CN105631891A - Human face collection system and method - Google Patents
Human face collection system and method Download PDFInfo
- Publication number
- CN105631891A CN105631891A CN201610096506.6A CN201610096506A CN105631891A CN 105631891 A CN105631891 A CN 105631891A CN 201610096506 A CN201610096506 A CN 201610096506A CN 105631891 A CN105631891 A CN 105631891A
- Authority
- CN
- China
- Prior art keywords
- image
- image acquisition
- face
- array
- acquisition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10141—Special mode during image acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Image Input (AREA)
Abstract
The invention discloses a human face collection system, and the system comprises a support, a light source, an image collection array, and a control system. The light source and the image collection array are disposed on the support, and the image collection array comprises a first image collection group which is used for collecting a first depth image and comprises a plurality of first image collection units, wherein the plurality of first image collection units are used for collecting a first image from a plurality of angles; a second image collection group which is used for collecting a second depth image and comprises a plurality of second image collection units, wherein the plurality of second image collection units are used for collecting a second image from a plurality of angles. The control system is connected with the light source and the image collection array, and is used for controlling the plurality of first image collection units to collect the first image at the same time and controlling the plurality of second image collection units to collect the second image at the same time. The system is advantageous in that the system provides abundant depth and color images for human face three-dimensional reconstruction; the data precision is high; the functions are abundant; and the collection efficiency is high.
Description
Technical field
The invention belongs to three-dimensional reconstruction, digital image processing field, be specifically related to a kind of face acquisition system and face acquisition method.
Background technology
The facial characteristics of people contains very abundant information, is the important way of identification and emotional expression. Emotion that human face is contained and psychographic information, it is also possible to for the field such as artificial intelligence, Cognitive Science. Human eye is particularly sensitive for face detail, to such an extent as to some trickle distortions, all can be caught in, and therefore face three-dimensional reconstruction is one and is not only rich in potentiality but also contain the work of challenge.
Along with face three-dimensional reconstruction is theoretical and the progress of method, for the requirement of acquisition system also in being continually changing. Achieve based on the face three-dimensional reconstruction of stereoscopic vision in recent years and develop on a large scale very much, reconstruction precision reaches submillimeter level other. Simultaneously, requirements at the higher level be there has also been for building of acquisition system. Three-dimensional reconstruction based on stereoscopic vision uses multiple stage camera shooting Same Scene, by calculating spatial point parallax in different images, reduces the space coordinates of these points. Complete procedure includes Image Acquisition, camera calibration, feature extraction, Stereo matching, three-dimensional reconstruction and post processing etc. But not high for the data precision of face 3D image reconstruction in correlation technique, data acquisition efficiency is low.
Summary of the invention
It is contemplated that at least solve one of above-mentioned technical problem.
For this, first purpose of the present invention is in that to propose a kind of face acquisition system.
Second purpose of the present invention is in that to propose a kind of face acquisition method.
To achieve these goals, the embodiment of one aspect of the present invention discloses a kind of face acquisition system, including: support, light source, image acquisition array and control system, described light source and described image acquisition array are respectively mounted on the bracket, described image acquisition array includes: the first image acquisition group, described first image acquisition group is used for gathering the first depth image, described first image acquisition group includes multiple first image acquisition units, and multiple described first image acquisition units are used for from multiple angle acquisition the first images; Second image acquisition group, described second image acquisition group is used for gathering the second depth image, and described second image acquisition group includes multiple second image acquisition units, and multiple described second image acquisition units are used for from multiple angle acquisition the second images; Described control system and described light source and described image acquisition array are all connected with, and are used for controlling multiple described first image acquisition units and gather described first image and multiple described second image acquisition units gathers described second image simultaneously simultaneously.
A kind of face acquisition system according to embodiments of the present invention, provides the abundant degree of depth and coloured image for work such as face three-dimensional reconstructions, and data precision height, feature richness, collecting efficiency are high.
