CU-Track: A Multi-Camera Framework for Real-Time Multi-Object Tracking

Abstract:

This paper presents CU-Track, a multi-camera framework for real-time multi-object tracking. The developed framework includes a processing unit, the target object, and the multi-object tracking algorithm. A PC-cluster has been developed as the processing unit of the framework to process data in real-time. To setup the PC-cluster, two PCs are connected by using PCI interface cards that memory can be shared between the two PCs to ensure high speed data transfer and low latency. A novel mechanism for PC-to-PC communication is proposed. It is realized by a dedicated software processing module called the Cluster Module. Six processing modules have been implemented to realize system operations such as camera calibration, camera synchronization and 3D reconstruction of each target. Multiple spherical objects with the same size are used as the targets to be tracked. Two configurations of them, active and passive, can be used for tracking by the system. The algorithm based on Kalman filter and nearest neighbor searching is developed for multi-object tracking. Two applications have been implemented on the system, which confirm the validity and effectiveness of the developed framework.

• Periodical: Applied Mechanics and Materials (Volume 415)
• Pages: 325-332
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.415.325
• Online since: September 2013
• Authors: Pongsakon Bamrungthai, Viboon Sangveraphunsiri
• Keywords: Multi-Camera Framework, Pc-Cluster, Real-Time Multi-Object Tracking

References

[1] A. Yilmaz, O. Javed and M. Shah: Object Tracking: A Survey, ACM Computing Surveys (CSUR), Vol. 38, No. 4. (2006).

DOI: 10.1145/1177352.1177355

[2] M. Liem and D.M. Gavrila: Multi-person Tracking with Overlapping Cameras in Complex, Dynamic Environments, In Proc. of the British Machine Vision Conference (BMVC) (2009).

DOI: 10.5244/c.23.87

[3] A.D. Straw, K. Branson, T.R. Neumann and M.H. Dickinson: Multi-Camera Real-Time Three-Dimensional Tracking of Multiple Flying Animals, J. R. Soc. Interface, Vol. 8 (2011), pp.395-409.

DOI: 10.1098/rsif.2010.0230

[4] H. Firouzi and H. Najjaran: Detection and Tracking of Multiple Similar Objects Based on Color-Pattern, AIS, Vol. 6752 of Lecture Notes in Computer Science, pp.273-283. Springer, (2011).

DOI: 10.1007/978-3-642-21538-4_27

[5] P. Santos, A. Stork, A. Buaes and J. Jorge: PTrack: Introducing a Novel Iterative Geometric Pose Estimation for a Marker-based Single Camera Tracking System, In Proc. of the IEEE Virtual Reality (2006), pp.143-150.

DOI: 10.1109/vr.2006.114

[6] M. Loaiza, A. Raposo and M. Gattass: A Novel Optical Tracking Algorithm for Point-Based Projective Invariant Marker Patterns, ISVC 2007, Part I. LNCS, Vol. 4841, p.160–169. Springer, Heidelberg (2007).

DOI: 10.1007/978-3-540-76858-6_16

[7] R.C. Gonzalez and R.E. Woods: Digital Image Processing, 3rd edition, Upper Saddle River, New Jersey, USA: Prentice Hall (2008).

[8] P. Zhou, Y. Liu and Y. Wang: Adaptive Real-Time Labeling and Recognition of Multiple Infrared Markers Using FPGA, ICIG (2009), pp.983-988.

DOI: 10.1109/icig.2009.117

[9] F. C. Chu and B. C. Chang: Automatic Visual Tracking Control System Using Embedded Computers, In Proc. of the 2005 IEEE International Conference on Mechatronics, July (2005), pp.108-112.

DOI: 10.1109/icmech.2005.1529236

[10] D. Arita, S. Yonemoto and R. Taniguchi: Real-time Computer Vision on PC-Cluster and Its Application to Real-time Motion Capture, In Proc. of IEEE Workshop on Computer Architectures for Machine Perception (2000), pp.205-214.

DOI: 10.1109/camp.2000.875979

[11] D. Arita and R. Taniguchi: RPV-II: A Stream-Based Real-Time Parallel Vision System and Its Application to Real-Time Volume Reconstruction, In Proc. of Second International Workshop on Computer Vision System, July (2001), pp.174-189.

DOI: 10.1007/3-540-48222-9_12

[12] K. Uttamang and V. Sangveraphunsiri: Multi-Camera System using PC-Cluster for Real-Time 3-D Pose Estimation, Thammasat Int. J. Sc. Tech., 12(2), April-June (2007), pp.52-63.

[13] P. Bamrungthai and V. Sangveraphunsiri: A PC-Cluster based Multi-Camera System for Real-Time Multiple Objects Tracking, Asian International Journal of Science and Technology in Production and Manufacturing Engineering, 3(4), (2010), pp.57-64.

[14] F. Chang, C.J. Chen and C.J. Lu: A Linear-Time Component-Labeling Algorithm using Contour Tracing Technique, Comput. Vis. Image Underst, 93(2), (2004), pp.206-220.

DOI: 10.1016/j.cviu.2003.09.002