CN104126989B - A kind of based on the foot surfaces 3 D information obtaining method under multiple stage RGB-D pick up camera - Google Patents
A kind of based on the foot surfaces 3 D information obtaining method under multiple stage RGB-D pick up camera Download PDFInfo
- Publication number
- CN104126989B CN104126989B CN201410367191.5A CN201410367191A CN104126989B CN 104126989 B CN104126989 B CN 104126989B CN 201410367191 A CN201410367191 A CN 201410367191A CN 104126989 B CN104126989 B CN 104126989B
- Authority
- CN
- China
- Prior art keywords
- foot
- camera
- pick
- rgb
- curved surface
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The present invention relates to a kind of based on the foot surfaces 3 D information obtaining method under multiple stage RGB-D pick up camera, the comprehensive measuring system that multiple stage RGB-D pick up camera is built by the method is applied in the quick acquisition of foot surfaces three-dimensional information and the fast reconstitution of foot surfaces model, can when not putting by any mark, the foot curved surface three-dimensional coordinate that disposable collection is complete. The comprehensive measuring system of many RGB-D pick up camera is utilized to obtain the degree of depth information of foot type curved surface under each visual angle fast, and be converted to three-dimensional point cloud, by the local foot curved surface three-dimensional point cloud that different RGB-D pick up camera obtains is carried out registration, reconstruct the overall model of foot type curved surface, and according to actual needs, can extract and measure foot type characteristic parameter. It is fast that the method not only rebuilds speed, efficiency of measurement height, and is easy to realize, and measures cost low, it may also be useful to effective.
Description
Technical field
The present invention relates to D surface masurement technical field, particularly a kind of based on the foot surfaces 3 D information obtaining method under multiple stage RGB-D pick up camera.
Background technology
In recent years, many industrial production wire system are produced to customization, personalized, type production transformation on a small scale by extensive batch-type. And it is indispensable to personalized production system to design production technology fast. In the production system that a typical curstomer-oriented customization requires, client provides the detailed data of desired product online, plays order subsequently. The product that after several days, client orders just can be produced according to the individual demand of client, posts in client's hand. This kind of thought is applied to our shoemaking industry by us. Producing as the customized personalized shoes of each client, shoe tree design, producing personalization for client fast is key. The style of everyone foot type, size and individual's preference is far from each other, and thus the application of customer-oriented footwear industry production system will show huge vitality.
The advantage of the shoemaking system of personalized customization is that client is fitted, can also be selected the SHOE STYLE oneself liked while comfort requirement meeting. From the angle of manufacturers, the shoemaking system of personalized customization not only means less stock, and scans client's foot three-dimensional model of acquisition and relevant information can also preserve for subsequent use. The shoemaking system of personalized customization can not only realize footwear customization, the Intelligent Selection footwear of human consumer, and in orthopedics customization, artificial limb is produced, medical diagnosis and operation are auxiliary etc., and medical field also has important application.
Accurate and high efficiency foot shape measurement method be not only shoe last designing and be convenient for people to select footwear, to wear footwear indispensable, and is that extensive foot shape measurement, foot type rectification etc. are necessary. Existing foot shape measurement method divides contact type measurement and non-contact measurement two kinds.
1, contact type measurement: the electronic measuring instrument that contact type measurement mainly uses some mechanical hand dipping instruments or is made up of contact-sensing device, wherein based on hand dipping. The instrument of hand dipping mainly comprises: cloth mark, steel tape, stroke pen, amount Gao Yi, step print device and amount pin slide calliper rule. Hand dipping is divided into again direct method and indirect method measuring method. Direct method is fairly simple. First marking relevant measurement point on the characteristic portion of pin with pen, each utilizing that cloth mark, the amount instrument such as Gao Yi can directly measure pin is about data. Indirect method utilizes footprint device to step footprint and draw out the skeletal lines of pin, and then carries out Measurement and analysis. The advantage of contact foot shape measurement is less investment, operation steps is simple, handiness is strong, be convenient for carrying, be convenient in the short period of time measures in different measurement places. Shortcoming is that foot can be produced pressure by contact type measurement mode, cause foot's deformation, cause measuring error, Measuring Time is long, and the foot's parameter measured is limited, some more complicated parameter or curve cannot be measured, and inefficiency, labour intensity are big, repetition is poor, error between measurer is big, meanwhile, this kind of metering system is difficult to obtain the data information of foot's entirety. The section morphology of pin can not be carried out data gathering. More profound research cannot be carried out.
