Browse > Article
http://dx.doi.org/10.3837/tiis.2014.11.025

A Parallel Implementation of Multiple Non-overlapping Cameras for Robot Pose Estimation  

Ragab, Mohammad Ehab (Informatics Dept., Electronics Research Institute)
Elkabbany, Ghada Farouk (Informatics Dept., Electronics Research Institute)
Publication Information
KSII Transactions on Internet and Information Systems (TIIS) / v.8, no.11, 2014 , pp. 4103-4117 More about this Journal
Abstract
Image processing and computer vision algorithms are gaining larger concern in a variety of application areas such as robotics and man-machine interaction. Vision allows the development of flexible, intelligent, and less intrusive approaches than most of the other sensor systems. In this work, we determine the location and orientation of a mobile robot which is crucial for performing its tasks. In order to be able to operate in real time there is a need to speed up different vision routines. Therefore, we present and evaluate a method for introducing parallelism into the multiple non-overlapping camera pose estimation algorithm proposed in [1]. In this algorithm the problem has been solved in real time using multiple non-overlapping cameras and the Extended Kalman Filter (EKF). Four cameras arranged in two back-to-back pairs are put on the platform of a moving robot. An important benefit of using multiple cameras for robot pose estimation is the capability of resolving vision uncertainties such as the bas-relief ambiguity. The proposed method is based on algorithmic skeletons for low, medium and high levels of parallelization. The analysis shows that the use of a multiprocessor system enhances the system performance by about 87%. In addition, the proposed design is scalable, which is necaccery in this application where the number of features changes repeatedly.
Keywords
Pose Estimation; Multiple-cameras; EKF; Robot Navigation; and Parallel Processing;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Ma. Dongdong, L. Jinzong, Z. Bing, and Z. Fuzhen, "Research on the Architectures of Parallel Image Processing Systems," in Proc. of the 2nd Int. Symposium on Intelligent Information Technology Application (IITA '08), PP: 146-150 Shanghai, 20-22 Dec., 2008.
2 J. Greco, "Parallel Image processing and Computer Vision Architecture", Bachelor of Science Summa Cum Laude thesis, Univ. of Florida, USA, 2005.
3 O.C. Jenkins, G. Gonzalez, and M. Loper, "Dynamical motion vocabularies for kinematic tracking and activity recognition," in Proc. of CVPRW'06. IEEE, vol. I, pp., 147-152, 2006.
4 T. J. Broida, S. Chanrashekhar, and R. Chellappa, "Recursive 3-D Motion Estimation from a Monocular Image Sequence," IEEE Trans. Aerospace and Electronic Systems, vol. 26, no. 4, pp.639-656, 1990.   DOI   ScienceOn
5 A. Azarbayejani, and A.P. Pentland, "Recursive estimation of motion, structure, and focal length," IEEE Trans. on PAMI, vol. 17, no. 6, pp.562-575, June 1995.   DOI   ScienceOn
6 M. E. Ragab and K. H. Wong, "Multiple Non-overlapping Camera Pose Estimation," in Proc. of the 17th IEEE Int. Conf. on Image Processing (ICIP), PP: 3253-3256, Hong Kong, Sept. 26-29, 2010.
7 M.E. Ragab, K.H. Wong, J.Z. Chen, and M.M.Y. Chang, ,"EKF Based Pose Estimation using Two Back-to-Back Stereo Pairs," in Proc. of ICIP'07. IEEE, vol. VI, pp., pp. 137-140, 2007.
8 T. Braunl, "Tutorial in Data Parallel Image Processing," Australian Journal of Intelligent Information Processing Systems (AJIIPS), vol. 6, no. 3, pp. 164-174, 2001.
9 A. Chiuso, P. Favaro, H. Jain, and S. Soatto, "Structure from Motion Causally Integrated Over Time," PAMI, vol. 24, no. 4, pp. 523-535, 2002.   DOI   ScienceOn
10 Y. K. Yu, K.H. Wong, and M. Chang, "Recursive Three-Dimensional Model Reconstruction Based on Kalman Filtering," IEEE Trans. SMC-B, vol. 35, no. 3, pp. 587-592, 2005.
11 Y.K. Yu, K.H.Wong, S.H.Or, and M.M.Chang, "Recursive recovery of position and orientation from stereo image sequences without three-dimentional structure," in Proc. of CVPR'06, vol. 1, New York, Jun, 2006.
12 P. Baker, C. Fermuller, Y. Aloimonos, and R. Pless, "A spherical eye from multiple cameras (makes better models of the world)," in Proc. of CVPR, vol.1, pp. 576-583, 2001.
13 W. Chang, and C. Chen, "Pose Estimation for Multiple Camera Systems," in Proc. of ICPR, vol. 3, pp. 262-265, 2004.
14 M. Grossberg, and S. Nayar, "A general imaging model and a method for finding its parameters," in Proc. of ICCV, vol. 2, pp. 108-115, 2001.
