CN108965696B - Multi-view reconfigurable face data acquisition system - Google Patents

Multi-view reconfigurable face data acquisition system Download PDF

Info

Publication number
CN108965696B
CN108965696B CN201810686483.3A CN201810686483A CN108965696B CN 108965696 B CN108965696 B CN 108965696B CN 201810686483 A CN201810686483 A CN 201810686483A CN 108965696 B CN108965696 B CN 108965696B
Authority
CN
China
Prior art keywords
support
degrees
cameras
layer
reconfigurable
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
Application number
CN201810686483.3A
Other languages
Chinese (zh)
Other versions
CN108965696A (en
Inventor
孙哲南
张堃博
赫然
谭铁牛
申振腾
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianjin Zhongke Intelligent Identification Co ltd
Original Assignee
Tianjin Zhongke Intelligent Identification Industry Technology Research Institute Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tianjin Zhongke Intelligent Identification Industry Technology Research Institute Co ltd filed Critical Tianjin Zhongke Intelligent Identification Industry Technology Research Institute Co ltd
Priority to CN201810686483.3A priority Critical patent/CN108965696B/en
Publication of CN108965696A publication Critical patent/CN108965696A/en
Application granted granted Critical
Publication of CN108965696B publication Critical patent/CN108965696B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/90Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F16ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
    • F16MFRAMES, CASINGS OR BEDS OF ENGINES, MACHINES OR APPARATUS, NOT SPECIFIC TO ENGINES, MACHINES OR APPARATUS PROVIDED FOR ELSEWHERE; STANDS; SUPPORTS
    • F16M11/00Stands or trestles as supports for apparatus or articles placed thereon ; Stands for scientific apparatus such as gravitational force meters
    • F16M11/02Heads
    • F16M11/04Means for attachment of apparatus; Means allowing adjustment of the apparatus relatively to the stand
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/61Control of cameras or camera modules based on recognised objects
    • H04N23/611Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/64Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/698Control of cameras or camera modules for achieving an enlarged field of view, e.g. panoramic image capture
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/70Circuitry for compensating brightness variation in the scene
    • H04N23/74Circuitry for compensating brightness variation in the scene by influencing the scene brightness using illuminating means

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • General Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Image Input (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention discloses a multi-view reconfigurable face data acquisition system, which comprises background cloth, a seat and a hemispherical support, wherein the hemispherical support comprises six support layers formed by arranging weft threads and six support rod layers formed by arranging warp threads, a preset number of cameras are uniformly arranged on each support layer, and the cameras are connected with a computer through interfaces; the camera and the light sources are connected with the computer through a control subsystem, and the control subsystem is used for controlling all the cameras to synchronously capture all-dimensional face images and the light sources to do circulating motion. The invention has various illumination, the number of light sources can be automatically adjusted and replaced, the background can be adjusted, and the omnibearing coverage of the face is realized through position correction.