2, non-contact measurement: under the drive of the discipline development such as computer, optics. Optical non-contact measures the attention that a measuring technology as rising in recent years is got more and more. At present, optical non-contact measuring method mainly contains structure optical measurement, stereo-visiuon measurement, laser measurement etc.
(1) structural light measurement: structured light three-dimensional vision is based on optic triangle method principle, its ultimate principle projects, to testee surface, luminous point, light bar or the light face structure that can control by structured light projector, and obtain image by image sensor (such as pick up camera), by system geometric relationship, triangle principle is utilized to calculate the three-dimensional coordinate of object. Structural light measurement method has the advantages that calculating is simple, volume is little, price is low, is convenient to installation and safeguards, is widely used in actual measuring three-dimensional profile. But measuring accuracy is by physioptial restriction, there is occlusion issue, and measuring accuracy and speed are conflicting, it is difficult to be improved simultaneously.
(2) stereo-visiuon measurement: in computer vision system, utilize pick up camera or a pick up camera that two positions fix relatively two different positions, obtain two width images of same scenery from different angles simultaneously, obtain its D coordinates value by computer memory point parallax in two images. The maximum feature of stereoscopic vision method is that shooting speed is fast, it is possible to completes shooting task within less than one second time, is suitable for needing Quick Measurement occasion. But stereoscopic vision method data treatment capacity is big, and the treatment time is long, and needs the coupling carrying out two width images, when body surface gray scale and face deformationization are little, coupling and measuring accuracy can be affected.
(3) laser measurement: by a direct line of sight laser beam of a polygon lens location, by high frequency sweep, body surface is carried out sweep measurement; Application triangle law, laser beam is received by laser susceptor after reflection at body surface, the coordinate then obtaining body surface through calculating. Laser scanning can accurately provide three-dimensional environment information, and data processing is simple, affected by environment little. But cost height, there is contradictory relation in precision, range finding and scanning speed.
In recent years, the application of conventional two-dimensional image/frame of video runs into bottleneck, and RGB-D depth camera can obtain the degree of depth information of image/video frame, has the great potential solving computer vision problem in the true world. Along with the decline of sensor price and the development of computer vision technique, RGB-D depth camera (such as the Kinect of Microsoft, the Xtion etc. of Asus) achieves huge success, obtaining more research in research field, it is applied in the research topics such as three-dimensional reconstruction, gesture recognition, Object identifying, scene understanding and action recognition.
RGB-D depth camera comprises 3 pick up cameras, comprises RGB color pick up camera, RF transmitter and infrared rays COMS pick up camera. RGB-D pick up camera can obtain RGB image and depth image data simultaneously. The principle of RGB-D camera depth imaging utilizes pumped FIR laser (LightCoding) technology, wherein, RF transmitter is directed at target scene with infrared rays COMS pick up camera is angled, and before uneven transparent medium is positioned over laser transmitter camera lens, RF transmitter launches a branch of infrared rays through forming the loose spot of laser after inhomogeneous medium in scene, the infrared receptor of CMOS obtains speckle image, and uses mathematics triangle relation to be converted into depth value according to RGB-D intrinsic parameters of the camera. Final generation depth image stream, in conjunction with depth map image coordinate and pinhole imaging system principle, it is possible to obtain the three-dimensional information of the body surface measured in visual field in real time.
Comparing with other three-dimensional scanning measurements with manual measurement, the advantage of RGB-D camera depth camera is: (1) without the need to by identify other mark point just can in disposable acquisition scene three-dimensional information a little; (2) real-time of image data is good, and reconstructing three-dimensional model speed is fast; (3) the depth map resolving power that the shooting of RGB-D pick up camera obtains is higher; (4) affect little by illumination and superficial makings when obtaining degree of depth information; (5) RGB-D pick up camera is cheap, it may also be useful to cost is low; (6) user as required, can increase the quantity of RGB-D pick up camera, thus obtain more detailed information.
