in the static large-sized object modeling; And for dynamic baby volume modeling, scanning errors is big, weak effect, and cost is higher, if the purpose of scanning only is to be modeled the clarification of objective point dynamically in order to extract, laser three-dimensional scanning system just can't be finished.
Summary of the invention
The object of the present invention is to provide a kind of image modeling system, the scan feature point that exists in the prior art is many to solve, the problem of length consuming time, and problems such as the scanning errors that occurs in the modeling process of dynamic or small-sized object is big, weak effect, cost height.
For realizing above purpose, the present invention discloses following technical scheme:
A kind of image modeling system, comprise and can place picture or the described picture of image collecting device, Treatment Analysis of video or the image processing and analyzing unit of video that target platform, collection and storage are modeled target that be modeled that is modeled target, described image collecting device is connected with described image processing and analyzing unit.
Described image collecting device comprises more than two cameras, and the camera lens of described camera is over against the described target that is modeled, and described two above cameras can multi-angle be taken the described target that is modeled; Described image collecting device comprises also and is used to described picture or video image encoded scrambler that described two above cameras are connected with described image processing and analyzing unit by described image encoder.
Described two above cameras are arranged in array.
Described two above cameras all are located on the same plane or are located at described and are modeled on the same sphere that target's center is the centre of sphere.
Described two above cameras all are located on the same pedal line, and described two above cameras can be done horizontal circular motion around being modeled place, target 1 center pedal line.
Be fixed with N group camera group on the N Along ent of same horizontal circumference that target's center is the center of circle respectively with described being modeled, described camera group comprises the more than two cameras of being located on the same pedal line, and wherein, N is the natural number more than or equal to 2.
Described image processing and analyzing unit is for to carry out the computing machine that the key area is cut apart, extracted feature, sets up model to described picture or video.
The described target platform that is modeled comprises horizontal rotation platform and drives the jacking gear that described horizontal rotation platform moves up and down.
Described be modeled target platform also comprise have solid color, the background board vertical with surface level.
The described target platform that is modeled also comprises control described horizontal rotation platform rotation and the controller that moves up and down.
The invention has the advantages that: a kind of image modeling of the present invention system, utilize a plurality of video cameras to collect the picture or the video extraction model parameter of modeling object variations under a plurality of different angles and the different light simultaneously, have that speed is fast, with strong points, cost is low, precision is high, little characteristics of splicing accumulated error; Also can be used to scan the modeling target with specific characteristic point, simple and fast is handled in data analysis; And the picture strip of scanning has color character, can exempt the sawtooth that later stage triangle pinup picture brings.
Description of drawings
Fig. 1 is a structural representation of the present invention,
Fig. 2 is modeled the structural representation of target platform for the present invention,
Fig. 3 makes structural representation under the circular motion situation for the present invention at camera,
The number in the figure explanation:
1, is modeled target; 2, be modeled target platform; 3, image collecting device;
4, image processing and analyzing unit; 5, camera; 6, horizontal rotation platform; 7, background board.
Embodiment
Below in conjunction with description of drawings the specific embodiment of the present invention, those skilled in the art more will be expressly understood how will put into practice the present invention.Although should be appreciated that in conjunction with its preferred specific embodiments and described the present invention, these embodiment limit the scope of the invention.
A kind of image modeling system as shown in Figure 1 and Figure 2, comprise placing being modeled being modeled target platform 2, gathering and storing and being modeled the picture of target or the image collecting device 3 of video, the image processing and analyzing unit 4 of the described picture of Treatment Analysis of target 1, image collecting device 3 is connected with image processing and analyzing unit 4.
Image collecting device 3 comprises more than two cameras 5, and the camera lens of camera 5 can the multi-angle shooting be modeled target 1 over against described 1, two the above camera 5 of target that is modeled.The camera of differing heights, its camera lens all equate to the distance that is modeled target 1, guarantee to show on plurality of pictures that different cameras photographed or the video to be modeled target 1 size corresponding.If the camera lens of camera has nothing in common with each other to the distance that is modeled target 1, then need to regulate each camera lens focus or by image processing make show on plurality of pictures that different cameras photographed or the video to be modeled target 1 big or small corresponding.Image collecting device 3 comprises also and is used to described picture or video image encoded scrambler that described two above cameras are connected with described image processing and analyzing unit by described image encoder.Image encoder splits into several graphical elements with described picture or video, and the graphical element after will splitting again is sent to described image processing and analyzing unit and is for further processing.Image encoder is used for the picture information of gathering is carried out picture coding so that picture transmission.Image collecting device 3 also comprises the storer that is used to store described picture or video.
