항행 및 항법 : 첨단운전자보조시스템용 이동객체검출을 위한 광학흐름추정기의 설계 및 구현 = Navigation : Design and Implementation of Optical Flow Estimator for Moving Object Detection in Advanced Driver Assistance System

국문 초록 (Abstract)

본 논문에서는 첨단 운전자 보조 시스템 (ADAS; advanced driver assistance system) 용 이동객체검출 (MOD; moving objectdetection)을 위한 광학흐름추정기 (OFE; optical flow estimator) 의 하드웨어 구조 설계 결과를 제시하였다. 광학흐름추정 알고리즘은 차량 환경에서 높은 정확도를 나타내는 광역 최적화 (global optimization) 기반 Brox 알고리즘을 적용하였다. Brox 알고리즘의 에너지 범함수 (energy functional)를 최소화 하는 과정에서 생성되는 Euler-Lagrange 방정식을 풀기 위해 하드웨어 구현에 용이한 Cholesky factorization이 적용되었으며, 메모리 접근율 (memory access rate)를 줄이기 위해 시프트 레지스터 뱅크 (shift registerbank)를 도입하였다. 하드웨어 구현은 Verilog-HDL을 사용하였으며, FPGA 기반 설계 및 검증이 수행되었다. 제안된 광학흐름추정기는 40.4K개의 logic slice 및 155개의 DSP48s, 11,290 Kbit의 block memory로 구현되었다.

다국어 초록 (Multilingual Abstract)

In this paper, the design and implementation results of the optical flow estimator (OFE) for moving object detection (MOD) in advanced driver assistance system (ADAS). In the proposed design, Brox’s algorithm with global optimization is considered, which shows the high performance in the vehicle environment. In addition, Cholesky factorization is applied to solve Euler-Lagrange equation in Brox’s algorithm. Also, shift register bank is incorporated to reduce memory access rate. The proposed optical flow estimator was designed with Verilog-HDL, and FPGA board was used for the real-time verification. Implementation results show that the proposed optical flow estimator includes the logic slices of 40.4K, 155 DSP48s, and block memory of 11,290Kbits.

참고문헌 (Reference)

1 오훈걸, "움직임 예측을 이용한 무인항공기 영상에서의 이동 객체 추적" 한국항행학회 10 (10): 400-405, 2006

2 김대훈, "실시간 다중 객체 인식 및 추적 기법" 한국항행학회 16 (16): 386-393, 2012

3 C. Schnorr, "Segmentation of visual motion by minimizing convex non-quadratic functionals" 1 : 661-663, 1994

4 R. Deriche, "Optical-flow estimation while preserving its discontinuities: A variational approach" 69-80, 1995

5 T. Brox, "High accuracy optical flow estimation based on a theory for warping" 25-36, 2004

6 O. P. Agrawal, "Formulation of Euler–Lagrange equations for fractional variational problems" 272 : 368-379, 2002

7 R. J. LeVeque, "Finite difference methods for ordinary and partial differential equations" Society for Industrial and Applied Mathematics 35-46, 2007

8 B. Horn, "Determining optical flow" 185-203, 1981

9 D. Cheda, "Camera egomotion estimation in the ADAS context" 1415-1420, 2010

10 B. Lucas, "An iterative image restoration technique with an application in stereo vision" 81 : 674-679, 1981

11 Z. Chaohui, "An improved moving object detection algorithm based on frame difference and edge detection" 519-523, 2007

12 C. Stauffer, "Adaptive background mixture models for real-time tracking" 2 : 246-252, 1999

13 J. Kim, "A new nonlinear method for optical flow estimation" 26 (26): 463-470, 2001

14 L. A. Leon, "A PDE model for computing the optical flow" 1349-1356, 1999