Summary of the invention
It is an object of the invention to provide a kind of based on the foot surfaces 3 D information obtaining method under multiple stage RGB-D pick up camera, it is fast that the method not only rebuilds speed, efficiency of measurement height, and is easy to realize, and measures cost low, it may also be useful to effective.
For achieving the above object, the technical scheme of the present invention is:
It is a kind of based on the foot surfaces 3 D information obtaining method under multiple stage RGB-D pick up camera, it is characterised in that, comprise the following steps:
(1) RGB-D pick up camera is demarcated: according to user's needs, choose the RGB-D pick up camera of at least 3 number of units amounts, carry out spatial arrangement, demarcate multiple stage RGB-D pick up camera respectively and obtain inner parameter, and taking wherein RGB-D pick up camera as benchmark, adopt the method demarcated between two to demarcate, obtain the position relation between them;
(2) reconstruction of three-dimensional model: utilize RGB-D pick up camera to obtain depth image, and according to inner calibration matrix, depth image is transformed to three-dimensional vertices, obtains three-dimensional model. Undertaken three-dimensional model splitting, denoising, obtain local foot curved surface three-dimensional model, according to the relative position between RGB-D pick up camera, carry out registration, obtain complete foot curved surface three-dimensional model;
(3) foot type parameter measurement: import in three-dimensional model process software by complete foot curved surface three-dimensional model, obtains foot curved surface three-dimensional information, extracts feature and measures corresponding foot type parameter.
Further, described step (1) comprises the following steps:
(1.1) the RGB-D pick up camera choosing different number can obtain different detailed information, user can be as required, choose the RGB-D pick up camera of at least 3 number of units amounts, field angle according to RGB-D carries out spatial arrangement, the whole foot surfaces information of combination expressed intact of the information obtained under enabling all viewpoints;
(1.2) demarcate depth camera and the color video camera of multiple stage RGB-D pick up camera respectively, obtain their inner parameter: focal length, principal point coordinate, distortion parameter;
(1.3) one of them RGB-D pick up camera selected is as fiducial cameras, other RGB-D pick up cameras carry out the demarcation of outside parameter respectively with fiducial cameras, obtain the rotation matrix R between other RGB-D pick up camera and fiducial cameras and translation matrix T, thus obtain the spatial relation between RGB-D pick up camera, by unified for the system of coordinates of multiple stage RGB-D pick up camera under the system of coordinates of fiducial cameras.
Further, described step (2) comprises the following steps:
(2.1) obtain depth data: when not pasting any mark point, directly utilize the loose spot range measurement principle of RGB-D pick up camera to obtain the degree of depth information of foot type three-dimension curved surface fast, and degree of depth information is preserved for depth image;
(2.2) reconstruction of three-dimensional model: the three-dimensional vertices according to inner calibration matrix the depth image under image coordinate system being transformed under camera system of coordinates, normal pinup picture is indicated according to apex coordinate, and according to rigid body translation matrix, three-dimensional vertices and normal pinup picture are converted to overall situation coordinate, obtain the three dimensional point cloud of foot surfaces;
(2.3) cloud segmentation, denoising is put: the three-dimensional model obtained by different RGB-D pick up camera obtains local foot curved surface three-dimensional model by dividing processing, denoising is carried out by level and smooth algorithm, the point not comprising foot information is removed, thus obtains more excellent local foot curved surface three-dimensional model;
(2.4) point cloud registering: according to the relative position transformation matrix between RGB-D pick up camera, carries out registration by the local foot curved surface three-dimensional model after process, thus obtains complete foot curved surface three-dimensional model.
Further, described step (3) comprises the following steps:
(3.1) foot type feature is extracted: by three-dimensional for complete foot curved surface data importing in three-dimensional model process software, reconstruct the complete three-dimensional model of foot, according to practical measurement requirement, extract individual features point, line, the free curved surface in local position in the three-dimensional model; (3.2) foot type parameter is measured: according to the foot type feature extracted, utilize the survey instrument in three-dimensional model process software, foot length, foot breadth, toes height, arch of foot are enclosed, internal malleolus height, external malleolus high information carry out Measurement and analysis, obtain corresponding foot type characteristic parameter, the free curved surface in local is carried out matching, obtains local curved surface model.
