Journal of IKEEE (전기전자학회논문지)

Institute of Korean Electrical and Electronics Engineers (한국전기전자학회)
권호 표지
DOI QR코드

DOI QR Code

Real-time FCWS implementation using CPU-FPGA architecture

CPU-FPGA 구조를 이용한 실시간 FCWS 구현

  • Han, Sungwoo (Dept. of Electronics and Communications Engineering, Kwangwoon University) ;
  • Jeong, Yongjin (Dept. of Electronics and Communications Engineering, Kwangwoon University)
  • Received : 2017.12.15
  • Accepted : 2017.12.29
  • Published : 2017.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Advanced Driver Assistance Systems(ADAS), such as Front Collision Warning System (FCWS) are currently being developed. FCWS require high processing speed because it must operate in real time while driving. In addition, a low-power system is required to operate in an automobile embedded system. In this paper, FCWS is implemented in CPU-FPGA architecture in embedded system to enable real-time processing. The lane detection enabled the use of the Inverse Transform Perspective (IPM) and sliding window methods to operate at fast speed. To detect the vehicle, a Convolutional Neural Network (CNN) with high recognition rate and accelerated by parallel processing in FPGA is used. The proposed architecture was verified using Intel FPGA Cyclone V SoC(System on Chip) with ARM-Core A9 which operates in low power and on-board FPGA. The performance of FCWS in HD resolution is 44FPS, which is real time, and energy efficiency is about 3.33 times higher than that of high performance PC enviroment.

최근 운전자의 편의와 안전을 위해 전방 차량 추돌 감지 시스템(Front Collision Warning System : FCWS)과 같은 다양한 운전자 보조 시스템(Advanced Driver Assistance System : ADAS)이 개발되고 있다. FCWS는 주행 중 실시간으로 동작해야 하기 때문에 높은 처리속도를 필요로 한다. 또한 자동차의 전장화에 따라 FCWS를 차량용 임베디드 시스템에서 동작시키기 위해 저전력 시스템이 필요하다. 본 논문에서는 FCWS를 CPU-FPGA 구조에서 실시간 처리가 가능하도록 구현하였다. 차선 검출은 Inverse Transform Perspective(IPM)와 슬라이딩 윈도우 방식을 이용하여 CPU에서도 빠른 속도로 동작할 수 있도록 하였다. 차량검출은 높은 인식률을 가지는 Convolutional Neural Network(CNN)을 이용하였고, FPGA에서 병렬처리로 가속하였다. 제안하는 구조는 저전력으로 동작하는 ARM-Core A9과 FPGA를 내장한 Intel FPGA Cyclone V SoC(System on Chip)에서 검증하였다. HD해상도에서 FCWS는 44FPS로 실시간으로 동작하며, 고성능 PC 환경보다 처리속도 대비 에너지 효율이 약 3.33배 높은 것을 확인했다.