Description

Multi-view reconfigurable face data acquisition system
Technical Field
The invention relates to the technical field of face data acquisition, in particular to a multi-view reconfigurable face data acquisition system.
Background
In recent years, the biometric identification technology plays an important role in identity authentication, national security maintenance, personal information security, aviation security, rescue material distribution, medical treatment and the like, and is increasingly widely applied. Compared with other biological feature recognition technologies such as fingerprint recognition, iris recognition and voice recognition, the face recognition has the advantages of naturalness, imperceptibility and the like, and is widely applied due to the characteristics of high detection rate, high adaptability, convenience in acquisition and the like.
The face recognition needs to utilize stable face features, and corresponding algorithms include methods based on LDA, PCA and the like. With the continuous optimization and perfection of the face recognition algorithm, the face recognition accuracy can reach more than 99%, various devices based on face recognition are also put into the market in succession, and the development of the intelligent society is greatly promoted. However, face recognition is easily affected by illumination, visual angle, expression, blocking objects and the like, and improving algorithm robustness and accuracy under complex conditions is an important direction for face recognition research. This requires a face database to optimize the algorithm in complex situations.
Because single camera collection is influenced seriously by single factor, the present face data collection equipment is mostly a multi-camera system. The complicated multi-camera face acquisition system has the disadvantages of immobility and mobility, the immobility system is difficult to disassemble and assemble and poor in portability, and the non-remote acquisition cannot be realized; although the mobile system has strong portability, the mobile system has single function and poor universality and expandability. In addition, they can not fully cover the view angle of the human face, and the data of the human face is not rich enough.
Disclosure of Invention
The invention aims to provide a multi-view reconfigurable face data acquisition system aiming at the technical defects in the prior art.
The technical scheme adopted for realizing the purpose of the invention is as follows:
a multi-view reconfigurable face data acquisition system comprises background cloth, seats and a hemispherical support, wherein the hemispherical support comprises six support layers formed by weft arrangement and six support rod layers formed by warp arrangement, a preset number of cameras are uniformly installed on each support layer, and the cameras are connected with a computer through interfaces; the camera and the light sources are connected with the computer through a control subsystem, and the control subsystem is used for controlling all the cameras to synchronously capture all-dimensional face images and the light sources to do circulating motion.
The support layer has 5 cameras from last to first support layer down, and second support layer, six layers of support layer respectively have 9 cameras, third support layer, four support layers, five support layers respectively have 13 cameras.
The whole bracket is of a profile structure, and each section of the profile of the bracket layer is connected through a nonstandard positioning angle piece and a fixed angle plate through a bolt and a slide block nut; and the positioning angle piece is provided with a positioning threaded hole and is connected with the camera holder through a stud.
The branch layer has 6 branches on every layer, the symmetric distribution, branch pass through the oblique angle connecting piece with the leg joint.
The bottom layer bracket of the bracket is connected with at least 6 hoof feet through a slide block nut; the support has 6 support legs, one end of the support is provided with a threaded hole and connected with a hoof foot, the other end of the support is connected with the fourth support layer through a standard angle piece, and the support legs are spaced at 36 degrees.
The camera is fixed on the camera holder, the pose can be adjusted, and the front, upper and lower full coverage of the collected person can be realized at 62 degrees.
The light source is a plane uniform light source, the brightness and the chromaticity are adjustable, and the light source is fixed on a light source holder and the pose is adjustable; the light source holder is fixed on the corresponding sectional materials at the front, rear, left, right, upper, front upper and front lower positions by using a human face as the center through a double-end stud and a T-shaped nut.
The background cloth is arranged behind the hemispherical support through a background support and is hung on the background support and can be manually folded and unfolded through a zipper.
The height of the seat can be adjusted to adapt to different heights, and a headrest with adjustable height is installed to ensure that the face is in the center of sphere.
The invention has the following characteristics:
1. the method can be applied to complex real human faces. The illumination is various, the number of light sources can be automatically adjusted and replaced, the background can be adjusted, and the omnibearing coverage of the face yaw angle (-90 degrees) and the pitch angle (-30-45 degrees) is realized through the position correction;
2. and (4) reconfigurable modular design. (1) In the aspect of mechanical design: the mechanical structure can be quickly disassembled and assembled, can be spliced into required radian and radius to form a panoramic ball, has the capacity of remote acquisition, and meets the requirements of a large number of data acquisition tasks; (2) the collection equipment aspect: cameras and light sources can be added, reduced and replaced according to requirements, and universal interfaces, angles and positions can be adjusted at will (the requirements of various cameras such as area arrays, three-dimensional cameras, light fields and the like are met); (3) acquisition architecture: the camera is mainly connected with a PCI-E expansion card, the camera can be continuously overlapped theoretically through expansion of a computer (PCI-E synchronous expansion), and a synchronizer is combined with an optimized parallel synchronous acquisition algorithm to control an acquisition synchronization error within 20 ms.
3. The universal expansibility is strong. The human face acquisition system can be used for acquiring human faces, objects, human body and multi-person interaction, image and video acquisition, three-dimensional reconstruction, tracking, recognition and other research and application. The height of the collected object is 1.0m-2.2m, the face size is 87mm x 87mm-593mm x 694mm, and the collected object is 50mm x 50mm-1380mm x 2200 mm.
The method is oriented to a complex real face application scene, and can realize full coverage of the face of the person to be collected; the collected human face database has great significance for optimizing and applying a human face recognition algorithm; due to the adoption of the reconfigurable modular design, the disassembly and assembly are convenient, the expandability is strong, and the transportation is convenient.
Drawings
FIG. 1 is a schematic front view of a multi-view reconfigurable face data acquisition system;
FIG. 2 is a side view schematic diagram of a multi-view reconfigurable face data acquisition system;
FIG. 3 is a control schematic of the present invention;
fig. 4 is a face image acquired under different light sources and viewing angles.
Detailed Description
The invention is described in further detail below with reference to the figures and specific examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1 to 4, a multi-view reconfigurable face data acquisition system includes:
the camera comprises a hemispherical support 9, a camera 3, a light source 10, a background 11, a seat 5 and a control subsystem 8, wherein the support 9 comprises a semicircular support layer 1 for supporting the camera 3, a bottom support, a support rod layer 2 and peripheral support legs 4, the support layer 1 is divided into a first support layer, a second support layer and a third support layer, and the support rod layer 2 is divided into a first support rod layer, a second support rod layer and a third support rod layer. The cameras 3 are divided into six layers, each layer of camera 3 is installed on the corresponding support layer, and all the cameras 3 are connected with the computer through interfaces. The light sources 10 are distributed at a plurality of positions with the center of the sphere as the center and are connected with the PC board, and the backgrounds 11 are of a plurality of types and are fixed on a background support arranged behind the support. The seat 5 may be an existing seat with a headrest and a height adjustment structure. The control subsystem is connected with the cameras 3 and the light sources 10 and is used for controlling all the cameras 3 to synchronously capture all the omnibearing face images and the light sources 10 to circularly move.
The serial number of support layer 1 is from last to down, first support layer has 5 cameras, second, six layers of support layer 1 respectively have 9 cameras, third, four, five support layer 1 respectively have 13 cameras, evenly install on semi-circular support layer 1. The depression angle of the first layer of cameras is 45 degrees, the yaw angle is-90 degrees, -45 degrees, 0 degrees, 45 degrees and 90 degrees; the depression angle of the second layer camera is 30 degrees, the yaw angle is-90 degrees, -67.5 degrees, -45 degrees, -22.5 degrees, 0 degrees, 22.5 degrees, 45 degrees, 67.5 degrees and 90 degrees; the depression angle of the third layer of camera is 15 degrees, the yaw angle is-90 degrees, -75 degrees, -60 degrees, -45 degrees, -30 degrees, -15 degrees, 0 degrees, 15 degrees, 30 degrees, 45 degrees, 60 degrees, 75 degrees and 90 degrees; the pitch angle of the fourth layer camera is 0 degree, the yaw angle is-90 degrees, -75 degrees, -60 degrees, -45 degrees, -30 degrees, -15 degrees, 0 degrees, 15 degrees, 30 degrees, 45 degrees, 60 degrees, 75 degrees and 90 degrees; the supination angle of the fifth layer camera is 15 degrees, the yaw angle is-90 degrees, -75 degrees, -60 degrees, -45 degrees, -30 degrees, -15 degrees, 0 degrees, 15 degrees, 30 degrees, 45 degrees, 60 degrees, 75 degrees and 90 degrees; the elevation angle of the sixth layer camera is 30 degrees, the yaw angle is-90 degrees, -75 degrees, -60 degrees, -45 degrees, -30 degrees, -15 degrees, 0 degrees, 15 degrees, 30 degrees, 45 degrees, 60 degrees, 75 degrees and 90 degrees. Meanwhile, the camera can be changed by increasing, reducing or changing the position according to the specific research requirement.