The advantage of the present invention: it is fast that the present invention rebuilds speed, it is possible to disposable acquisition user's foot type, need not consider to make the model reconstructed produce deviation in scanning process because user's foot moves; Collection real-time is good; RGB-D pick up camera adopts LightCoding technology, it may also be useful to be continuous illumination, it is not necessary to special sensitive materials, only needs common CMOS sensitive chip, can be cheap and effectively capture degree of depth information, therefore can greatly reduce costs; Different from traditional structured light technique, what the light source of RGB-D pick up camera got out is not the picture coding of periodically variable two dimension, but the loose spot of the laser with three-dimensional depth, the impact by illumination and article surface vein is little; Efficiency of measurement height, has very strong practicality and wide application prospect.
Accompanying drawing explanation
Fig. 1 is that in the embodiment of the present invention, foot type curved surface model diagram measured by three RGB-D pick up cameras.
Fig. 2 is the foot type parameter schematic diagram needing in the embodiment of the present invention to measure.
Wherein: 1 represents RGB-D pick up camera 1,2 represents RGB-D pick up camera 2,3 and represent RGB-D pick up camera 3(benchmark).
Embodiment
, the present invention utilizes RGB-D pick up camera to obtain the measuring method of the three-dimensional foot type information of foot and three-dimensional reconstruction model fast, comprises the following steps:
(1) RGB-D pick up camera is demarcated: according to user's needs, chooses the RGB-D pick up camera (at least 3) of different quantities, carries out spatial arrangement. Demarcate multiple stage RGB-D pick up camera respectively and obtain inner parameter, and taking wherein RGB-D pick up camera as benchmark, adopt the method demarcated between two to demarcate, obtain the position relation between them.
Specifically comprise the following steps:
(1.1) the RGB-D pick up camera choosing different number can obtain different detailed information, user can be as required, choose the RGB-D pick up camera (at least 3) of different quantities, field angle according to RGB-D carries out spatial arrangement, the whole foot surfaces information of combination expressed intact of the information obtained under enabling all viewpoints;
(1.2) demarcate depth camera and the color video camera of multiple stage RGB-D pick up camera respectively, obtain their inner parameter: focal length, principal point coordinate, distortion parameter;
(1.3) one of them RGB-D pick up camera selected is as fiducial cameras, other RGB-D pick up cameras carry out the demarcation of outside parameter respectively with fiducial cameras, obtain the rotation matrix R between other RGB-D pick up camera and fiducial cameras and translation matrix T, thus obtain the spatial relation between RGB-D pick up camera, by unified for the system of coordinates of multiple stage RGB-D pick up camera under the system of coordinates of fiducial cameras.
(2) reconstruction of three-dimensional model: utilize RGB-D pick up camera to obtain depth image, and according to inner calibration matrix, depth image is transformed to three-dimensional vertices, obtains three-dimensional model. Undertaken three-dimensional model splitting, denoising, obtain local foot curved surface three-dimensional model. According to the relative position between RGB-D pick up camera, carry out registration, obtain complete foot curved surface three-dimensional model.
Specifically comprise the following steps:
(2.1) obtain depth data: when not pasting any mark point, directly utilize the loose spot range measurement principle of RGB-D pick up camera to obtain the degree of depth information of foot type three-dimension curved surface fast, and degree of depth information is preserved for depth image;
(2.2) reconstruction of three-dimensional model: the three-dimensional vertices according to inner calibration matrix the depth image under image coordinate system being transformed under camera system of coordinates, normal pinup picture is indicated according to apex coordinate, and according to rigid body translation matrix, three-dimensional vertices and normal pinup picture are converted to overall situation coordinate, obtain the three dimensional point cloud of foot surfaces;
(2.3) cloud segmentation, denoising is put: the three-dimensional model obtained by different RGB-D pick up camera obtains local foot curved surface three-dimensional model by dividing processing, denoising is carried out by level and smooth algorithm, the point not comprising foot information is removed, thus obtains more excellent local foot curved surface three-dimensional model;
(2.4) point cloud registering: according to the relative position transformation matrix between RGB-D pick up camera, carries out registration by the local foot curved surface three-dimensional model after process, thus obtains complete foot curved surface three-dimensional model.
