Quality, Reliability, Security and Robustness in Heterogeneous Networks. 9th International Conference, QShine 2013, Greader Noida, India, January 11-12, 2013, Revised Selected Papers

Research Article

Real Time Object Tracking: Simulation and Implementation on FPGA Based Soft Processor

Download
510 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-37949-9_38,
        author={Manoj Pandey and Dorothi Borgohain and Gargi Baruah and J. Ubhi and Kota Raju},
        title={Real Time Object Tracking: Simulation and Implementation on FPGA Based Soft Processor},
        proceedings={Quality, Reliability, Security and Robustness in Heterogeneous Networks. 9th International Conference, QShine 2013, Greader Noida, India, January 11-12, 2013, Revised Selected Papers},
        proceedings_a={QSHINE},
        year={2013},
        month={7},
        keywords={Kernel Mean Shift Real Time Tracking EDK FPGA Spartan6},
        doi={10.1007/978-3-642-37949-9_38}
    }
    
  • Manoj Pandey
    Dorothi Borgohain
    Gargi Baruah
    J. Ubhi
    Kota Raju
    Year: 2013
    Real Time Object Tracking: Simulation and Implementation on FPGA Based Soft Processor
    QSHINE
    Springer
    DOI: 10.1007/978-3-642-37949-9_38
Manoj Pandey1,*, Dorothi Borgohain2, Gargi Baruah2, J. Ubhi3, Kota Raju2
  • 1: B K Birla Institute of Engineering and Technology
  • 2: Central Electronics Engineering Research Institute (CEERI) CSIR-CEERI
  • 3: Sant Longowal Institute of Engineering and Technology
*Contact email: manoj2pandey@yahoo.com

Abstract

Adaptive systems are being easy to design using reconfiguration facility on Field programmable gate arrays (FPGAs). In this paper, Kernel based Mean shift algorithm is used for tracking a moving object. First it is simulated on Matlab and then implemented on microblaze soft processor based FPGA board. Tracking is observed for two similar objects crossing each other moving with uniform speed in a stored video as well as real time video. Object tracking, when it comes to implement on pure software (SW) in real time becomes difficult task due to certain limitations of SW. This paper shows how the mean shift algorithm is implemented on Xilinx Spartan 6 FPGA board using EDK. Once the complete algorithm is implemented on microblaze soft processor then some of the mathematical functions of algorithm are calculated on hardware to use HW-SW co-designing methodology to enhance the performance of the system.