It addition, a kind of face acquisition system according to the above embodiment of the present invention, it is also possible to there is following additional technical characteristic:
Further, described light source includes multiple light-emitting device, described support includes base, connecting rod and spherical source installing rack, described spherical source installing rack and described base are connected by described connecting rod, the packet of multiple described light-emitting devices is arranged on described spherical source installing rack, and described spherical source installing rack is rotatable in described connecting rod.
Further, often organizing described light-emitting device is 5, often organizes described light-emitting device and fixedly mounts in a criss-cross fashion on the sphere of described spherical source installing rack.
Further, the position that gathers of described first image includes the hair of gathered person, and the position that gathers of described second image includes the face of gathered person, and the collection picture depth of described first image is less than the collection picture depth of described second image.
Further, described first image acquisition units is Kinect1 camera, and described second image acquisition units is Flea3 camera.
Further, described control system includes server and control circuit, described light source and described image acquisition array and is all connected with described control circuit array, and described server is connected with described control circuit.
To achieve these goals, the embodiment of one aspect of the present invention discloses a kind of face acquisition method, including above-mentioned face acquisition system, and comprise the following steps: A: gathered person enters man face image acquiring place, described image acquisition array is set to non-toggle pattern; B: adjust the sampling depth of described first image, shoots described first image and stores; C: multiple described second image acquisition units are disposed as trigger mode, described control system controls described light source and multiple described second image acquisition units camera gathers described second image simultaneously and stores.
A kind of face acquisition method method according to embodiments of the present invention, provides the abundant degree of depth and coloured image for work such as face three-dimensional reconstructions, and data precision height, feature richness, collecting efficiency are high.
The additional aspect of the present invention and advantage will part provide in the following description, and part will become apparent from the description below, or is recognized by the practice of the present invention.
Accompanying drawing explanation
Above-mentioned and/or the additional aspect of the present invention and advantage are from conjunction with will be apparent from easy to understand the accompanying drawings below description to embodiment, wherein:
Fig. 1 is the face acquisition system structural representation of one embodiment of the invention;
Fig. 2 is the flow chart of the face acquisition method of one embodiment of the invention.
Detailed description of the invention
Being described below in detail embodiments of the invention, the example of described embodiment is shown in the drawings, and wherein same or similar label represents same or similar element or has the element of same or like function from start to finish. The embodiment described below with reference to accompanying drawing is illustrative of, and is only used for explaining the present invention, and is not considered as limiting the invention.
In describing the invention, it will be appreciated that, term " " center ", " longitudinal direction ", " transverse direction ", " on ", D score, " front ", " afterwards ", " left side ", " right side ", " vertically ", " level ", " top ", " end ", " interior ", orientation or the position relationship of the instruction such as " outward " are based on orientation shown in the drawings or position relationship, it is for only for ease of the description present invention and simplifies description, rather than the device of instruction or hint indication or element must have specific orientation, with specific azimuth configuration and operation, therefore it is not considered as limiting the invention. additionally, term " first ", " second " are only for descriptive purposes, and it is not intended that indicate or hint relative importance.
In describing the invention, it is necessary to explanation, unless otherwise clearly defined and limited, term " installation ", " being connected ", " connection " should be interpreted broadly, for instance, it is possible to it is fixing connection, it is also possible to be removably connect, or connect integratedly; Can be mechanically connected, it is also possible to be electrical connection; Can be joined directly together, it is also possible to be indirectly connected to by intermediary, it is possible to be the connection of two element internals. For the ordinary skill in the art, it is possible to concrete condition understands above-mentioned term concrete meaning in the present invention.
With reference to as explained below and accompanying drawing, it will be clear that these and other aspects of embodiments of the invention. Describe at these and in accompanying drawing, specifically disclose some particular implementation in embodiments of the invention, representing some modes of the principle implementing embodiments of the invention, but it is to be understood that the scope of embodiments of the invention is not limited. On the contrary, all changes within the scope of embodiments of the invention include falling into attached claims spirit and intension, amendment and equivalent.
Below in conjunction with accompanying drawing, face acquisition system according to embodiments of the present invention is described.