(3) foot type parameter measurement: complete foot curved surface three-dimensional model is imported in three-dimensional model process software, obtain foot curved surface three-dimensional information, extract feature and also measure corresponding foot type parameter, as foot length, foot breadth, toes height, arch of foot enclose, internal malleolus height, external malleolus high.
Specifically comprise the following steps:
(3.1) foot type feature is extracted: by three-dimensional for complete foot curved surface data importing in three-dimensional model process software, reconstruct the complete three-dimensional model of foot, according to practical measurement requirement, extract individual features point, line, the free curved surface in local position in the three-dimensional model; (3.2) foot type parameter is measured: according to the foot type feature extracted, utilize the survey instrument in three-dimensional model process software, foot length, foot breadth, toes height, arch of foot are enclosed, the information such as internal malleolus height, external malleolus height carry out Measurement and analysis, obtain corresponding foot type characteristic parameter, the free curved surface in local is carried out matching, obtains local curved surface model.
Below in conjunction with drawings and the specific embodiments, the invention will be further described.
1, as shown in Figure 1, the Kinectforwindows model RGB-D pick up camera that Microsoft develops selected by RGB-D pick up camera.
2, three Kinectforwindows model RGB-D pick up cameras are selected. Demarcate these three Kinectforwindows pick up cameras respectively and obtain inner parameter, and taking wherein Kinectforwindows pick up camera as benchmark, adopt the method demarcated between two to demarcate, obtain the position relation between them.
2.1 choose three Kinectforwindows model pick up cameras, it is arranged on and it is perpendicular to ground and becomes 120 �� of arrangements each other, select a suitable place for placing measurement pin so that the information obtained under three different points of view carries out combination can the whole foot surfaces information of expressed intact.
2.2 demarcate depth camera and the color video camera of three Kinectforwindows pick up cameras respectively, obtain their inner parameter: focal length, principal point coordinate, distortion parameter.
The Kinectforwindows pick up camera of 2.3 selected bottoms is as fiducial cameras, other two Kinectforwindows pick up cameras carry out the demarcation of outside parameter respectively with fiducial cameras, obtain the rotation matrix R between other Kinectforwindows pick up camera and fiducial cameras and translation matrix T, thus obtain the spatial relation between Kinectforwindows pick up camera, by unified for the system of coordinates of three Kinectforwindows pick up cameras under the system of coordinates of fiducial cameras.
3, utilize Kinectforwindows pick up camera to obtain depth image, and according to inner calibration matrix, depth image is transformed to three-dimensional vertices, obtains three-dimensional model. Undertaken three-dimensional model splitting, denoising, obtain local foot curved surface three-dimensional model. According to the relative position between Kinectforwindows pick up camera, carry out registration, obtain complete foot curved surface three-dimensional model.
3.1 when not pasting any mark point, directly utilizes the loose spot range measurement principle of Kinectforwindows pick up camera to obtain the degree of depth information of foot type three-dimension curved surface fast, and preserves degree of depth information for depth image.
3.2 three-dimensional vertices depth image under image coordinate system being transformed under camera system of coordinates according to inner calibration matrix, normal pinup picture is indicated according to apex coordinate, and according to rigid body translation matrix, three-dimensional vertices and normal pinup picture are converted to overall situation coordinate, obtain the three dimensional point cloud of foot surfaces.
3.3 three-dimensional models obtained by different K inectforwindows pick up camera obtain local foot curved surface three-dimensional model by dividing processing, denoising is carried out by level and smooth algorithm, the point not comprising foot information is removed, thus obtains more excellent local foot curved surface three-dimensional model.
3.4 according to the relative position transformation matrix between Kinectforwindows pick up camera, the local foot curved surface three-dimensional model after process is carried out registration, thus obtains complete foot curved surface three-dimensional model.
4, complete foot curved surface three-dimensional model is imported in three-dimensional model process software, obtains foot curved surface three-dimensional information, extract feature and also measure corresponding foot type parameter, as foot length, foot breadth, toes height, arch of foot enclose, internal malleolus height, external malleolus high.
4.1 by three-dimensional for complete foot curved surface data importing to, in three-dimensional model process software, reconstructing the complete three-dimensional model of foot, according to practical measurement requirement, extract individual features point, line, the free curved surface in local position in the three-dimensional model; Fig. 2 is some conventional foot type characteristic parameter definition: L1 foot length; L2 foot breadth; H1 toes height; H2 external malleolus height; H3 internal malleolus height; C1 arch of foot encloses.
