Recognition algorithms would significantly benefit from object images acquired from preferential view points, e.g. unobstructed frontal views or complementary views. Active-vision systems, which are dynamically reconfigurable in an online mode, have been suggested in the literature as effective solutions for achieving this objective, namely, relocating cameras to obtain optimal visibility for a given situation.
To obtain optimal visibility of an object of interest (OI), however, that OI's three-dimensional (3D) position and orientation (i.e. six degree-of-freedom pose) must be tracked in real time. Thus, this paper presents such an autonomous, real-time, six degree-of-freedom pose tracking system for a priori unknown objects. The proposed tracking method autonomously (a) selects the OI, (b) builds its approximate 3D model and uses this model to (c) track it in real time.
As will be shown in this paper, via experimental results, the output of the proposed modeller can be effectively used by an active-vision system to relocate its cameras for effective preferential image acquisition. In the examples included herein, it will be noted that object visibility data obtained via camera reconfiguration based on the authors' ‘approximate’ tracking method are comparable with those obtainable based on ‘perfect’ OI tracking.
YuS.TanD.TanT., A framework for evaluating the effect of view angle, clothing, carrying condition on gait recognition. In Proceedings of the International Conference on Pattern recognition, Hong Kong, 2006, pp. 441–444.
2.
ChanY.ZongZ.LeeJ.XuY., Multi-agent based surveillance. In Proceedings of the IEEE International. Conference on Intelligent robots and systems, Beijing, China, 2006, pp. 2810–2815.
3.
Murrieta-CidR.TovarB.HutchinsonS., A sampling-based motion planning approach to maintain visibility of unpredictable targetsJ. Autonomous Robots19 (3) (2005): 285–300.
4.
TarabanisK.AllenP.TsaiR., A survey of sensor planning in computer visionIEEE Trans. Robotics Automn11 (1) (1995): 86–104.
5.
HodgeL.KamelN., An agent-based approach to multi-sensor coordinationIEEE Trans. Systems, Man, Cybernetics, Part A: Systems and Humans33 (5) (2003): 648–662.
6.
SakaneS.SatoT.KakikuraM., Model-based planning of visual sensors using a hand–eye action simulator: HEAVEN. In Proceedings of the Conference on Advanced robotics, Versailles, France, 1987, pp. 163–174.
7.
SpletzerJ.TaylorC., Dynamic sensor planning and control for optimally tracking targetsInt. J. Robotic Res.22 (1) (2003): 7–20.
8.
NaishM., Sensing-system planning for the surveillance of moving objects PhD, thesis, University of Toronto, Toronto, Canada, 2004.
9.
BakhtariA.BenhabibB., An active vision system for multi-target surveillance in dynamic environmentsIEEE Trans. Systems, Man, Cybernetics37 (1) (2007): 190–198.
10.
MackayM.BenhabibB., A multi-camera active-vision system for dynamic form recognitionElleithyK. Ed. In Innovations and advanced techniques in systems, computing sciences and software engineering (2008).
11.
BakhtariA.EskandariM.NaishM.BenhabibB., A multi-sensor surveillance system for active-vision-based object localization. In Proceedings of the IEEE International Conference on Systems, man, and cyber-netics, Washington, D.C., 2003, pp. 1013–1018.
12.
Safee-RadR.TchoukanovI.SmithK.BenhabibB., Three-dimensional location estimation of circular features for machine visionIEEE Trans. Robotics Automn8 (5) (1992): 624–640.
13.
BouchrikaI.NixonM., Model-based feature extraction for gait analysis and recognition In Computer vision/computer graphics collaboration techniques and applications Rocquencourt, France, 2007, pp. 150–160.
14.
MackayM.FentonR. G.BenhabibB., Time-varying-geometry object surveillance using a multi-camera active-vision systemInt. J. Smart Sensing Intell. Systems1 (3) (2008): 679–704.
15.
MackayM.BenhabibB.FentonR., Active vision for human action sensing In Proceedings of the CISSE2009, online http://www.cisse2008.org.
AhrnsI.NeumannH., Space-variant dynamic neural fields for visual attention. In IEEE Conferenceon Computer vision and pattern recognition, vol. 2, Ft Collins, Colorado, June 1999, pp. 313–318.
18.
DavisonA. J.CidY. G.KitaN., Real-time 3D SLAM with wide-angle vision. In Proceedings of IFAC Symposium on Intelligent autonomous vehicles, Lisbon, July, 2004.
19.
KutulakosK. N., Approximate N-view stereo. In Pro-ceedings of the European Conference on Computer vision, Dublin, Ireland, 2000, pp. 67–83.
20.
MulayimA. Y.YilmazU.AtalayV., Silhouette-based 3-D model reconstruction from multiple imagesIEEE Trans. Systems, Man, Cybernetics, Part B: Cybernetics33 (4) (2003): 582–591.
21.
KahlF.AugustJ., Multi-view reconstruction of space curves. In Proceedings of the IEEE International Conference on Computer vision, vol. 2, October 2003, pp. 1017–1024.
22.
SimardP.FerrieF., Image-based model updating. Proceedings of the British Machine Vision Con-ference, Cardiff, Wales, 2002, pp. 193–202.
23.