Refer to Fig. 1, a kind of face acquisition system, including: support, light source, image acquisition array and control system. Light source and image acquisition array are installed on support. Image acquisition array includes: the first image acquisition group, first image acquisition group is used for gathering the first depth image, first image acquisition group includes multiple dispersed and distributed the first image acquisition units on support, and multiple first image acquisition units are used for from multiple angle acquisition the first images; Second image acquisition group, the second image acquisition group is used for gathering the second depth image, and the second image acquisition group includes the second image acquisition units of multiple dispersed and distributed, and multiple second image acquisition units are used for from multiple angle acquisition the second images; Control system and light source and image acquisition array are all connected with, and are used for controlling multiple first image acquisition units and gather the first image and multiple second image acquisition units gathers the second image simultaneously simultaneously.
In one embodiment of the invention, light source includes multiple light-emitting device, and in this embodiment, light-emitting device is LED. Support includes base, connecting rod and spherical source installing rack, spherical source installing rack and base are connected by connecting rod, spherical source installing rack is rotatable in connecting rod, the packet of multiple light-emitting devices is arranged on spherical source installing rack, the light of multiple angles is provided to irradiate gathered person by rotating of spherical source installing rack, it is to avoid light dead angle to occur thus affecting shooting effect.
In one embodiment of the invention, often organize described light-emitting device and fixedly mount on the sphere of described spherical source installing rack in a criss-cross fashion, i.e. one, centre position light-emitting device, respectively arranging a light-emitting device on the direction, upper and lower, left and right of the light-emitting device in centre position, 5 light-emitting devices form criss-cross construction.
In one embodiment of the invention, the position that gathers of the first image is the hair of gathered person, gathers 640 �� 480 depth images. The position that gathers of the second image is the face of gathered person, becomes 4000 �� 3000 coloured images under illumination condition.
In one embodiment of the invention, the first image acquisition units is Kinect1 camera, gathers image resolution ratio relatively low, but can directly obtain depth information, it is possible to for rebuilding the part that the textures such as hair lack and required precision is not high. Second image acquisition units is Flea3 camera, gathers image resolution ratio higher, and cooperated with LED has Lighting information, it is possible to be used for rebuilding high accuracy mask.
In one embodiment of the invention, control system includes server and control circuit, light source and image acquisition array and is all connected with described control circuit array, and server is connected with described control circuit.
Specifically, control circuit plate divides mainboard and from plate, and mainboard passes through Serial Port Line Connection Service device, receives and triggers configuration file and trigger command. Mainboard is connected by network data line with from plate and between plate, and every piece of mainboard can control polylith from plate, and every piece can control at most 8 groups of LED and 4 Flea3 cameras trigger from plate.
Acquisition system comprises 3 station servers, and wherein server B 1/B2 respectively connects 5 Flea3, and server A connects 3 Kinect1. Every station server carries a set of collection terminal program, is responsible for the camera controlling to connect; There is a station server to carry and control end program, be responsible for controlling all collection terminals.
Below in conjunction with accompanying drawing, face acquisition method according to embodiments of the present invention is described.
Step A: gathered person enters acquisition system, is set to non-toggle pattern by camera, opens all-round display, and whether observation face location is suitable and is adjusted.
Step B: control Kinect1 collected by camera depth map, be stored in home server.
Step C: Flea3 camera is set to trigger mode, carries out darkening according to gathering. Control circuit buttress controls LED and Flea3 camera according to the triggering configuration file imported to be triggered simultaneously, gathers 14 groups of left images. These images are first deposited such as internal memory, and after storage, control circuit plate stops sending and triggers signal, LED and camera and stop triggering, and image is written into hard disk afterwards.
Step D: gathered person leaves acquisition system, and next round collection starts.
It addition, other of the face acquisition system of the embodiment of the present invention and face acquisition method is constituted and effect is all known for a person skilled in the art, in order to reduce redundancy, do not repeat.
In the description of this specification, specific features, structure, material or feature that the description of reference term " embodiment ", " some embodiments ", " example ", " concrete example " or " some examples " etc. means in conjunction with this embodiment or example describe are contained at least one embodiment or the example of the present invention. In this manual, the schematic representation of above-mentioned term is not necessarily referring to identical embodiment or example. And, the specific features of description, structure, material or feature can combine in an appropriate manner in any one or more embodiments or example.
