This paper focuses on online scene learning and fast camera relocalisation which are two key problems currently limiting the performance of wide area augmented reality systems. Firstly, we propose to use adaptive random trees to deal with the online scene learning problem. The algorithm can provide more accurate recognition rates than traditional methods, especially with large scale workspaces. Secondly, we use the enhanced PROSAC algorithm to obtain a fast camera relocalisation method. Compared with traditional algorithms, our method can significantly reduce the computation complexity, which facilitates to a large degree the process of online camera relocalisation. Finally, we implement our algorithms in a multithreaded manner by using a parallel-computing scheme. Camera tracking, scene mapping, scene learning and relocalisation are separated into four threads by using multi-CPU hardware architecture. While providing real-time tracking performance, the resulting system also possesses the ability to track multiple maps simultaneously. Some experiments have been conducted to demonstrate the validity of our methods.
References
[1]
Duan, L.Y.; Guan, T.; Yang, B. Registration Combining Wide and Narrow Baseline Feature Tracking Techniques for Markerless AR Systems. Sensors？2009, 9, 10097–10116.
[2]
David, Y.; Efron, U. The Image Transceiver Device: Studies of Improved Physical Design. Sensors？2008, 8, 4350–4364.
[3]
Davison, A.; Reid, I.; Molton, N.D.; Stasse, O. MonoSLAM: Real-Time Single Camera SLAM. IEEE Trans. Pattern Anal. Mach. Int？2007, 29, 1052–1067.
[4]
Klein, G.; Murray, D. Parallel Tracking and Mapping for Small AR Workspaces. Proceedings of International Symposium on Mixed and Augmented Reality (ISMAR’07), Nara, Japan, November 2007; pp. 225–234.
[5]
Bleser, G.; Wuest, H.; Stricker, D. Online Camera Pose Estimation in Partially Known and Dynamic Scenes. Proceedings of International Symposium on Mixed and Augmented Reality (ISMAR’06), San Diego, CA, USA, October 2006; pp. 56–65.
[6]
Guan, T.; Wang, C. Registration Based on Scene Recognition and Natural Features Tracking Techniques for Wide-area Augmented Reality Systems. IEEE Trans. Multimedia？2009, 11, 1393–1406.
[7]
Mouragnon, E.; Dekeyser, F.; Sayd, P.; Lhuillier, M.; Dhome, M. Real Time Localization and 3D Reconstruction. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR’06), New York, NY, USA, June 2006; pp. 363–370.
[8]
Lee, T.; H？llerer, T. Multithreaded Hybrid Feature Tracking for Markerless Augmented Reality. IEEE Trans. Vis. Comput. Graph？2009, 15, 355–368.
[9]
Klein, G.; Murray, D. Improving the Agility of Keyframe-Based SLAM. Proceedings of European Conference on Computer Vision (ECCV’08), Marseille, France, October 2008; pp. 802–815.
[10]
Lingua, A.; Marenchino, D.; Nex, F. Performance Analysis of the SIFT Operator for Automatic Feature Extraction and Matching in Photogrammetric Applications. Sensors？2009, 9, 3745–3766.
[11]
Williams, B.; Smith, P.; Reid, I. Automatic relocalisation for a single-camera simultaneous localisation and mapping system. Proceedings of International Conference on Robotics and Automation, (ICRA 07), Rome, Italy, April 2007; pp. 2784–2790.
[12]
Williams, B.; Klein, G.; Reid, I. Real-Time SLAM Relocalisation. Proceedings of ICCV, Rio de Janeiro, Brazil, October 2007; pp. 1–8.
[13]
Castle, R.O.; Murray, D.W. Object Recognition And Localization While Tracking And Mapping. Proceedings of International Symposium on Mixed and Augmented Reality (ISMAR’09), Orlando, FL, USA, October 2009; pp. 179–180.
[14]
Wagner, D.; Schmalstieg, D.; Bischof, H. Multiple Target Detection and Tracking with Guaranteed Frame rates on Mobile Phones. Proceedings of International Symposium on Mixed and Augmented Reality (ISMAR’09), Orlando, FL, USA, October 2009; pp. 57–64.
[15]
Dong, Z.L.; Zhang, G.F.; Jia, J.Y.; Bao, H.J. Keyframe-Based Real-Time Camera Tracking. Proceedings of ICCV, Kyoto, Japan, September 2009; pp. 1538–1545.
[16]
Lepetit, V.; Fua, P. Keypoint Recognition Using Randomized Trees. IEEE Trans. Patt. Anal. Mach. Int？2006, 28, 1465–1479.