As shown in Figure 3, two above cameras 5 all are located on the same pedal line, and two above cameras 5 can be done horizontal circular motion around being modeled place, target 1 center pedal line.More than two cameras 5 equates that with the distance that is modeled place, target 1 center pedal line that is to say, all cameras 5 all equate to the distance that is modeled place, target 1 center pedal line.The above center that is modeled target 1 is meant the central point of the axis that is modeled target 1.
With described to be modeled target's center be the center of circle, be to be fixed with N group camera group respectively on the N Along ent of same horizontal circumference of radius with the pedal line at camera place and the distance that is modeled target's center, described camera group comprises the more than two cameras of being located on the same pedal line, wherein, N is the natural number more than or equal to 2.Preferred version is that every group of camera group comprises three cameras, N=8, the pedal line at the distance of two adjacent cameras and camera place is identical with the distance that is modeled target's center on the same group, is the center of circle to be modeled target's center, is to be fixed with 8 groups of camera groups respectively on 8 Along ents of same horizontal circumference of radius with the pedal line and the distance that is modeled target's center at camera place.
Image processing and analyzing unit 4 is for to carry out the computing machine that the key area is cut apart, extracted feature, sets up model to described picture or video.By computer technology image modeling is handled, at first described picture or video are carried out the key area dividing processing, picture or Video Segmentation are become several different zones; Then described picture or video are carried out feature extraction and handle, carry out grouping comparison, and extract and be modeled target 1 feature showing on different pictures or the video that the part picture that is modeled target 1 the same area or video divide to same group; Set up model at last, the different characteristic of extracting is concentrated in together, be combined into the model that is modeled target 1.Image processing and analyzing unit 4 is a local computer, also can be remote server or service centre etc., and image that camera array collects or video are sent in the image collecting device, can the local analytics deal with data or upload onto the server or data center.The mode that transmits and upload includes but not limited to Ethernet, wifi, 3G, modes such as GPRS.
As shown in Figure 2, be modeled target platform 2 and comprise horizontal rotation platform 6, be used for placement and be modeled target 1.The rotation in the horizontal direction of horizontal rotation platform 6, different directions, the different angles of guaranteeing to be modeled target 1 can both be photographed by the camera 5 of image collecting device 3.
Be modeled target platform 2 and be provided with the jacking gear (figure does not show) that the horizontal rotation platform 6 of drive moves up and down, each angle, each details of guaranteeing to be modeled target 1 can both be photographed by the camera 5 of image collecting device 3, the jacking gear kind that moves up and down is various, be all prior art, this do not added give unnecessary details.
Be modeled target platform 2 also comprise have solid color, the background board 7 vertical with surface level, in picture or video post-processed, at first to remove the part except that being modeled target 1 on picture or the video, have the color background plate can be so that the part color of need removing is single, deletion action be convenient.The background board 7 general whites of selecting as if being modeled target 1 for light colors such as whites, can be selected black or mazarine.
If the camera 5 of image collecting device 3 can move, then background board 7 also must be selected the packaged type background board, in camera 5 moving process, all the time guarantee camera 5 camera lens, be modeled target 1 and background board 7 on same straight line, background board 7 is vertical with described straight line all the time, can guarantee the effect of taking pictures of camera 5.
If the camera 5 of image collecting device 3 be separately fixed at described to be modeled target's center be the center of circle, be that background board 7 can the surrounding target rotation on the N Along ent of same horizontal circumference of radius with the pedal line and the distance that is modeled target's center at camera place.After background board 7 is static, guarantee the camera 5 relative with this background board 7 camera lens, be modeled target 1 and background board 7 on same straight line, background board 7 is vertical with described straight line, can guarantee the effect of taking pictures of camera 5.
Be modeled the controller (figure does not show) that target platform 2 also comprises 6 rotations of controlling level rotation platform and moves up and down, can be so that the user be more convenient to operate.
The above only is a preferred implementation of the present invention; should be pointed out that for those skilled in the art, under the prerequisite that does not break away from the principle of the invention; can also make some improvements and modifications, these improvements and modifications also should be considered as protection scope of the present invention.
Claims (10)
1. image modeling system, it is characterized in that, comprise and can place picture or the described picture of image collecting device, Treatment Analysis of video or the image processing and analyzing unit of video that target platform, collection and storage are modeled target that be modeled that is modeled target, described image collecting device is connected with described image processing and analyzing unit.
2. a kind of image modeling as claimed in claim 1 system, it is characterized in that, described image collecting device comprises more than two cameras, and the camera lens of described camera is over against the described target that is modeled, and described two above cameras can multi-angle be taken the described target that is modeled; Described image collecting device comprises also and is used to described picture or video image encoded scrambler that described two above cameras are connected with described image processing and analyzing unit by described image encoder.
3. a kind of image modeling as claimed in claim 2 system is characterized in that described two above cameras are arranged in array.
4. a kind of image modeling as claimed in claim 3 system is characterized in that described two above cameras all are located on the same plane or are located at described and are modeled on the same sphere that target's center is the centre of sphere.
5. a kind of image modeling as claimed in claim 2 system is characterized in that described two above cameras all are located on the same pedal line, and described two above cameras can be done horizontal circular motion around being modeled target's center's place pedal line.
6. a kind of image modeling as claimed in claim 2 system, it is characterized in that, be fixed with N group camera group on the N Along ent of same horizontal circumference that target's center is the center of circle respectively with described being modeled, described camera group comprises the more than two cameras of being located on the same pedal line, wherein, N is the natural number more than or equal to 2.
7. a kind of image modeling as claimed in claim 1 system is characterized in that described image processing and analyzing unit is for to carry out the computing machine that the key area is cut apart, extracted feature, sets up model to described picture or video.
8. a kind of image modeling as claimed in claim 1 system is characterized in that the described target platform that is modeled comprises horizontal rotation platform and drives the jacking gear that described horizontal rotation platform moves up and down.
9. a kind of image modeling as claimed in claim 8 system is characterized in that, described be modeled target platform also comprise have solid color, the background board vertical with surface level.
10. a kind of image modeling as claimed in claim 8 system is characterized in that the described target platform that is modeled also comprises control described horizontal rotation platform rotation and the controller that moves up and down.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012100165289A CN103218849A (en) | 2012-01-19 | 2012-01-19 | Image modeling system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012100165289A CN103218849A (en) | 2012-01-19 | 2012-01-19 | Image modeling system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103218849A true CN103218849A (en) | 2013-07-24 |
Family
ID=48816591
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012100165289A Pending CN103218849A (en) | 2012-01-19 | 2012-01-19 | Image modeling system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103218849A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105279785A (en) * | 2014-06-24 | 2016-01-27 | 北京鸿合智能系统股份有限公司 | Display platform three-dimensional modeling method and device |
| CN105447481A (en) * | 2015-12-30 | 2016-03-30 | 四川川大智胜软件股份有限公司 | Three-dimensional face data acquisition system based on image sensor array |
| CN105865356A (en) * | 2016-04-05 | 2016-08-17 | 华中科技大学无锡研究院 | Axial multi-hole medium appearance dimension automatic measurement system and method |
| CN106656333A (en) * | 2016-11-17 | 2017-05-10 | 合肥铭锶伟途信息科技有限公司 | Fiber-based embedded real-time image exchange processing system |
| CN109118089A (en) * | 2018-08-10 | 2019-01-01 | 韩鹏 | A kind of Chinese meal dinner party is set a table image collecting device and points-scoring system |
| TWI759061B (en) * | 2020-12-28 | 2022-03-21 | 財團法人工業技術研究院 | A method for generating goods modeling data and goods modeling data generation device |
| CN114693861A (en) * | 2020-12-28 | 2022-07-01 | 财团法人工业技术研究院 | Article modeling data generation method and article modeling data generation device |
| CN115984488A (en) * | 2023-03-16 | 2023-04-18 | 深圳市完美显示科技有限公司 | AI image intelligent modeling system based on 5G network |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11248431A (en) * | 1998-02-27 | 1999-09-17 | Sharp Corp | Three-dimensional model forming apparatus and computer readable medium recorded with three-dimensional model generating program |
| CN1421020A (en) * | 1999-11-23 | 2003-05-28 | 佳能株式会社 | Image processing apparatus |
| CN1595280A (en) * | 2004-07-01 | 2005-03-16 | 上海交通大学 | Three-dimensional human face rebuilding system on rotating platform |
| CN101118570A (en) * | 2007-09-06 | 2008-02-06 | 许焱 | Device and method for gem three-dimensional blank reconstruction design based on machine vision |
| CN101271579A (en) * | 2008-04-10 | 2008-09-24 | 清华大学 | Method for modeling high-speed moving object adopting ring shaped low frame rate camera array |
| CN101853521A (en) * | 2010-04-22 | 2010-10-06 | 武汉微目科技有限公司 | Cultural relic rotation structured light three-dimensional digital modeling method |
-
2012
- 2012-01-19 CN CN2012100165289A patent/CN103218849A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11248431A (en) * | 1998-02-27 | 1999-09-17 | Sharp Corp | Three-dimensional model forming apparatus and computer readable medium recorded with three-dimensional model generating program |