Although an embodiment of the present invention has been shown and described, it will be understood by those skilled in the art that: these embodiments can being carried out multiple change, amendment, replacement and modification when without departing from principles of the invention and objective, the scope of the present invention is by claim and equivalency thereof.
Claims (7)
1. a face acquisition system, it is characterised in that including: support, light source, image acquisition array and control system, described light source and described image acquisition array are respectively mounted on the bracket, and described image acquisition array includes:
First image acquisition group, described first image acquisition group is used for gathering the first depth image, and described first image acquisition group includes multiple first image acquisition units, and multiple described first image acquisition units are used for from multiple angle acquisition the first images;
Second image acquisition group, described second image acquisition group is used for gathering the second depth image, and described second image acquisition group includes multiple second image acquisition units, and multiple described second image acquisition units are used for from multiple angle acquisition the second images;
Described control system and described light source and described image acquisition array are all connected with, and are used for controlling multiple described first image acquisition units and gather described first image and multiple described second image acquisition units gathers described second image simultaneously simultaneously.
2. face acquisition system according to claim 1, it is characterized in that, described light source includes multiple light-emitting device, described support includes base, connecting rod and spherical source installing rack, described spherical source installing rack and described base are connected by described connecting rod, the packet of multiple described light-emitting devices is arranged on described spherical source installing rack, and described spherical source installing rack is rotatable in described connecting rod.
3. face acquisition system according to claim 2, it is characterised in that often organizing described light-emitting device is 5, often organizes described light-emitting device and fixedly mounts in a criss-cross fashion on the sphere of described spherical source installing rack.
4. face acquisition system according to claim 1, it is characterized in that, the position that gathers of described first image includes the hair of gathered person, the position that gathers of described second image includes the face of gathered person, and the collection picture depth of described first image is less than the collection picture depth of described second image.
5. face acquisition system according to claim 1, it is characterised in that described first image acquisition units is Kinect1 camera, described second image acquisition units is Flea3 camera.
6. face acquisition system according to claim 1, it is characterised in that described control system includes server and control circuit, described light source and described image acquisition array and is all connected with described control circuit array, and described server is connected with described control circuit.
7. a face acquisition method, it is characterised in that include the arbitrary described face acquisition system of claim 1 to 6, and comprise the following steps:
A: gathered person enters man face image acquiring place, is set to non-toggle pattern by described image acquisition array;
B: adjust the sampling depth of described first image, shoots described first image and stores;
C: multiple described second image acquisition units are disposed as trigger mode, described control system controls described light source and multiple described second image acquisition units camera gathers described second image simultaneously and stores.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610096506.6A CN105631891B (en) | 2016-02-22 | 2016-02-22 | Face acquisition system and face acquisition method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610096506.6A CN105631891B (en) | 2016-02-22 | 2016-02-22 | Face acquisition system and face acquisition method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105631891A true CN105631891A (en) | 2016-06-01 |
| CN105631891B CN105631891B (en) | 2018-12-11 |
Family
ID=56046777
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610096506.6A Active CN105631891B (en) | 2016-02-22 | 2016-02-22 | Face acquisition system and face acquisition method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105631891B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106604016A (en) * | 2017-01-26 | 2017-04-26 | 上海图漾信息科技有限公司 | Stereoscopic video capture system |