In the embodiment, 62 cameras are respectively connected to 6 computers by utilizing PCI-E, one computer is selected as a host, and the serial port end of a PC board is connected to the host; connecting a mouse and a keyboard of a host computer to a synchronizer, and simultaneously connecting the synchronizer with the 6 computers by using a data line; clicking a mouse to synchronously trigger an acquisition button on a software interactive interface of the multi-view reconfigurable face data acquisition system, controlling the light source to be circularly switched on and switched off by the host, and simultaneously sending a shooting instruction to the corresponding camera by 6 computers, wherein the synchronization precision can reach within 20 ms. There is no limitation to cameras that can be controlled synchronously in theory, as long as there is sufficient computer.
The whole bracket 9 is of a profile structure, and each section of the profile of the semicircular bracket layer 1 is connected through a non-standard positioning angle piece and a fixed angle plate through a bolt and a slide block nut; the positioning angle piece is provided with a positioning threaded hole and is connected with the camera holder through a stud; each layer of the strut layer 2 is provided with 6 struts which are symmetrically distributed, and the struts are connected with the strut layer 1 through oblique angle connecting pieces; the bottom layer support is connected with at least 6 hoof feet through slide block nuts; the number of the support legs is 6, one end of each support leg is provided with a threaded hole and is connected with a hoof foot, the other end of each support leg is connected with the fourth support layer through a standard corner piece, and the support legs are spaced at intervals of 36 degrees.
The nonstandard fixed angle plate has three angles of 135 degrees, 157.5 degrees and 165 degrees, so that the bracket at each layer is firmly connected; the non-standard positioning angle piece has three angles of 135 degrees, 157.5 degrees and 165 degrees, and accurate splicing of the bracket profiles on each layer is guaranteed. According to the design principle, a hemispherical support 9 is built; and fixing a cloud platform at the threaded hole of the positioning angle piece, and then fixing the camera on the camera cloud platform.
With the simulated person 6 as a target, adjusting the pose of each camera through a camera holder to enable the face to be in the center position of the image; manually focusing 62 cameras until the image reaches the maximum definition; under a certain stable background illumination condition, parameters such as exposure, brightness, contrast, gamma value, white balance, gain and the like of each camera are adjusted in sequence, and the image effect is optimal under the condition of ensuring clearness.
For convenience of installation, control and analysis, the cameras are numbered in sequence, the first layer camera is numbered I-1-I-5, the second layer camera is numbered II-1-II-9, the third layer camera is numbered III-1-III-13, the fourth layer camera is numbered IV-1-IV-13, the fifth layer camera is numbered V-1-V-13 and the sixth layer camera is numbered VI-1-VI-9. The serial numbers of the cameras on each layer are sequentially increased from left to right, and the left and right directions are based on the collected person. Before collection, the exact camera 3 number corresponding to the port number of each computer needs to be determined.
The light source is a plane uniform light source, the brightness and the chromaticity are adjustable, the light source is fixed on a light source holder, and the pose can be adjusted randomly according to the requirement; the light source holder is fixed on the corresponding sectional materials at the front, rear, left, right, upper, front upper and front lower positions by using a human face as a center through a double-end stud and a T-shaped nut. The brightness and the chromaticity of the light source are adjusted to be consistent, and the position is adjusted by the light source holder. Meanwhile, the light source can be changed by increasing, reducing or changing the position according to the specific research requirement.
The principle of the method is that a PC computer sends a corresponding hexadecimal number command to the PC board through a serial port.
The background cloth is hung on the L-shaped background support and can be manually folded and unfolded through a zipper, the background has various types, the type of the background can be changed according to the situation, and the height of the background 11.1 is 2.2m, and the width of the background is 3 m; the left background 11.2 and the right background (symmetrical to the left background) are 2.2m high and 1.5m wide. The background support is a cubic support which is built by sectional materials and has the length, width and height of 3m by 1.5m by 2.2 m. The background cloth is fixed on the L-shaped background support, and the L-shaped background support is fixed on the support through bolts and T-shaped nuts.
The seat 5 is specially customized, is not deformed when bearing, and is adjustable in height to adapt to different heights; the height of the headrest is adjustable and does not change along with the change of the height of the seat, so that the face is kept at the center of the sphere.
Before collection, the person to be collected should adjust the sitting posture under the reminding of the person to be collected, and the head touches the headrest lightly to look ahead. The collector numbers the collected person on the interactive interface before collecting, selects the corresponding background option, establishes the corresponding folder, and names the image by the light source position and the camera number so as to search and analyze quickly. During collection, a computer parallel storage technology is adopted, so that all images are synchronously stored in a local disk of a computer without data congestion.
Fig. 4 shows face images collected under 5 light sources and 5 viewing angles.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims (6)

