The Journal of Korean Institute of Information Technology (한국정보기술학회논문지)

Korean Institute of Information Technology (한국정보기술학회)
권호 표지
DOI QR코드

DOI QR Code

System Design and Implementation with Improved FCWS Detection Speed

FCWS 검출속도 향상을 위한 시스템 설계 및 구현

  • Yu, Hwan-Shin (Dept. of Automotive Mechanical Engineering, Howon University)
  • 유환신 (호원대학교 자동차기계공학과)
  • Received : 2017.11.29
  • Accepted : 2017.12.21
  • Published : 2018.01.31
⟨ Previous Next ⟩

Abstract

Recently, ADAS (Advanced Driver-Assistance Systems) system has been installed to assist the safe operation of the vehicle and improve the driver's convenience. LDWS (Lane departure warning system) and FCWS (Forward collision warning system) are the core of the technology. Among these, FCWS has been evaluated as a key assistive technology to prevent vehicle collision. Therefore, many algorithms for improving the detection speed have been developed and tested, and actual detection algorithms have been commercialized. The design of the entire embedded system from the input of the actual image to the final recognition must be contemplated and the processing speed should be improved as well. It has the best effect by combining hardware and BSP driver (Board Support Package) and algorithm. In this paper, we propose the design of a system that optimizes the FCWS speed by analyzing the hardware structure of the embedded system.

최근 차량의 안전운행을 보조하고 운전자의 편의성을 향상시키기 위해 ADAS(Advanced driver-assistance systems) 시스템이 장착되고 있다. LDWS(Lane departure warning system)과 FCWS(Forward collision warning system)이 그 기술의 핵심이다. 이 중 FCWS는 차량의 충돌사고를 방지하기 위한 핵심 보조 기술로 평가받고 있다. 이에 검출속도의 향상을 위한 많은 알고리즘들이 개발되고 실험되고 있으며, 실제 검출 알고리즘들이 상용화 되고 있다. 실제 영상의 입력부터 최종 인식까지의 임베디드 시스템 전체의 설계가 고민되어야 하며, 처리속도가 같이 향상 되어야 한다. 이는 하드웨어, BSP(Board Support Package) driver와 알고리즘이 결합하여 최상의 효과를 본다. 본 논문에서는 임베디드 시스템의 OS별 특성을 파악하고, 하드웨어 설계 구조를 분석하여, FCWS 속도를 최적화한 시스템의 설계를 제안한다.

Keywords

Acknowledgement

Supported by : 호원대학교

References

  1. Dong-Gyu Jeong and Seon-Hyung Kim, “Intelligent Vehicle Status and Future Outlook,” Journal of KIIT, Vol. 14, No. 2, pp. 21-26, Dec. 2016.
  2. Hyo-Kyun Jeong, Myung-Jin Lee, and Yong-Jin Jeong, “FPGA iimplementation of AVM-based lane departure warning system,” Journal of KIIT, Vol. 12, No. 11, pp. 59-68, Nov. 2014.
  3. Seunghan Yang, Bongsob Song, and Jaeyong Um, “Radar and vision sensor fusion for primary vehicle detection,” Journal of Institute of Control, Robotics and Systems, Vol. 16, No. 7, pp. 639-645, Jul. 2010. https://doi.org/10.5302/J.ICROS.2010.16.7.639
  4. Felipe Jimenez, Jose E. Naranjo, Oscar Gomez, and Jose J. Anaya, “Vehicle tracking for an evasive manoeuvres assistant using low-cost ultrasonic sensors,” Sensors 2014, Vol. 13, No. 10, pp. 22689-22705, Nov. 2014.
  5. Chung-Cheng Chiu, Meng-Liang Chung, and Wen-Chung Chen, “Real-Time front vehicle detection algorithm for an asynchronous binocular system,” Journal of information science and engineering, Vol. 26, No. 3, pp. 735-752, May 2010.
  6. Longhui Gang, Mingheng Zhang, Xiudong Zhao, and Shuai Wang, “Improved genetic algorithm optimization for forward vehicle detection problems,” Information 2015, Vol. 6, No. 3, pp. 339-360, Jul. 2015.
  7. Hwan-Shin Yu, “The lane departure warning algorithm optimized for automotive black-boxes and compact system,” Journal of KIIT, Vol. 13, No. 10, pp. 9-15, Oct. 2015.
  8. Hwan-Shin Yu and Eui-Bung Jeoung, “The optimized file system designed for vehicle black box system,” Journal of KIIT, Vol. 14, No. 2, pp. 1-6, Feb. 2016.
  9. Hwan-Shin Yu and Eui-Bung Jeoung, “The lane recognition enhancement algorithms of around view monitoring system based on automotive black boxes,” Journal of KIIT, Vol. 15, No. 1, pp. 45-53, Jan. 2017.