15 Francisco Bonin-Font, Alberto Ortiz and Gabriel, "Visual Navigation for Mobile Robots: a Survey," Journal of Intelligent and Robotic Systems, vol. 53, Issue 3, pp. 263-296, November 2008.   DOI
16 R. Pless, "Using many cameras as one," in Proc. of CVPR , vol. 2, pp. 587-593, 2003.
17 D. C. Schurman, and D. W. Capson, "Direct Visual Servoing Using Network-synchronized Cameras and Kalman Filter," in Proc. of ICRA, vol. 4, pp. 4191-4197, 2002.
18 N. Ushimi, M. Yamamoto, J. Inoue, T. Sugimoto, M. Araoka, T. Matsuoka, T. Kiriki, Y. Yamaguchi, T. Hasegawa, and A. Mohri, "On-line Navigation of Mobile Robot Among Moving Obstacles Using Ultrasonic Sensors," Lecture Notes in Computer Science, Robot Soccer World Cup V, vol. 2377, pp. 477-483, 2002.
19 Pierre Lebraly, Eric Royer, Omar Ait-Aider, and Michel Dhome, "Calibration of Non-Overlapping Cameras- Application to Vision-Based Robotics," BMVC, pp: 1-12, 2010.
20 G. Macesau and F. Moldoveanu, "Computer Vision Based Mobile Robot Navigation in Unknown Environments," Bulletin of the Transilvania University of Brasov, Series I: Engineering Sciences, vol. 3, no. 52, 2010.
21 M. Guzel, "Autonomous Vehicle Navigation Using Vision and Mapless Strategies: A Survey," Hindawi Publishing Corporation Advances in Mechanical Engineering, vol. 2013, pp.1-10, 2013.
22 Guilherme N. DeSouza and Avinash C. Kak, "Vision for Mobile Robot Navigation: A Survey," IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 24, no. 2, Feb. 2002.
23 Lionel Heng, Bo Li, and Marc Pollefeys, "CamOdoCal: Automatic Intrinsic and Extrinsic Calibration of a Rig with Multiple Generic Cameras and Odometry," in Proc. of IEEE/RSJ Int. Conf. of Intelligent Robots and Systems, July 18, 2013.
24 J. Shi and C. Tomasi, "Good features to track," in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition CVPR'94, Seattle, June 1994.
25 Gim H. Lee, Bo Li, Marc Pollefeys, and Friedrich Fraundorfer, "Minimal Solutions for Pose Estimation of a Multi-Camera System," in Proc. of Int. Symposium on Robotics Research (ISRR), 2013.
26 S. Ghiasi, E. Bozorgzadeh, K. Nguyen, and M. Sarrafzadeh, "Profiling Accuracy-Latency Characteristics of Collaborative Object Tracking Applications," Journal of VLSI Signal Processing Systems, vol. 42, Issue 1, pp. 43-55, January 2006.   DOI
27 B. Lucas and T. Kanade, "An iterative image registration technique with an application to stereo vision," in Proc. of DARPA Image Understanding Workshop, pp 121-130, April 1981.
28 S. Sinha, J. Frahm, M. Pollefeys and Y. Genc, "Feature tracking and matching in video using programmable graphics hardware," Machine Vision and Applications, vol. 22, Issue 1, pp 207-217, January 2011.   DOI
29 G. Klein and D.Murray, "Parallel tracking and mapping for small AR workspaces," in Proc. of IEEE and ACM Int. Symposium on Mixed and Augmented Reality, pp. 1-10, Washington, DC, USA, 2007.
30 Jun-Sik Kim, M. Hwangbo, and T. Kanade, "Realtime Affine-photometric KLT Feature Tracker on GPU in CUDA Framework," in Proc. of 12th Int. IEEE Conf./ Workshops (ICCV Workshops), on Computer Vision, pp. 886-893, Kyoto, Sept. 27 - Oct. 4 2009.
31 H. Fassold, J. Rosner, P. Schallauer, and W. Bailer, "Realtime KLT Feature Point Tracking for High Definition Video," VaclavSkala and Dietmar Hildebrand, editors, GraVisMa 2009-Computer Graphics, Vision and Mathematics for Scientific Computing, 2010.
32 Bo Li, Lionel Heng, Kevin Koeser, and Marc Pollefeys, "A Multiple-Camera System Calibration Toolbox Using a Feature Descriptor-Based Calibration Pattern," in Proc. of EEE/RSJ Int. Conf. on Intelligent Robots and Systems, 2013.
33 C. McMillen, K. Stubbs, P. Rybski, S. Stoeter, M. Gini, and N. Papanikolopoulos, "Resource Scheduling and Load Balancing in Distributed Robotic Control Systems," Robotics and Autonomous Systems, vol. 44, no. 3-4, pp. 251-259, 2003.   DOI   ScienceOn
34 Michael O. McCracken, "Evaluating Performance of Two Implementations of the Shi & Tomasi Feature Tracker," Department of Computer Science and Engineering, University of California, San Diego, 2008.
35 L. Rai, S. A. Merritt, and W.E. Higgins, "Real-time image-based guidance method for lung-cancer assessment," CVPR'06. IEEE, vol. II, pp., 2437-2444, 2006.
36 V. Lippiello, B. Siciliano and L. Villani, "Position and Orientation Estimation Based on Kalman Filtering of Stereo Images," in Proc. of CCA, pp. 702-707, 2001.