FPGA-Based Hardware Implementation of Real-Time Optical Flow Calculation

被引:19
|
作者
Seyid, Kerem [1 ]
Richaud, Andrea [1 ]
Capoccia, Raffaele [1 ]
Leblebici, Yusuf [1 ]
机构
[1] Ecole Polytech Fed Lausanne, Microelect Syst Lab, CH-3331015 Lausanne, Switzerland
关键词
Field programmable gate array (FPGA); hardware implementation; hierarchical block matching; optical flow; real-time systems; reconfigurable architectures; PERFORMANCE; ARCHITECTURE; OPTIMIZATION; COMPUTATION; ALGORITHMS; MULTISCALE; SEQUENCES; MOTION;
D O I
10.1109/TCSVT.2016.2598703
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Optical flow calculation algorithms are hard to implement on the hardware level in real-time, due to their complexity and high computational load. Therefore, presented works in the literature focusing on the hardware implementation are limited. In this paper, we present a hierarchical block matching-based optical flow algorithm suitable for real-time hardware implementation. The algorithm estimates the initial optical flow with block matching and refines the vectors with local smoothness constraints in each level. We evaluate the proposed algorithm with novel data sets and provide results compared with the ground truth optical flow. Furthermore, we present a reconfigurable hardware architecture of the proposed algorithm for calculating the optical flow in real-time. The presented system can process 640 x 480 resolution frames at 39 frames/s.
引用
收藏
页码:206 / 216
页数:11
相关论文
共 50 条
  • [1] FPGA-based real-time optical-flow system
    Díaz, J
    Ros, E
    Pelayo, F
    Ortigosa, EM
    Mota, S
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2006, 16 (02) : 274 - 279
  • [2] A Reliable FPGA-based Real-time Optical-flow Estimation
    Abutaleb, M. M.
    Hamdy, A.
    Abuelwafa, M. E.
    Saad, E. M.
    [J]. NRSC: 2009 NATIONAL RADIO SCIENCE CONFERENCE: NRSC 2009, VOLS 1 AND 2, 2009, : 467 - 474
  • [3] Block Matching Based Real-Time Optical Flow Hardware Implementation
    Seyid, Kerem
    Richaud, Andrea
    Capoccia, Raffaele
    Leblebici, Yusuf
    [J]. 2016 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), 2016, : 2206 - 2209
  • [4] FPGA-Based Parallel Hardware Architecture for Real-Time Image Classification
    Qasaimeh, Murad
    Sagahyroon, Assim
    Shanableh, Tamer
    [J]. IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING, 2015, 1 (01) : 56 - 70
  • [5] An FPGA-based Parallel Hardware Architecture for Real-time Eye Detection
    Kim, Dongkyun
    Jung, Junhee
    Thuy Tuong Nguyen
    Kim, Daijin
    Kim, Munsang
    Kwon, Key Ho
    Jeon, Jae Wook
    [J]. JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE, 2012, 12 (02) : 150 - 161
  • [6] Real-Time Emulator of an Induction Motor: FPGA-based Implementation
    Esparza, M. A.
    Alvarez-Salas, R.
    Miranda, H.
    Cabal-Yepez, E.
    Garcia-Perez, A.
    Romero-Troncoso, R. J.
    Osornio-Rios, R. A.
    [J]. 2012 9TH INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING, COMPUTING SCIENCE AND AUTOMATIC CONTROL (CCE), 2012,
  • [7] FPGA-based Hardware Implementation of Optical Flow Constraint Equation of Horn and Schunck
    Rustam, Ruzali
    Hamid, Nor Hisham
    Hussin, Fawnizu Azmadi
    [J]. 2012 4TH INTERNATIONAL CONFERENCE ON INTELLIGENT AND ADVANCED SYSTEMS (ICIAS), VOLS 1-2, 2012, : 790 - 794
  • [8] IMPLEMENTATION OF FREQUENCY-BASED CLASSIFICATION OF DAMAGES IN COMPOSITES USING REAL-TIME FPGA-BASED HARDWARE FRAMEWORK
    Cunha, Adauto P. A.
    Wirtz, Sebastian F.
    Soeffker, Dirk
    Beganovic, Nejra
    [J]. PROCEEDINGS OF THE ASME INTERNATIONAL DESIGN ENGINEERING TECHNICAL CONFERENCES AND COMPUTERS AND INFORMATION IN ENGINEERING CONFERENCE, 2017, VOL 8, 2017,
  • [9] FPGA-Based Real-Time EMTP
    Chen, Yuan
    Dinavahi, Venkata
    [J]. IEEE TRANSACTIONS ON POWER DELIVERY, 2009, 24 (02) : 892 - 902
  • [10] Real time Orthorectification by FPGA-based Hardware Acceleration
    Kuo, David
    Gordon, Don
    [J]. IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XVI, 2010, 7830