| CN109871859A (en) * | 2018-09-28 | 2019-06-11 | 北京矩视智能科技有限公司 | One kind automatically generating training set of images system |
| US10935376B2 (en) | 2018-03-30 | 2021-03-02 | Koninklijke Philips N.V. | System and method for 3D scanning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101949721A (en) * | 2009-12-22 | 2011-01-19 | 中国矿业大学(北京) | Method for measuring coal bunker material level based on laser and binocular vision and device thereof |
| US20140177942A1 (en) * | 2012-12-26 | 2014-06-26 | Industrial Technology Research Institute | Three dimensional sensing method and three dimensional sensing apparatus |
| CN105023275A (en) * | 2015-07-14 | 2015-11-04 | 清华大学 | Super-resolution light field acquisition device and three-dimensional reconstruction method thereof |
| CN105120257A (en) * | 2015-08-18 | 2015-12-02 | 宁波盈芯信息科技有限公司 | Vertical depth sensing device based on structured light coding |
-
2016
- 2016-02-22 CN CN201610096506.6A patent/CN105631891B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101949721A (en) * | 2009-12-22 | 2011-01-19 | 中国矿业大学(北京) | Method for measuring coal bunker material level based on laser and binocular vision and device thereof |
| US20140177942A1 (en) * | 2012-12-26 | 2014-06-26 | Industrial Technology Research Institute | Three dimensional sensing method and three dimensional sensing apparatus |
| CN105023275A (en) * | 2015-07-14 | 2015-11-04 | 清华大学 | Super-resolution light field acquisition device and three-dimensional reconstruction method thereof |
| CN105120257A (en) * | 2015-08-18 | 2015-12-02 | 宁波盈芯信息科技有限公司 | Vertical depth sensing device based on structured light coding |
Non-Patent Citations (3)
| Title |
|---|
| XUN CAO等: "《Vision Field Capture for Advanced 3DTV Applications》", 《2011 VISUAL COMMUNICATIONS AND IMAGE PROCESSING (VCIP)》 * |
| 李忠炤等: "《自由视点视频采集及其传输系统研究》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 李红波等: "《基于Kinect深度图像的人体识别分析》", 《数字通信》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106604016A (en) * | 2017-01-26 | 2017-04-26 | 上海图漾信息科技有限公司 | Stereoscopic video capture system |
| US10935376B2 (en) | 2018-03-30 | 2021-03-02 | Koninklijke Philips N.V. | System and method for 3D scanning |
| US11969231B2 (en) | 2018-03-30 | 2024-04-30 | Koninklijke Philips N.V. | System and method for 3D scanning |
| CN109871859A (en) * | 2018-09-28 | 2019-06-11 | 北京矩视智能科技有限公司 | One kind automatically generating training set of images system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105631891B (en) | 2018-12-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106797460B (en) | The reconstruction of 3 D video | |
| CN108259921B (en) | Multi-angle live broadcast system based on scene switching and switching method | |
| CN107610185A (en) | A kind of fisheye camera fast calibration device and scaling method | |
| CN105023275B (en) | Super-resolution optical field acquisition device and its three-dimensional rebuilding method | |
| CN107438152B (en) | Method and system for quickly positioning and capturing panoramic target by motion camera | |
| CN105744239B (en) | More focal length lens ultrahigh resolutions linkage imaging devices | |
| CN101872243B (en) | System and method for realizing 360-degree panoramic play following real space direction | |
| CN205693769U (en) | A kind of motion cameras positioning capturing quick to panorama target system | |
| CN105631891A (en) | Human face collection system and method | |
| CN104702871A (en) | Unmanned plane projection displaying method, unmanned plane projection displaying system and unmanned plane projection displaying device | |
| CN104079916A (en) | Panoramic three-dimensional visual sensor and using method | |
| CN108259787B (en) | Panoramic video switching device and method | |
| CN206609424U (en) | Microlight-type variable-angle aviation oblique photograph system | |
| CN207198919U (en) | Camera array three-dimensional reconstruction apparatus and system | |
| CN105892030A (en) | Internet communication based digital microscope and interaction method of digital microscope | |
| CN205982978U (en) | Three -dimensional panorama shooting equipment | |
| CN107896301A (en) | Panoramic scanning device and panoramic scanning method for movie and television play | |
| CN205987113U (en) | Modularization panoramic camera | |
| CN108713317A (en) | Image acquisition device | |
| CN209085612U (en) | A kind of field 3 D image acquring system | |
| CN110977970A (en) | Image recognition system and recognition method thereof | |
| CN109374037A (en) | A kind of image automatic detection device | |
| CN115088014A (en) | Method and system for real social contact by using virtual scene | |
| CN113870163A (en) | Video fusion method and device based on three-dimensional scene, storage medium and electronic device | |
| CN206272761U (en) | A kind of panorama Synchronous camera head assembling device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |