The Journal of Korean Institute of Communications and Information Sciences (한국통신학회논문지)

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지
DOI QR코드

DOI QR Code

Design and Implementation of Multi Exposure Smart Vehicular Camera Applying Auto Exposure Control Algorithm Based on Region of Interest

관심 영역 기반의 자동 노출 조절 알고리즘을 적용한 다중 노출 차량용 스마트 카메라의 설계 및 구현

  • Jeon, Yongsu (Pusan National University Dept. of Electrical and Computer Engineering) ;
  • Park, Heejin (Pusan National University Dept. of Electrical and Computer Engineering) ;
  • Yoon, Youngsub (Pusan National University Dept. of Electrical and Computer Engineering) ;
  • Baek, Yunju (Pusan National University Dept. of Electrical and Computer Engineering)
  • Received : 2016.10.24
  • Accepted : 2017.01.13
  • Published : 2017.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, many researches are carried out for Advanced Driver Assistant Systems(ADAS). Especially, many studies are carried out to analyze the road situation using road images. In order to improve the performance of the road situation analysis, it is necessary to acquire images with appropriate exposure time. In this paper, we design and implement multi exposure smart vehicular camera which provides road traffic information to driver. Proposed device can acquire road traffic information by on-board camera and various sensors. And we propose an auto exposure control algorithm for the road environment to increase accuracy of image recognition. In addition, we also propose the switching ROI method that apply existing ROI techniques to overcome a limited computation power of embedded devices. We developed prototype of multi exposure smart vehicular camera and performed experiments to evaluate proposed auto exposure control algorithm and switching ROI method. The results show that the average accuracy of image recognition increased by 13.45%.

최근 첨단 운전자 보조 시스템에 대한 활발한 연구가 이루어지고 있으며 특히 도로 영상을 활용한 도로 상황 분석에 대한 연구가 활발히 진행되고 있다. 도로 상황 분석 성능을 높이기 위해 좋은 품질의 영상이 필요하고, 이를 위해 적절한 노출 시간으로 영상을 획득할 필요가 있다. 본 논문에서는 온보드 카메라와 다양한 센서들로 주변의 정보를 습득하고 분석하여 운전자에게 정보를 제공해 줄 수 있는 다중 노출 차량용 스마트 카메라를 설계 및 구현하였다. 그리고 도로 환경에 적합한 자동 노출 조절 알고리즘을 고안하여 영상 처리 성능을 높이고자 하였다. 추가적으로 임베디드 장치의 제한된 계산 성능을 보완할 뿐만 아니라 영상 분석의 성능을 더 높일 수 있는 기존 관심 영역 기법을 응용한 관심 영역 전환 기법에 대한 연구를 수행하였다. 제안한 다중 노출 차량용 스마트 카메라의 프로토타입을 구현하여 실제 도로 환경에서 노출 조절 알고리즘과 관심 영역 전환 기법의 성능을 평가하였으며 실험을 통해 제안하는 노출 조절 알고리즘과 관심 영역 전환 기법을 사용하였을 때, 영상 인식의 정확도가 평균 13.45% 증가함을 확인하였다.

Keywords

References

  1. J. B. Yoo and C. Y. Park, "The road reservation scheme in emergency situation for intelligent transportation systems," J. KICS, vol. 36, no. 11, pp. 1346-1356, Nov. 2011. https://doi.org/10.7840/KICS.2011.36B.11.1346
  2. S. H. Son, T. W. Kim, Y. S. Jeon, and Y. J. Baek, "Smart camera technology to support high speed video processing in vehicular network," J. KICS, vol. 40, no. 01, pp. 152-164, Jan. 2015. https://doi.org/10.7840/kics.2015.40.1.152
  3. M. Y. Kim and J. W. Jang, "Implement automobile black box system for proving cause of sudden unintended acceleration," J. Korea Inst. Inf. and Commun. Eng., vol. 18, no. 6, pp. 1429-1434, Jun. 2014. https://doi.org/10.6109/jkiice.2014.18.6.1429
  4. O. M. Lee, I. S. won, S. M. lee, and J. W. Kwon, "On-road car detection system using VD-GMM 2.0," J. KICS, vol. 40, no. 11, pp. 2291-2297, Nov. 2015. https://doi.org/10.7840/kics.2015.40.11.2291
  5. D. S. Shin, S. R. Lee, and J. W. Kwon, "Improvement of lipreading performance using gabor filter for ship environment," J. KICS, vol. 35, no. 7, pp. 598-603, Jul. 2010.
  6. C. K. Cheong, "A high speed road lane detection based on optimal extraction of ROI-LB," J. Broadcast Eng., vol. 14, no. 2, pp. 253-264, Mar. 2009. https://doi.org/10.5909/JBE.2009.14.2.253
  7. T. Li, Y. Song, and T. Mei, "An auto exposure control algorithm based on lane recognition for on-board camera," 2015 IEEE Intell. Veh. Symp. (IV), pp. 851-856, Seoul, Korea, Jun. 2015.
  8. T. Kuno, H. Sugiura, and N. Matoba, "A new automatic exposure system for digital still camera," IEEE Trans. Consumer Electron., vol. 44, no. 1, pp. 192-199, Feb. 1998. https://doi.org/10.1109/30.663747
  9. J. Y. Liang, Y. J. Qin, and Z. L. Hong, "An auto-exposure algorithm for detecting high contrast lighting conditions," in Proc. Int. Conf. ASIC, pp. 725-728, Guilin, China, Oct. 2007.
  10. SAE, Surface vehicle recommended practice, SAE J1939, Jan. 2005.
  11. OpenCV, Retrieved Oct. 20, 2016, from http://opencv.org
  12. NVIDIA Corp., Nvidia cuda compute unified device architecture programming guide, 2014.
  13. M. A. Olson, K. Bostic, and M. Seltzer, "Berkeley DB," in Proc. FREENIX Track: 1999 USENIX Annu. Tech. Conf., Monterey, California, USA, Jun. 1999.
  14. Linuxwireless, Retrieved Oct. 15, 2016, from http://wireless.kernel.org
  15. NVIDIA Corp., NVIDIA jetson TK1 development kit bringing GPU-accelerated computing to embedded systems, 2014
  16. D. Borsetti and J. Gozalvez, "Infrastructure assisted geo-routing for cooperative vehicular networks," in Proc. IEEE Veh. Netw. Conf., pp. 255-262, Jersey City, NJ, Dec. 2010.
  17. Wi-Fi direct, Retrieved Sept. 10, 2016, from http://www.wi-fi.org/discover-wi-fi/wi-fi-direct
  18. Y. S. Jeon, T. W. Kim, S. H. Son, and Y. J. Baek, "Design and implementation of vehicular network based smart camera device to support high speed video processing," in Proc. Symp. KICS, pp. 378-379, Jeju Island, Korea, Jun. 2014.
  19. OpenALPR, Retrieved Sept. 24, 2016, from https://github.com/openalpr/openalpr
  20. S. N. Yang, Y. M. Jun, J. S. Jung, and S. H. Ryu, "An extraction method of number plates for various vehicles using digital signal analysis processing techniques," IEEK - System and Control, vol. 45, no. 3, pp. 12-19, May 2008.