Keywords

References

  1. Karen Aldana, "NHTSA Announces Model Year 2012 Vehicles to be Rated Under Government 5-Star Safety Ratings Program," https://www.nhtsa.gov/staticfiles/communications/pdf/nhtsa1711.pdf
  2. Gao, Yongbin, and Hyo Jong Lee. "Vehicle Make Recognition Based on Convolutional Neural Network," Information Science and Security (ICISS), 2015 2nd International Conference on. IEEE, 2015. DOI:10.1109/ICISSEC.2015.7371039
  3. A. Krizhevsky, I. Sutskever, G. E. Hinton and et al., "ImageNet classification with deep convolutional neural networks," in Proc. Neural Information Processing Systems (NIPS'12), 2012
  4. Cuneyt Akinlar and Cihan Topal, "EDLines: A real-time line segment detector with a false detection control," Pattern Recognition Letters, vol. 32, no. 13, pp. 1633-1642, 2011 DOI:10.1016/j.patrec.2011.06.001
  5. X. Lu, J. Yao, K. Li, and L. Li, "Cannylines: A parameter-free line segment detector," In 2015 IEEE International Conference on Image Processing (ICIP), pp.507-511, Sept, 2015. DOI:10.1109/ICIP.2015.7350850
  6. Massimo Bertozzi and Alberto Broggi, "Real-Time Lane and Obstacle Detection on the GOLD System," IEEE International Symposium on Computer Vision, 1995 DOI:10.1109/IVS.1996.566380
  7. H.Tan, Y. Zhou, Y.Zhu, D.Yao, and K. Li, "A novel curve lane detection based on Improved River Flow and RANSAC," In Intelligent Transportation Systems (ITSC), 2014 IEEE 17th International Conference on, pp.133-138. IEEE, 2014 DOI:10.1109/ITSC.2014.6957679
  8. J.Wang, T.Mei, B. Kong, and H.Wei, "An approach of lane detection based on Inverse Perspective Mapping," In Intelligent Transportation Systems (ITSC), 2014 IEEE 17th International Conference on pp. 35-38. IEEE, 2014. DOI:10.1109/ITSC.2014.6957662
  9. Kaur, Gurjyot, and Amit Chhabra, "Curved Lane Detection using Improved Hough Transform and CLAHE in a Multi-Channel ROI," International Journal of Computer Applications 122.13 , 2015.
  10. Nur Shazwani A "Vehicle Detection Based on Underneath Vehicle Shadow Using Edge Features," 2016 6th IEEE International Conference on Control System, Computing and Engineering,Penang, Malaysia, pp.25-27, Nov, 2016. DOI:10.1109/ICCSCE.2016.7893608
  11. C. Cortes and V. Vapnik, "Support-Vector Network," Machine Learning, Vol. 20, No. 3 pp.273-297, May, 1995. DOI:10.1007/BF00994018
  12. Hao Yu, "Vision-based Lane Marking Detection and Moving Vehicle Detection," 2016 8th International Conference on Intelligent Human-Machine Systems and Cybernetics, 2016. DOI: 10.1109/IHMSC.2016.240
  13. Sungji Han, "Vehicle Detection Method Using Haar-like Feature on Real Time System," World Academy of Science, Engineering and Technology 59, 2009.
  14. Zhipeng Di, "Forward Collision Warning System Based on Vehicle Detection and Tracking," 2016 International Conference on Optoelectronics and Image Processing, 2016. DOI: 10.1109/OPTIP.2016.7528490
  15. O. Russakovsky et. al, "ImageNet Large Sclae Visual Recognition Challenge," International Journal of Computer Vision, Vol.115, No.3, pp.211-252, Dec.2015. DOI:10.1007/s11263-015-0816-y
  16. D. Strigl, K. Kofler, and S. Podlipnig. "Performance and scalability of gpu-based convolutional neural networks. Parallel," Distributed, and Network-Based Processing, Euromicro Conference on, 0:317-324, 2010 DOI: 10.1109/PDP.2010.43
  17. Kim, Jin-Soo, "Effective Road Distance Estimation Using a Vehicle-attached Black Box Camera," Journal of the Korea Institute of Information and Communication Engineering. vol.19, no.3, pp.651-658, 2015. DOI : 10.6109/jkiice.2015.19.3.651
  18. Chris Rauer and George S.Powley "Accelerating Genomics Research with OpenCLTM and FPGAs," https://www.altera.com/content/dam/altera-www/global/en_US/pdfs/literature/wp/wp-accelerating-genomics-opencl-fpgas.pdf
  19. Kim ll-Ho, Kim Gyeong-Hwan, "FPGA-DSP Based Implementation of Lane and Vehicle Detection," The Journal of Korean Institute of Communications and Information Sciences,vol.36, no.12, pp.727-737, Dce. 2011. https://doi.org/10.7840/KICS.2011.36C.12.727
  20. Bang,Ji-Won,Jeong,Yong-Jin, "A Real-Time Hardware Design of CNN for Vehicle Detection," j.inst.Korean.electr.electron.eng. vol.20, no.4, pp.351-360, Dec. 2016. DOI:10.7471/ikeee.2016.20.4.351