Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Driving Condition based Dynamic Frame Skip Method for Processing Real-time Image Recognition Methods in Smart Driver Assistance Systems

스마트 운전자 보조 시스템에서 영상인식기법의 실시간 처리를 위한 운전 상태 기반의 동적 프레임 제외 기법

  • Son, Sanghyun (R&D Center, SEMES) ;
  • Jeon, Yongsu (Department of Electrical and Computer Engineering, Pusan National University) ;
  • Baek, Yunju (School of Computer Science and Engineering, Pusan National University)
  • Received : 2017.08.18
  • Accepted : 2017.10.15
  • Published : 2018.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

According to evolution of technologies, many devices related to various applications were researched. The advanced driver assistance system is a famous technique effected from the evolution. The technique of driver assistance uses image recognition methods to collect exactly information around the vehicle. The computing power of driver assistance device has become more improved than in the past. However, it's difficult that processed various recognition methods at real-time. We propose new frame skip method to process various recognition methods at real-time in the limited hardware. In the previous researches, frame skip rate was set up static values, thus the number of processed frames through recognition methods was smaller. We set up the frame skip rate dynamically using a driving condition of vehicle through speed and acceleration value, in addition, the number of processed frames was maximized. The performance is improved more 32.5% than static frame skip method.

기술의 발전에 따라 다양한 응용을 위한 장치가 연구 및 개발되고 있으며 운전자 보조 시스템은 그 중 대표적인 기술이다. 운전자 보조 시스템 기술은 차량 주변의 정보를 인식하기 위해 영상인식 기법을 사용한다. 차량에 적용되는 운전자 보조 장치는 계산시간이 오래 걸리는 다수의 영상인식기법을 실시간으로 처리하는데 어려움이 존재한다. 이를 위해 제한된 하드웨어에서 영상인식 기법의 실시간 처리를 위한 동적 프레임 제외 기법을 제안한다. 기존의 연구에서 프레임 제외는 처리시간에 비례하여 정적으로 설정되었으며 처리 할 수 있는 영상인식기법의 수가 적음을 알 수 있다. 차량의 속도와 가속도를 통해 주행상태를 파악하여 동적으로 프레임 제외률을 설정하고 그에 맞게 영상인식 기법을 처리하여 그 수를 최대화시켰다. 실험을 통해 처리 수가 정적 기법에 비해 32.5% 상승함을 확인하였다.

Keywords

References

  1. L. D. Burns, "Sustainable mobility : a vision of our transport future," Nature, vol. 497, no. 7448, pp. 181-182, May 2013. https://doi.org/10.1038/497181a
  2. D. Stavens and S. Thrun, "A self-supervised terrain roughness estimator for off-road autonomous driving," In Proceedings of the Twenty-Second Conference on Uncertainty in Artificial Intelligence (UAI), United State, pp. 469-476, June 2012.
  3. S. Borhade, M. Shah, P. Jadhav, D. Rajurkar, and A. Bhor, "Advanced driver assistance system," In Proceedings of the International Conference on Sensing Technology (ICST), India, pp. 718-722, Dec. 2012.
  4. S. Son, T. Kim, Y. Jeon, and Y. Baek, "Smart camera technology to support high speed video processing in vehicluar network," The Journal of Korean Institute of Communications and Information Sciences, vol. 40, no.1, pp. 466-474, Jan. 2015.
  5. S. Son and Y. Baek, "Design and implementation of real-time vehicular camera for driver assistance and traffic congestion estimation," Sensors, vol. 15, no.8, pp. 20204-20231, Aug. 2015. https://doi.org/10.3390/s150820204
  6. J. Becker, M. B. A. Colas, S. Nordbruch, and M. Fausten, "Bosch's vision and roadmap toward fully autonomous driving," Road Vehicle Automation, Springer International Publishing, pp. 49-59, June 2014.
  7. D. Geronimo, A. M. Lopez, A. D. Sappa, and T. Graf, "Survey of pedestrian detection for advanced driver assistance systems," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, no. 7, pp. 1239-1258, May 2010. https://doi.org/10.1109/TPAMI.2009.122
  8. M. Kang, Y. Kim, "Road Lane and Vehicle Distance Recognition using Real-time Analysis of Camera Images," Journal of the Korea Institute of Information and Communication Engineering, vol. 16, no. 12, pp. 2665-2674. Dec. 2012. https://doi.org/10.6109/jkiice.2012.16.12.2665
  9. H. Oh, E. Rhee, "Enhancement of Car License Plate Recognition Rate and Security with Rotation Algorithm," Journal of Security Engineering, vol.13, no.2, pp. 83-90, Apr. 2016. https://doi.org/10.14257/jse.2016.04.01
  10. S. David and A. Manzalini, "Horizon 2020 and beyond: on the 5G operating system for a true digital society," IEEE Vehicular Technology Magazine, vol. 10, no. 1, pp. 32-42, Feb. 2015. https://doi.org/10.1109/MVT.2014.2380581
  11. V. Balisavira and V. K. Pandey, "Real-time object detection by road plane segmentation technique for ADAS," In Proceeding of IEEE International Conference of Signal Image Technology and Internet Based Systems (SITIS), Italy, pp. 161-167, Nov. 2012.
  12. C. Arth, F. Limberger, and H. Bischof, "Real-time license plate recognition on an embedded DSP-platform," In Proceeding of IEEE Conference on Computer Vision and Pattern Recognition, (CVPR), Las vegas: NV, pp. 1-8, June 2007.
  13. NVIDIA Jetson development kit information [internet]. Available: https://developer.nvidia.com/jetson-tk1.
  14. S. Son and Y. Baek "Real-time Video Recognition and Data Dissemination in Smart Driver Assistance Systems," Ph. D. dissertation, Pusan National University, Busan, 2016.