1. The multi-view reconfigurable face data acquisition system is characterized by comprising background cloth, seats and a hemispherical support, wherein the hemispherical support comprises six support layers formed by weft arrangement and six support rod layers formed by warp arrangement, a preset number of cameras are uniformly arranged on each support layer, and the cameras are connected with a computer through interfaces; the system also comprises a plurality of light sources which are distributed at a plurality of positions with the ball of the bracket as the center, the cameras and the light sources are connected with the computer through a control subsystem, and the control subsystem is used for controlling all the cameras to synchronously capture all-dimensional face images and the cyclic action of the light sources; the camera is fixed on the camera holder, the pose can be adjusted, and the front, upper and lower full coverage of the collected person can be realized at 62 degrees; the light source is a plane uniform light source, the brightness and the chromaticity are adjustable, and the light source is fixed on a light source holder and the pose is adjustable; the first support layer of the support layer from top to bottom is provided with 5 cameras, the second support layer and the sixth support layer are respectively provided with 9 cameras, and the third support layer, the fourth support layer and the fifth support layer are respectively provided with 13 cameras; the light source holder is fixed on the corresponding sectional materials at the front, rear, left, right, upper, front upper and front lower positions by using a human face as the center through a double-end stud and a T-shaped nut.
2. The multi-view reconfigurable face data acquisition system according to claim 1, wherein the bracket is of a profile structure as a whole, and each section of the profile of the bracket layer is connected with a fixed angle plate through a bolt and a sliding block nut by using a non-standard positioning angle piece; and the positioning angle piece is provided with a positioning threaded hole and is connected with the camera holder through a stud.
3. The system according to claim 1, wherein the strut layers comprise 6 struts symmetrically distributed in each layer, and the struts are connected with the bracket through oblique connectors.
4. The multi-view reconfigurable face data acquisition system according to claim 2, wherein a bottom layer bracket of the bracket is connected with at least 6 hooves through slider nuts; the support has 6 support legs, one end of the support is provided with a threaded hole and connected with the hoof foot, the other end of the support is connected with the fourth support layer through a standard angle piece, and the support legs are spaced at 36 degrees.
5. The multi-view reconfigurable face data acquisition system according to claim 1, wherein the replaceable background cloth is arranged behind the hemispherical support through a background support, is hung on the background support, and can be manually folded and unfolded through a zipper.
6. The multi-view reconfigurable face data acquisition system according to claim 1, wherein the seat is adjustable in height to accommodate different heights and is equipped with a height adjustable headrest to ensure that the face is in the center of sphere position.
CN201810686483.3A 2018-06-28 2018-06-28 Multi-view reconfigurable face data acquisition system Active CN108965696B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810686483.3A CN108965696B (en) 2018-06-28 2018-06-28 Multi-view reconfigurable face data acquisition system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810686483.3A CN108965696B (en) 2018-06-28 2018-06-28 Multi-view reconfigurable face data acquisition system