4.2 according to the foot type feature extracted, utilize the survey instrument in three-dimensional model process software, foot length, foot breadth, toes height, arch of foot are enclosed, the information such as internal malleolus height, external malleolus height carry out Measurement and analysis, obtain corresponding foot type characteristic parameter, the free curved surface in local is carried out matching, obtains local curved surface model.
Being more than the better embodiment of the present invention, all changes done according to technical solution of the present invention, when the function produced does not exceed the scope of technical solution of the present invention, all belong to protection scope of the present invention.
Claims (1)
1. one kind based on the foot surfaces 3 D information obtaining method under multiple stage RGB-D pick up camera, it is characterised in that, comprise the following steps:
(1) RGB-D pick up camera is demarcated: according to user's needs, choose the RGB-D pick up camera of at least 3 number of units amounts, carry out spatial arrangement, demarcate multiple stage RGB-D pick up camera respectively and obtain inner parameter, and taking wherein RGB-D pick up camera as benchmark, adopt the method demarcated between two to demarcate, obtain the position relation between them;
(2) reconstruction of three-dimensional model: utilize RGB-D pick up camera to obtain depth image, and according to inner calibration matrix, depth image is transformed to three-dimensional vertices, obtain three-dimensional model, undertaken three-dimensional model splitting, denoising, obtain local foot curved surface three-dimensional model, according to the relative position between RGB-D pick up camera, carry out registration, obtain complete foot curved surface three-dimensional model;
(3) foot type parameter measurement: import in three-dimensional model process software by complete foot curved surface three-dimensional model, obtains foot curved surface three-dimensional information, extracts feature and measures corresponding foot type parameter;
Described step (1) comprises the following steps:
(1.1) the RGB-D pick up camera choosing different number can obtain different detailed information, user can be as required, choose the RGB-D pick up camera of at least 3 number of units amounts, field angle according to RGB-D carries out spatial arrangement, the whole foot surfaces information of combination expressed intact of the information obtained under enabling all viewpoints;
(1.2) demarcate depth camera and the color video camera of multiple stage RGB-D pick up camera respectively, obtain their inner parameter: focal length, principal point coordinate, distortion parameter;
(1.3) one of them RGB-D pick up camera selected is as fiducial cameras, other RGB-D pick up cameras carry out the demarcation of outside parameter respectively with fiducial cameras, obtain the rotation matrix R between other RGB-D pick up camera and fiducial cameras and translation matrix T, thus obtain the spatial relation between RGB-D pick up camera, by unified for the system of coordinates of multiple stage RGB-D pick up camera under the system of coordinates of fiducial cameras;
Described step (2) comprises the following steps:
(2.1) obtain depth data: when not pasting any mark point, directly utilize the loose spot range measurement principle of RGB-D pick up camera to obtain the degree of depth information of foot type three-dimension curved surface fast, and degree of depth information is preserved for depth image;
(2.2) reconstruction of three-dimensional model: the three-dimensional vertices according to inner calibration matrix the depth image under image coordinate system being transformed under camera system of coordinates, normal pinup picture is indicated according to apex coordinate, and according to rigid body translation matrix, three-dimensional vertices and normal pinup picture are converted to overall situation coordinate, obtain the three dimensional point cloud of foot surfaces;
(2.3) cloud segmentation, denoising is put: the three-dimensional model obtained by different RGB-D pick up camera obtains local foot curved surface three-dimensional model by dividing processing, denoising is carried out by level and smooth algorithm, the point not comprising foot information is removed, thus obtains more excellent local foot curved surface three-dimensional model;
