Abstract
This paper presents the design and implementation of a feature tracker on an embedded reconfigurable hardware system. Contrary to other works, the focus here is on the efficient hardware/software partitioning of the feature tracker algorithm, a viable data flow management, as well as an efficient use of memory and processor features. The implementation is done on a Xilinx Spartan 3 evaluation board and the results provided show the superiority of our implementation compared to the other works.
References
-
A Bissacco, J Meltzer, S Ghiasi, S Soatto, M Sarrafzadeh, Fast visual feature selection and tracking in a hybrid reconfigurable architecture (UCLA, Los Angeles, Calif, USA, 2004) (http://www, 2004), . cs.ucla.edu/~bissacco/hybridfeatrack.html webcite
-
C Bobda, M Majer, A Ahmadinia, et al. The erlangen slot machine: a highly flexible fpga-based reconfigurable platform. Proceedings of the 13th Annual IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM '05), April 2005, Napa, Calif, USA, 319–320
-
J Chen, D Silver, M Parashar, Real time feature extraction and tracking in a computational steering environment. Proceedings of the High Performance Computing Symposium (HPC '03), March-April 2003, San Diego, Calif, USA (Society for Modeling and Simulation International), pp. 155–160
-
X Feng, P Perona, Real time motion detection system and scene segmentation. in Tech, ed. by . Rep. CIT-CDS-98-004 (California Institute of Technology, Pasadena, Calif, USA, 1998)
-
S Ghiasi, A Nahapetian, HJ Moon, M Sarrafzadeh, Reconfiguration in network of embedded systems: challenges and adaptive tracking case study. Journal of Embedded Computing 1(1), 147–166 (2005)
-
MB Kulaczewski, HJ Siegel, Implementations of a feature-based visual tracking algorithm on two MIMD machines. Proceedings of the International Conference on Parallel Processing, August 1997, Bloomington, Ill, USA, 422–430
-
MB Kulaczewski, HJ Siegel, SIMD and mixed-mode implementations of a visual tracking algorithm. Proceedings of the International Parallel Processing Symposium (IPPS/SPDP '98), March-April 1998, Orlando, Fla, USA, 716–720
-
BD Lucas, T Kanade, An iterative image registration technique with an application to stereo vision. Proceedings of the 7th International Joint Conference on Artificial Intelligence (IJCAI '81), August 1981, Vancouver, BC, Canada, 674–679
-
P Lysaght, FPGAs in the decade after the von Neumann century. Friday workshop at Design, Automation and Test European (DATE '06), March 2006, Munich, Germany
-
D Nister, O Naroditsky, J Bergen, Visual odometry. in Tech, ed. by . Rep. CN5300 (Sarnoff Corporation, Princeton, NJ, USA, 2004)
-
J Shi, C Tomasi, Good features to track. in Tech, ed. by . Rep. TR-93-1399 (Department of Computer Science, Cornell University, Ithaca, NY, USA, 1993)
-
J Shi, C Tomasi, Good features to track. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR '94), June 1994, Seattle, Wash, USA, 593–600
-
C Tomasi, T Kanade, Detection and tracking of point features. in Tech, ed. by . Rep. CMUCS-91-131 (Carnegie Mellon University, Pittsburgh, Pa, USA, 1991)
-
T Zinßer, C Gräßl, H Niemann, Efficient feature tracking for long video sequences. Proceedings of the 26th DAGM Symposium, August-September 2004, Tübingen, Germany, 326–333