| CN1421020A (en) * | 1999-11-23 | 2003-05-28 | 佳能株式会社 | Image processing apparatus |
| CN1595280A (en) * | 2004-07-01 | 2005-03-16 | 上海交通大学 | Three-dimensional human face rebuilding system on rotating platform |
| CN101118570A (en) * | 2007-09-06 | 2008-02-06 | 许焱 | Device and method for gem three-dimensional blank reconstruction design based on machine vision |
| CN101271579A (en) * | 2008-04-10 | 2008-09-24 | 清华大学 | Method for modeling high-speed moving object adopting ring shaped low frame rate camera array |
| CN101853521A (en) * | 2010-04-22 | 2010-10-06 | 武汉微目科技有限公司 | Cultural relic rotation structured light three-dimensional digital modeling method |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105279785A (en) * | 2014-06-24 | 2016-01-27 | 北京鸿合智能系统股份有限公司 | Display platform three-dimensional modeling method and device |
| CN105279785B (en) * | 2014-06-24 | 2021-10-15 | 北京鸿合智能系统有限公司 | Method and device for three-dimensional modeling of exhibition stand |
| CN105447481B (en) * | 2015-12-30 | 2019-04-30 | 四川川大智胜软件股份有限公司 | Three-dimensional face data acquisition system based on image sensor array |
| CN105447481A (en) * | 2015-12-30 | 2016-03-30 | 四川川大智胜软件股份有限公司 | Three-dimensional face data acquisition system based on image sensor array |
| CN105865356A (en) * | 2016-04-05 | 2016-08-17 | 华中科技大学无锡研究院 | Axial multi-hole medium appearance dimension automatic measurement system and method |
| CN106656333A (en) * | 2016-11-17 | 2017-05-10 | 合肥铭锶伟途信息科技有限公司 | Fiber-based embedded real-time image exchange processing system |
| CN109118089A (en) * | 2018-08-10 | 2019-01-01 | 韩鹏 | A kind of Chinese meal dinner party is set a table image collecting device and points-scoring system |
| CN109118089B (en) * | 2018-08-10 | 2022-08-02 | 韩鹏 | Chinese food banquet platform setting image acquisition device and scoring system |
| TWI759061B (en) * | 2020-12-28 | 2022-03-21 | 財團法人工業技術研究院 | A method for generating goods modeling data and goods modeling data generation device |
| CN114693861A (en) * | 2020-12-28 | 2022-07-01 | 财团法人工业技术研究院 | Article modeling data generation method and article modeling data generation device |
| US11568578B2 (en) | 2020-12-28 | 2023-01-31 | Industrial Technology Research Institute | Method for generating goods modeling data and goods modeling data generation device |
| CN115984488A (en) * | 2023-03-16 | 2023-04-18 | 深圳市完美显示科技有限公司 | AI image intelligent modeling system based on 5G network |
| CN115984488B (en) * | 2023-03-16 | 2023-10-27 | 深圳市完美显示科技有限公司 | AI image intelligent modeling system based on 5G network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103218849A (en) | Image modeling system | |
| JP6616862B2 (en) | Image feature detection using edge vectors | |
| CN110609037B (en) | Product defect detection system and method | |
| JP2020537217A (en) | Object detection and avoidance for aircraft | |
| CN1247955C (en) | Method and apparatus for three-dimensional color scanning | |
| CN100576234C (en) | Use the local locating method of rapid image coupling | |
| CN107977639B (en) | Face definition judgment method | |
| JP2016162442A (en) | Text extraction method, system, and program | |
| CN112912890A (en) | Method and system for generating synthetic point cloud data using generative models | |
| CN109978805A (en) | It takes pictures processing method, device, mobile terminal and storage medium | |
| CN111178317A (en) | Detection positioning method, system, device, electronic equipment and storage medium | |
| CN1912534A (en) | Contactless three-axle air-float stage corner measuring device and its measuring method | |
| CN107845095A (en) | Mobile object real time detection algorithm based on three-dimensional laser point cloud | |
| CA3157444A1 (en) | Method for depth estimation for a variable focus camera | |
| US20240020923A1 (en) | Positioning method based on semantic information, device and computer-readable storage medium | |
| JP2018107593A5 (en) | ||
| JP5423764B2 (en) | Moving object detection apparatus, computer program, and moving object detection method | |
| CN115689928B (en) | Method and system for removing duplication of transmission tower inspection images under visible light | |
| CN1584915A (en) | Human iris identifying method | |
| CN102087700B (en) | Method and system for identifying production information of automobile hub | |
| CN112700498A (en) | Wind driven generator blade tip positioning method and system based on deep learning | |
| CN103733225A (en) | Characteristic point coordination system, characteristic point coordination method, and recording medium | |
| CN115550517A (en) | Scanning control method, system, electronic device and storage medium | |
| Matsumoto et al. | Extraction of guardrails from mms data using convolutional neural network | |
| CN201788517U (en) | Automobile hub production information recognition system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130724 |