(2.4) point cloud registering: according to the relative position transformation matrix between RGB-D pick up camera, carries out registration by the local foot curved surface three-dimensional model after process, thus obtains complete foot curved surface three-dimensional model;
Described step (3) comprises the following steps:
(3.1) foot type feature is extracted: by three-dimensional for complete foot curved surface data importing in three-dimensional model process software, reconstruct the complete three-dimensional model of foot, according to practical measurement requirement, extract individual features point, line, the free curved surface in local position in the three-dimensional model; (3.2) foot type parameter is measured: according to the foot type feature extracted, utilize the survey instrument in three-dimensional model process software, foot length, foot breadth, toes height, arch of foot are enclosed, internal malleolus height, external malleolus high information carry out Measurement and analysis, obtain corresponding foot type characteristic parameter, the free curved surface in local is carried out matching, obtains local curved surface model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410367191.5A CN104126989B (en) | 2014-07-30 | 2014-07-30 | A kind of based on the foot surfaces 3 D information obtaining method under multiple stage RGB-D pick up camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410367191.5A CN104126989B (en) | 2014-07-30 | 2014-07-30 | A kind of based on the foot surfaces 3 D information obtaining method under multiple stage RGB-D pick up camera |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104126989A CN104126989A (en) | 2014-11-05 |
| CN104126989B true CN104126989B (en) | 2016-06-01 |
Family
ID=51800039
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410367191.5A Active CN104126989B (en) | 2014-07-30 | 2014-07-30 | A kind of based on the foot surfaces 3 D information obtaining method under multiple stage RGB-D pick up camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104126989B (en) |
Families Citing this family (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105029831A (en) * | 2015-08-28 | 2015-11-11 | 师汉民 | Three-dimensional foot shoe tree scanner and scanning modules |
| CN105455308B (en) * | 2015-11-17 | 2018-07-20 | 深圳大学 | A kind of foot type three-dimensional vision information system |
| CN106204727A (en) * | 2016-07-11 | 2016-12-07 | 北京大学深圳研究生院 | The method and device that a kind of foot 3-D scanning is rebuild |
| CN106203390B (en) * | 2016-07-22 | 2019-09-24 | 杭州视氪科技有限公司 | A kind of intelligent blind auxiliary system |
| CN108182702B (en) * | 2016-12-08 | 2020-06-30 | 北京物语科技有限公司 | Real-time three-dimensional modeling method and system based on depth image acquisition equipment |
| CN106652026A (en) * | 2016-12-23 | 2017-05-10 | 安徽工程大学机电学院 | Three-dimensional space automatic calibration method based on multi-sensor fusion |
| CN106960470B (en) * | 2017-04-05 | 2022-04-22 | 未来科技（襄阳）有限公司 | Three-dimensional point cloud curved surface reconstruction method and device |
| CN106840602A (en) * | 2017-04-20 | 2017-06-13 | 山东大学 | A kind of system for following the trail of wave feature, method and application |
| KR101899064B1 (en) * | 2017-05-17 | 2018-09-17 | 문광섭 | Personal customized assembly-insole making method by the foot size measurement using a smart device |
| CN107341844A (en) * | 2017-06-21 | 2017-11-10 | 上海大学 | A kind of real-time three-dimensional people's object plotting method based on more Kinect |
| CN107578019B (en) * | 2017-09-13 | 2020-05-12 | 河北工业大学 | Gait recognition system and method based on visual sense and tactile sense fusion |
| CN107767456A (en) * | 2017-09-22 | 2018-03-06 | 福州大学 | A kind of object dimensional method for reconstructing based on RGB D cameras |
| CN109559349B (en) * | 2017-09-27 | 2021-11-09 | 虹软科技股份有限公司 | Method and device for calibration |
| CN107869967A (en) * | 2017-11-02 | 2018-04-03 | 渭南领智三维科技有限公司 | A kind of human foot quick three-dimensional scan method |
| CN108010036B (en) * | 2017-11-21 | 2020-01-21 | 江南大学 | Object symmetry axis detection method based on RGB-D camera |
| CN108305286B (en) * | 2018-01-25 | 2021-09-07 | 哈尔滨工业大学深圳研究生院 | Color coding-based multi-view stereoscopic vision foot type three-dimensional measurement method, system and medium |
| CN109199392A (en) * | 2018-08-09 | 2019-01-15 | 重庆邮电大学 | A kind of infant foot bottom image data acquiring and 3D shape modeling method |
| CN110838136B (en) * | 2018-08-15 | 2023-06-20 | 上海脉沃医疗科技有限公司 | Image calibration method based on RGBD depth camera |