Publications (2)

Publication Number Publication Date
CN108965696A CN108965696A (en) 2018-12-07
CN108965696B true CN108965696B (en) 2021-08-06

Family

ID=64487353

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810686483.3A Active CN108965696B (en) 2018-06-28 2018-06-28 Multi-view reconfigurable face data acquisition system

Country Status (1)

Country Link
CN (1) CN108965696B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111428668B (en) * 2020-03-31 2024-03-08 中科人工智能创新技术研究院(青岛)有限公司 Multi-view variable-pitch type face data acquisition system and method

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6081739A (en) * 1998-05-21 2000-06-27 Lemchen; Marc S. Scanning device or methodology to produce an image incorporating correlated superficial, three dimensional surface and x-ray images and measurements of an object
CN203785640U (en) * 2014-04-09 2014-08-20 黄河科技学院 Double-elevating-type character head portrait three-dimensional modeling information acquisition device
CN106534671A (en) * 2016-11-02 2017-03-22 南京大学 360-degree image synchronization acquisition system
CN106851070B (en) * 2017-03-13 2019-04-12 北京智造宝科技有限公司 A kind of three dimensional face scanner with monitoring camera

Also Published As

Publication number Publication date
CN108965696A (en) 2018-12-07

Similar Documents

Publication Publication Date Title
CN109960401B (en) Dynamic projection method, device and system based on face tracking
KR100938021B1 (en) System and method for capturing facial and body motion
CN104067111B (en) For following the tracks of the automated systems and methods with the difference on monitoring objective object
US8712102B2 (en) Relative pose estimation of non-overlapping cameras using the motion of subjects in the camera fields of view
CN109186584A (en) A kind of indoor orientation method and positioning system based on recognition of face
DE202014011422U1 (en) Optical navigation and positioning system
US11137824B2 (en) Physical input device in virtual reality
CN108363946A (en) Face tracking system and method based on unmanned plane
WO2022242395A1 (en) Image processing method and apparatus, electronic device and computer-readable storage medium
CN102638653A (en) Automatic face tracing method on basis of Kinect
US20200117952A1 (en) Target object position prediction and motion tracking
CN108965696B (en) Multi-view reconfigurable face data acquisition system
CN111881888A (en) Intelligent table control method and device based on attitude identification
US11703820B2 (en) Monitoring management and control system based on panoramic big data
Voit et al. Multi-view head pose estimation using neural networks
CN115562490A (en) Cross-screen eye movement interaction method and system for aircraft cockpit based on deep learning
EP3863275B1 (en) System and method for smart image-capturing
CN110553628A (en) Depth camera-based flying object capturing method
CN112911150A (en) Automatic snapshot method for high-definition human face in target area
US11422618B2 (en) Smart strap and method for defining human posture
CN108119780A (en) A kind of free-viewing angle becomes illumination image capturing system
Tomori et al. Active segmentation in 3d using kinect sensor
Galanakis et al. Tracking persons using a network of RGBD cameras
WO2023159668A1 (en) System and method of capturing large scale scenes using wearable inertial measurement devices and light detection and ranging sensors
Shere et al. Temporally consistent 3D human pose estimation using dual 360deg cameras

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CP03 Change of name, title or address

Address after: 300457 unit 1001, block 1, msd-g1, TEDA, No.57, 2nd Street, Binhai New Area Economic and Technological Development Zone, Tianjin

Patentee after: Tianjin Zhongke intelligent identification Co.,Ltd.

Address before: Unit 300465 TEDA MSD-G1-1001, 57 Second Avenue, Tianjin Economic and Technological Development Zone, Binhai New Area, Tianjin

Patentee before: TIANJIN ZHONGKE INTELLIGENT IDENTIFICATION INDUSTRY TECHNOLOGY RESEARCH INSTITUTE Co.,Ltd.

CP03 Change of name, title or address