© The Institution of Engineering and Technology
A novel approach for three-dimensional (3D) volumetric reconstruction of an object inside a scene is proposed. A camera network is used to observe the scene. Each camera within the network is rigidly coupled with an Inertial Sensor (IS). A virtual camera is defined for each IS–camera couple using the concept of infinite homography, by fusion of inertial and visual information. Using the inertial data and without planar ground assumption, a set of virtual horizontal planes are defined. The intersections of these inertial-based virtual planes with the object are registered using the concept of planar homography. Moreover a method to estimate the translation vectors among virtual cameras is proposed, which just needs the relative heights of two 3D points in the scene with respect to one of the cameras and their correspondences on the image planes. Different experimental results for the proposed 3D reconstruction method are provided on two different types of scenarios. In the first type, a single IS–camera couple is used and placed in different locations around the object. In the second type, the 3D reconstruction of a walking person (dynamic case) is performed where a set of installed cameras in a smart-room is used for the data acquisition. Moreover, a set of experiments are simulated to analyse the accuracy of the translation estimation method. The experimental results show the feasibility and effectiveness of the proposed framework for the purpose of multi-layer data registration and volumetric reconstruction.
References
-
-
1)
-
G. Bleser ,
C. Wohlleber ,
M. Becker ,
D. Stricker
.
(2006)
Fast and stable tracking for ar fusing video and inertial sensor data, .
-
2)
-
Zhang, Q.-B., Wang, H.-X., Wei, S.: `A new algorithm for 3D projective reconstruction based on infinite homography', IEEE Int. Conf. on Machine Learning and Cybernetics, 2003.
-
3)
-
R. Guerchouche ,
O. Bernier ,
T. Zaharia
.
Multiresolution volumetric 3D object reconstruction for collaborative interactions.
Pattern Recognit. Image Anal.
,
621 -
637.
-
4)
-
Wada, T., Wu, X., Tokai, S., Matsuyama, T.: `Homography based parallel volume intersection: toward real-time volume reconstruction using active cameras', Computer Architectures for Machine Perception, 2000. Proc. Fifth IEEE Int. Workshop on 11–13 September 2000, 2000, p. 331–339.
-
5)
-
J.Y. Bouguet
.
Camera calibration toolbox for matlab.
-
6)
-
Lai, P.-L., Yilmaz, A.: `Projective reconstruction of building shape from silhouette images acquired from uncalibrated cameras', Proc. Commission III, ISPRS Congress, Beijing 2008, 2008.
-
7)
-
Michoud, B., Saida, B., Erwan, G., Hector, B.: `Largest silhouette-equivalent volume for 3D shapes modeling without ghost object', M2SFA2 2008: Workshop on Multi-camera and Multi-modal Sensor Fusion, 2008, Marseille, France.
-
8)
-
Hogue, A., German, A., Jenkin, M.: `Underwater environment reconstruction using stereo and inertial data', IEEE Int. Conf. on Systems, Man and Cybernetics, ISIC, 2007, p. 2372–2377.
-
9)
-
Labrie, M., Hebert, P.: `Efficient camera motion and 3d recovery using an inertial sensor', Fourth Canadian Conf. on Computer and Robot Vision, CRV'07, 2007, p. 55–62.
-
10)
-
B. Michoud ,
E. Guillou ,
S. Bouakaz ,
A. Elgammal ,
B. Rosenhahn ,
R. Klette
.
(2007)
Real-time and markerless 3D human motion capture using multiple views, Human motion-understanding, modeling, capture and animation.
-
11)
-
Aliakbarpour, H., Dias, J.: `Human silhouette volume reconstruction using a gravity-based virtual camera network', Proc. 13th Int. Conf. on Information Fusion, 26–29 July 2010, EICC Edinburgh, UK.
-
12)
-
Lai, P.-L., Yilmaz, A.: `Efficient object shape recovery via slicing planes', IEEE Conf. on Computer Vision and Pattern Recognition, CVPR 2008, 2008, p. 1–6.
-
13)
-
Hsieh, H.-W., Yu, H.-H., Wu, C.-C., Hu, J.-S.: `Concurrent multiple cameras calibration and robot localization from visual and 3d inertial measurements', Proc. SICE Annual Conf., 2010, p. 1914–1919.
-
14)
-
J. Lobo ,
J. Dias
.
Relative pose calibration between visual and inertial sensors.
Int. J. Robot. Res.
,
6 ,
561 -
575
-
15)
-
Ababsa, F.: `Toward a real-time 3D reconstruction system for urban scenes using georeferenced and oriented images', Second Int. Conf. on Computer and Electrical Engineering, ICCEE'09, 2009, 1, p. 75–79.
-
16)
-
M.A. Brodie ,
A. Walmsley ,
W. Page
.
The static accuracy and calibration of inertial measurement units for 3d orientation.
Comp. Methods Biomech. Biomed. Eng.
,
641 -
648
-
17)
-
Lee, H., Yilmaz, A.: `3D reconstruction using photo consistency from uncalibrated multiple views', VISAPP 2010 – The Int. Joint Conf. on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2010.
-
18)
-
T. Feldmann ,
I. Mihailidis ,
S. Schulz ,
D. Paulus ,
A. Worner ,
D. Rudiger ,
B. Jurgen ,
H. Uwe ,
S. Tanja
.