[17]
UkBench, Available online: http://www.vis.uky.edu/~stewe/ukbench/ (accessed on February 2, 2010).
[18]
CUDA, Available online: http://cuda.csdn.net/ (accessed on February 5, 2010).
[19]
GPGPU, Available online: http://www.gpgpu.org/w/index.php/glossary/ (accessed on February 5, 2010).
[20]
Pelletier, M.G. Parallel Algorithm for GPU Processing; for Use in High Speed Machine Vision Sensing of Cotton Lint Trash. Sensors？2008, 8, 817–829.
[21]
Calonder, M.; Lepetit, V.; Fua, P. Keypoint Signatures for Fast Learning and Recognition. Proceedings of European Conference on Computer Vision (ECCV’08), Marseille, France, October 2008; pp. 58–71.
[22]
Calonder, M.; Lepetit, V.; Konolige, K.; Mihelich, P.; Bowman, J.; Fua, P. Compact Signatures for High-Speed Interest Point Description and Matching. Proceedings of ICCV, Kyoto, Japan, September 2009.
[23]
Bay, H.; Ess, A.; Tuytelaars, T.; Gool, L.V. Surf: Speeded Up Robust Features. Comput. Vis. Image Understand？2008, 110, 346–359.
[24]
Bay, H.; Ess, A.; Tuytelaars, T.; Gool, L.V. Surf: Speeded Up Robust Features. Proceedings of European Conference on Computer Vision (ECCV’06), Graz, Austria, May 2006; pp. 404–417.
[25]
Konolige, K.; Bowman, J.; Chen, J.D.; Mihelich, P.; Calonder, M.; Lepetit, V.; Fua, P. View-Based Maps. Proceedings of Robotics: Science and Systems, Seattle, WA, USA, June 2009.
[26]
SAD, Available online: http://en.wikipedia.org/wiki/Sum_of_absolute_differences . (accessed on February 7, 2010).
[27]
Fischler, M.A.; Bolles, R.C. Random Sample Consensus: A Paradigm for Model Fitting With Applications to Image Analysis and Automated Cartography. CACM？1981, 24, 381–395.
[28]
Chum, O.; Matas, J. Matching with PROSAC Progressive Sample Consensus. Proceedings of ICCV, Beijing, China, October 2005; pp. 220–226.
[29]
Pablo, M.N.; Jacobo, G.; Luis, B.; José, M.B. Improving RANSAC for Fast Landmark Recognition. Proceedings of Visual Localization for Mobile Platforms, Anchorage, AK, USA, June 2008.
[30]
Huber, P.J. Robust Estimation of A Location Parameter. Ann. Math. Stat？1964, 35, 73–101.
[31]
GML Camera Calibration Toolbox Downloads Resource, Available online: http://research.graphicon.ru/calibration/gml-c-camera-calibration-toolbox-5.html/ (accessed on February 19, 2010).
[32]
Matas, J.; Chum, O. Randomized RANSAC with Td,d Test. Image Vis. Comput？2004, 22, 837–842.
[33]
Nister, D. Preemptive RANSAC for Live Structure and Motion Estimation. Proceedings of ICCV, Nice, France, October 2003; pp. 199–206.
[34]
Capel, D. An effective Bail-out Test for RANSAC Consensus Scoring. Proceedings of British Machine Vision Conference (BMVC’05), Oxford, UK, September 2005; pp. 629–638.
Wagner, D.; Schmalstieg, D. Making Augmented Reality Practical on Mobile Phones, Part 1. IEEE Comput. Graph. Appl？2009, 29, 12–15.
[37]
Wagner, D.; Schmalstieg, D. Making Augmented Reality Practical on Mobile Phones, Part 2. IEEE Comput. Graph. Appl？2009, 29, 6–9.
[38]
Wagner, D.; Reitmayr, G.; Mulloni, A.; Drummond, T.; Schmalstieg, D. Pose Tracking from Natural Features on Mobile Phones. Proceedings of International Symposium on Mixed and Augmented Reality (ISMAR’08), Cambridge, UK, September 2008; pp. 125–134.
[39]
Klein, G.; Murray, D.W. Parallel Tracking and Mapping on a Camera Phone. Proceedings of International Symposium on Mixed and Augmented Reality (ISMAR’09), Orlando, FL, USA, October 2009; pp. 83–86.
[40]
Teng, G.; Zheng, K.; Dong, W. Adapting Mobile Beacon-Assisted Localization in Wireless Sensor Networks. Sensors？2009, 9, 2760–2779.