FrancoJ. S.MénierC.BoyerE.RaffinB., A distributed approach for real time 3D modeling. In Proceedings of the IEEE Workshop on Real time 3D sensors and their use, Washington, D.C., July 2004.
24.
MarchandE.BouthemyP.ChaumetteF., A 2D-3D model-based approach to real-time visual trackingImage vision comput.19 (7) (2001): 941–955.
25.
JurieF.DhomeM., Real time robust template matching. In Proceedings of the British Machine Vision Conference, Cardiff, Wales, 2002, pp. 123–132.
KimS.KweonI., Robust model-based 3D object recognition by combining feature matching with tracking. In Proceedings of the International Conference on Robotics and automation, vol. 2, Taipei, Taiwan, Sep-tember 2003, pp. 2123–2128.
28.
KyrkiV.KragicD., Integration of model-based and model-free cues for visual object tracking in 3D. In Proceedings of the International Conference on Robot-ics and automation, Barcelona, Spain, April 2005, pp. 1554–1560.
29.
VinczeM.SchlemmerM.GemeinerP.AyromlouM., Vision for robotics: A tool for model-based object trackingIEEE Robotics Automn Mag.12 (4) (2005): 53–64.
30.
ComportA.MarchandE.PressigoutM.ChaumetteF., Real-time markerless tracking for augmented reality: The virtual visual servoing frameworkIEEE Trans. Visualization Computer Graphics12 (4) (2006): 615–628.
31.
de RuiterH.BenhabibB., Object-of-interest selection for model-based 3D pose tracking with background clutterTarek SobhK. E. Ed. In Novel algorithms and techniques in telecommunications, automation and industry electronics (2008) pp. 93–98.
32.
de RuiterH.BenhabibB., On-line modeling for real-time, model-based, 3D pose trackingMach. Vision Applic. (August 2007): 555–560 (published online).
33.
KalmanR., A New approach to linear filtering and prediction problemsJ. Basic Engng81 (1) (1960): 35–45.
34.
BakhtariA.BenhabibB., Agent-based active-vision system reconfiguration for autonomous surveillance of dynamic, multi-object environments. In Pro-ceedings of the IEEE/RSJ International Conference on Intelligent robots and systems, Edmonton, Canada, 2005, pp. 1373–1378.
35.
LucasB.KanadeT., An iterative image registration technique with application to stereo vision. In Pro-ceedings of the Seventh International Joint Conference on Artificial intelligence, Vancouver, Canada, August 1981, pp. 674–479.
36.
HagerG. D.BelhumeurP. N., Real-time tracking of image regions with changes in geometry and illumination. In Proceedings of the IEEE Conference onComputer vision and pattern recognition, San Francisco, California, 1996, pp. 403–410.
ChangP.KrummJ., Object recognition with color cooccurrence histograms. In Proceedings of the IEEE Conference on Computer vision and pattern recognition, Fort Collins, Colorado, June 1999, pp. 498–504.
39.
YangR.WelchG.BishopG., Real-time consensus-based scene reconstruction using commodity graphics hardware. In Proceedings of the 10th Pacific Conference on Computer graphics and applications, Beijing, China, 2002, pp. 225–234.
40.
LeeS.JangD.KimE.HongS.HanJ., A real-time 3D workspace modeling with stereo camera. In Proceedings of the International Conference onRobots and systems, Edmonton, Canada, August 2005, pp. 2140–2147.
41.
BhanuB.LeeS.DasS., Adaptive image segmentation using genetic and hybrid search methodsIEEE Trans. Aerospace and Electronic Systems31 (4) (1995): 1268–1291.
42.
HoS.LeeK., An efficient evolutionary image segmentation algorithm. In Proceedings of the 2001 Con-gress on Evolutionary computation, vol. 2, Seoul, South Korea, May 2001, pp. 1327–1334.
43.
PedriniH.Modeling dense range images through fast polygonal approaches. In Proceedings of the 11th Conference on Image analysis and processing, Palermo, Italy, September 2001, pp. 448–453.
44.
HarrisC.StephensM.A combined corner and edge detector. In Proceedings of the Alvey Vision Con-ference, vol. 15, Manchester, UK, September 1988, pp. 141–151.
45.
VinczeM., A system to navigate a robot into a ship structureMach. Vision Applic.14 (1) (2003): 15–25.
CadmanL.TjahjadiT.Simultaneous feature tracking and three-dimensional object reconstruction from an image sequence. In Proceedings of the Inter-national Conferenceon Image processing, vol. 2, Thes-saloniki, Greece, October 2001, pp. 391–394.
48.
de RuiterH.BenhabibB.Tracking of rigid bodies for autonomous surveillance. In Proceedings of the IEEE InternationalConference on Mechatronics and automation, vol. 2, Niagara Falls, Canada, July 2005, pp. 928–933.
49.
de RuiterH.BenhabibB.Colour-gradient redundancy for real-time spatial pose tracking in autonomous robot navigation. In Proceedings of the Canadian Conference on Computer and robotic vision, Québec City, Canada, June 2006, pp. 20–28.
50.
CollinsG.DennisL.A system for video surveil-lance and monitoring. In Proceedings of the International Conference on Automated deduction, Pittsburgh, Pennsylvania, June 2000, pp. 497–501.