(2010)
Online full body human motion tracking based on dense volumetric 3d reconstructions from multi camera setups, KI 2010, advances in artificial intelligence, volume 6359 of lecture notes in computer science.
-
19)
-
T.C.S. Azevedo ,
J.M.R.S. Tavares ,
M.A.P. Vaz
.
(2009)
3D object reconstruction from uncalibrated images using an off-the-shelf camera, Advances in Computational Vision and Medical Image Processing; in Series of Computational Methods in Applied Sciences.
-
20)
-
Opencv. http://opencv.willowgarage.com/.
-
21)
-
Lobo, J., Almeida, L., Alves, J., Dias, J.: `Registration and segmentation for 3D map building – a solution based on stereo vision and inertial sensors', Proc. IEEE Int. Conf. on Robotics and Automation, ICRA'03, 2003, 1, p. 139–144.
-
22)
-
Aliakbarpour, H., Dias, J.: `Imu-aided 3D reconstruction based on multiple virtual planes', IEEE Proc. DICTA'10 (the Australian Pattern Recognition and Computer Vision Society Conf.), 1–3 December 2010, Sydney, Australia.
-
23)
-
Hwang, Y., Kim, J.-S., Kweon, I.: `Silhouette extraction for visual hull reconstruction', Proc. IAPR workshop on Machine Vision Applications (MVA), 2005.
-
24)
-
Mirisola, L.G.B., Dias, J.M.M.: `Exploiting inertial sensing in mosaicing and visual navigation', Sixth IFAC Symp. on Inteligent Autonomous Vehicles (IAV07), September 2007, Toulouse, France.
-
25)
-
Khan, S.M., Yan, P., Shah, M.: `A homographic framework for the fusion of multi-view silhouettes', IEEE 11th Int. Conf. on Computer Vision, ICCV 2007, 2007.
-
26)
-
Bleser, G., Stricker, D.: `Advanced tracking through efficient image processing and visual-inertial sensor fusion', Virtual Reality Conf, 2008. VR'08. IEEE, 2008, p. 137–144.
-
27)
-
R. Hartley
.
(2003)
Multiple view geometry in computer vision.
-
28)
-
Xsens motion technologies. http://www.xsens.com.
-
29)
-
Zendjebil, I.M., Ababsa, F., Didier, J., Mallem, M.: `A gps-imu-camera modelization and calibration for 3d localization dedicated to outdoor mobile applications', 2010 Int. Conf. on Control Automation and Systems (ICCAS), 2010, p. 1580–1585.
-
30)
-
Lin, H.-Y., Wu, J.-R.: `3D reconstruction by combining shape from silhouette with stereo', Proc. of the 19th Int. Conf. on Patt. Rec. (ICPR 2008), Tampa, Florida, USA, Dec 2008.
-
31)
-
Zhang, Z., Hanson, A.R.: `3D reconstruction based on homography mapping', In ARPA Image Understanding Workshop, 1996.
-
32)
-
Okatani, T., Deguchi, K.: `Robust estimation of camera translation between two images using a camera with a 3d orientation sensor', Proc. 16th Int. Conf. on Pattern Recognition, 2002, 1, p. 275–278.
-
33)
-
Dias, J., Lobo, J., Almeida, L.A.: `Cooperation between visual and inertial information for 3D vision', Proc. 10th Mediterranean Conf. on Control and Automation – MED2002 Lisbon, 9–12 July 2002, Portugal.
-
34)
-
B. Zhang ,
Y.F. Li
.
An efficient method for dynamic calibration and 3D reconstruction using homographic transformation.
Sens. Actuators A, Phys.
,
2 ,
349 -
357
-
35)
-
M. Kalantari ,
A. Hashemi ,
F. Jung ,
J.-P. Guedon
.
A new solution to the relative orientation problem using only 3 points and the vertical direction.
J. Math. Imag. Vis.
,
259 -
268
-
36)
-
Aliakbarpour, H., Ferreira, J.F., Khoshhal, K., Dias, J.: `A novel framework for data registration and data fusion in presence of multi-modal sensors', Proc. DoCEIS2010, Emerging Trends in Technological Innovation, IFIP AICT 314-2010, Springer, 2010, 314/2010, p. 308–315.
-
37)
-
M. Sormann ,
C. Zach ,
J. Bauer ,
K. Karner ,
H. Bishof ,
E. Bjarne ,
P. Kim
.
(2007)
Watertight multi-view reconstruction based on volumetric graph-cuts, Image analysis, volume 4522 of lecture notes in computer science’.
-
38)
-
Mirisola, L.G.B., Dias, J., Traca de Almeida, A.: `Trajectory recovery and 3D mapping from rotation-compensated imagery for an airship', Proc. 2007 IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, 29 October–2 November, 2007, San Diego, CA, USA.
-
39)
-
J. Lobo ,
C. Queiroz ,
J. Dias
.
World feature detection and mapping using stereovision and inertial sensors.
Robot. Auton. Syst.
,
1 ,
69 -
81.
-
40)
-
J.K.Y. Ma ,
S. Soatta ,
S. Shankar Sastry
.
(2004)
An invitation to 3D vision.
-
41)
-
Mirisola, L.G.B.: `Exploiting attitude sensing in vision-based navigation, mapping and tracking including results from an airship', 2009, PhD, .
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2011.0078
Related content
content/journals/10.1049/iet-cvi.2011.0078
pub_keyword,iet_inspecKeyword,pub_concept
6
6