대한전자공학회논문지SP (Journal of the Institute of Electronics Engineers of Korea SP)

대한전자공학회 (The Institute of Electronics and Information Engineers)
권호 표지

계층적 KLT 특징 추적기의 하드웨어 구현

A Hardware Implementation of Pyramidal KLT Feature Tracker

  • 발행 : 2009.03.25
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 계층적 KLT 특징 추적기의 하드웨어 구조를 제안한다. 계층적 KLT 특징 추적기(pyramidal Kanade-Lucas-Tomasi feature tracker)는 주로 MPU를 기반으로 구현되어 왔으나 반복연산 과정이 많아 실시간으로 처리하기 어려우므로, 실시간 수행을 위하여 FPGA(Field Programmable Gate Array)를 이용하여 구현하였다. 본 논문에서는 추출되는 특징점의 수를 일정하게 유지하기 위해 입력 영상의 밝기에 적응적으로 임계값을 설정하는 특징점 추출 알고리즘을 제안한다. 또한 계층적 KLT 추적 알고리즘을 메모리의 용량 및 대역폭의 한계를 극복하고, FPGA의 병렬처리 특성에 적합한 구조로 변환한다. 소프트웨어로 실행한 결과와의 비교를 통하여 특징점의 추출 및 추적이 유사한 양상으로 이루어짐을 검증하였고, $720{\times}480$ 영상 입력에 대해 초당 30 프레임의 full frame rate로 추적이 수행됨을 확인하였다.

This paper presents the hardware implementation of the pyramidal KLT(Kanade-Lucas-Tomasi) feature tracker. Because of its high computational complexity, it is not easy to implement a real-time KLT feature tracker using general-purpose processors. A hardware implementation of the pyramidal KLT feature tracker using FPGA(Field Programmable Gate Array) is described in this paper with emphasis on 1) adaptive adjustment of threshold in feature extraction under diverse lighting conditions, and 2) modification of the tracking algorithm to accomodate parallel processing and to overcome memory constraints such as capacity and bandwidth limitation. The effectiveness of the implementation was evaluated over ones produced by its software implementation. The throughput of the FPGA-based tracker was 30 frames/sec for video images with size of $720{\times}480$.

키워드

참고문헌

  1. J. K. Suhr, K. H. Bae, J. H. Kim, "Free parking space detection using optical flow-based euclidean 3D reconstruction," IAPR Conf on Machine Vision Application(MVA'07), pp. 563-566, May 2007
  2. C. Tomasi and T. Kanade, "Detection and tracking of point features," Technical Report CMU-CS-91-132, Carnegie Mellon University, April 1991
  3. J. Y. Bouguet, "Pyramidal implementation of the Lucas Kanade feature tracker description of the algorithm," Intel Corporation, 2003
  4. P. Arato, G. Kocza, I. Lovanyi and L. Vajta, "Hardware-software codesing of feature tracking algorithms," in Intelligent Engineering Systems(INES 2008), pp. 41-45, February 2008
  5. P. D. Fiore, D. Kottke, W. Krawiec and C. David, "Efficient feature tracking with application to camera motion estimation," in Signals, Systems and Computers, pp. 949-953, November 1998
  6. C. Harris and M. J. Stephens, "A combined corner and edge detector," in Alvey Vision Conference, pp. 147-152, 1988
  7. C. Schmid, R.Mohr and C. Bauckhage, "Evaluation of interest point detectors," International Journal of Computer Vision, pp. 151-172, June 2000 https://doi.org/10.1023/A:1008199403446
  8. S. Birchfield, "KLT:An implementation of the Kanade-Lucas-Tomasi feature tracker," http://www.ces.clemson.edu/~stb/klt, November 2005
  9. C. Cabani and W. J MacLean, "A proposed pipelined-architecture for FPGA-based affine-invariant feature detectors," in Proc. of IEEE Conf on Computer Vision and Pattern Recognition Workshop January 2006
  10. S. Ghiasi, H. J. Moon, A. Nahapetian and M. Sarrafzadeh, "Collaborative and reconfigurable object tracking," Kluwer Journal of Supercomputing, Vol. 30, No 3, pp. 213-238, December 2004 https://doi.org/10.1023/B:SUPE.0000045210.48347.ee
  11. W. J. MacLean, "An evaluation of the suitability of FPGAs for embedded vision systems," in the first IEEE Workshop on Embedded Computer Vision, CVPR 2005, June 2005