| CN115500582B (en) * | 2022-08-17 | 2024-03-22 | 上海科技大学 | Foot three-dimensional contour acquisition system |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6735547B1 (en) * | 2000-10-06 | 2004-05-11 | Evangelos A. Yfantis | Method and apparatus for determining the size and shape of a foot |
| JP5417654B2 (en) * | 2008-03-26 | 2014-02-19 | 株式会社アサヒコーポレーション | Center of gravity analysis method |
| CN101866497A (en) * | 2010-06-18 | 2010-10-20 | 北京交通大学 | Binocular stereo vision based intelligent three-dimensional human face rebuilding method and system |
| CN102525034B (en) * | 2011-11-22 | 2015-04-15 | 中国科学院合肥物质科学研究院 | Foot type parameter measuring device and measuring method |
| TWM441358U (en) * | 2012-03-22 | 2012-11-21 | Jung-Tang Huang | System for measurement of three-dimensional foot shape |
| CN103106688B (en) * | 2013-02-20 | 2016-04-27 | 北京工业大学 | Based on the indoor method for reconstructing three-dimensional scene of double-deck method for registering |
| CN103279987B (en) * | 2013-06-18 | 2016-05-18 | 厦门理工学院 | Object quick three-dimensional modeling method based on Kinect |
| CN103559736B (en) * | 2013-11-11 | 2016-06-15 | 程志全 | The unmarked three-dimensional real-time capture system of performing artist |
| CN103646394B (en) * | 2013-11-26 | 2016-08-17 | 福州大学 | A kind of mixing vision system calibration method based on Kinect video camera |
-
2014
- 2014-07-30 CN CN201410367191.5A patent/CN104126989B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN104126989A (en) | 2014-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104126989B (en) | A kind of based on the foot surfaces 3 D information obtaining method under multiple stage RGB-D pick up camera | |
| CN103971409B (en) | Measuring method for foot three-dimensional foot-type information and three-dimensional reconstruction model by means of RGB-D camera | |
| CN107767442B (en) | Foot type three-dimensional reconstruction and measurement method based on Kinect and binocular vision | |
| Bartol et al. | A review of body measurement using 3D scanning | |
| CN107945268B (en) | A kind of high-precision three-dimensional method for reconstructing and system based on binary area-structure light | |
| US10347031B2 (en) | Apparatus and method of texture mapping for dental 3D scanner | |
| CN105608737B (en) | A kind of human foot three-dimensional rebuilding method based on machine learning | |
| CN105547189B (en) | High-precision optical method for three-dimensional measurement based on mutative scale | |
| CN103535960B (en) | Human body three-dimensional measurement method based on digital images | |
| CN101887477B (en) | Method for customizing digitalized shoe trees according to a plurality of images of foot shapes | |
| CN108151671A (en) | A kind of 3 D digital imaging sensor, 3 D scanning system and its scan method | |
| CN102157013A (en) | System for fully automatically reconstructing foot-type three-dimensional surface from a plurality of images captured by a plurality of cameras simultaneously | |
| CN107869967A (en) | A kind of human foot quick three-dimensional scan method | |
| CN107860337B (en) | Structured light three-dimensional reconstruction method and device based on array camera | |
| CN102032878A (en) | Accurate on-line measurement method based on binocular stereo vision measurement system | |
| CN108665535A (en) | A kind of three-dimensional structure method for reconstructing and system based on coding grating structured light | |
| CN102779354B (en) | Three-dimensional reconstruction method for traditional Chinese medicine inspection information surface based on photometric stereo technology | |
| CN204132561U (en) | Three-dimensional foot scanning means | |
| CN105212436B (en) | The measuring system and measuring method of non-contact 3-D laser foot type | |
| CN104665107B (en) | A kind of vola three dimensional data collection processing system and data acquisition treatment method | |
| Novak et al. | Three-dimensional foot scanning system with a rotational laser-based measuring head | |
| TW200939053A (en) | Apparatus and method for rapidly measuring 3-dimensional foot sizes from multi-images | |
| Sansoni et al. | 3-D optical measurements in the field of cultural heritage: the case of the Vittoria Alata of Brescia | |
| Niu et al. | 3d foot reconstruction based on mobile phone photographing | |
| CN109815830A (en) | A method of obtaining foot information in the slave photo based on machine learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |