Journal of Auto-vehicle Safety Association (자동차안전학회지)

Korean Auto-vehicle Safety Association (한국자동차안전학회)
권호 표지
DOI QR코드

DOI QR Code

Improved Environment Recognition Algorithms for Autonomous Vehicle Control

자율주행 제어를 위한 향상된 주변환경 인식 알고리즘

  • 배인환 (대구경북과학기술원 융복합대학) ;
  • 김영후 (대구경북과학기술원 융복합대학) ;
  • 김태경 (대구경북과학기술원 융복합대학) ;
  • 오민호 (대구경북과학기술원 융복합대학) ;
  • 주현수 (대구경북과학기술원 융복합대학) ;
  • 김슬기 (대구경북과학기술원 융복합대학) ;
  • 신관준 (대구경북과학기술원 융복합대학) ;
  • 윤선재 (대구경북과학기술원 융복합대학) ;
  • 이채진 (대구경북과학기술원 융복합대학) ;
  • 임용섭 (대구경북과학기술원 융복합대학) ;
  • 최경호 (대구경북과학기술원 융복합대학)
  • Received : 2018.11.30
  • Accepted : 2019.06.13
  • Published : 2019.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

This paper describes the improved environment recognition algorithms using some type of sensors like LiDAR and cameras. Additionally, integrated control algorithm for an autonomous vehicle is included. The integrated algorithm was based on C++ environment and supported the stability of the whole driving control algorithms. As to the improved vision algorithms, lane tracing and traffic sign recognition were mainly operated with three cameras. There are two algorithms developed for lane tracing, Improved Lane Tracing (ILT) and Histogram Extension (HIX). Two independent algorithms were combined into one algorithm - Enhanced Lane Tracing with Histogram Extension (ELIX). As for the enhanced traffic sign recognition algorithm, integrated Mutual Validation Procedure (MVP) by using three algorithms - Cascade, Reinforced DSIFT SVM and YOLO was developed. Comparing to the results for those, it is convincing that the precision of traffic sign recognition is substantially increased. With the LiDAR sensor, static and dynamic obstacle detection and obstacle avoidance algorithms were focused. Therefore, improved environment recognition algorithms, which are higher accuracy and faster processing speed than ones of the previous algorithms, were proposed. Moreover, by optimizing with integrated control algorithm, the memory issue of irregular system shutdown was prevented. Therefore, the maneuvering stability of the autonomous vehicle in severe environment were enhanced.

Keywords

JCOJAX_2019_v11n2_35_f0001.png 이미지

Fig. 1 The experimental platform for the autonomous system

JCOJAX_2019_v11n2_35_f0002.png 이미지

Fig. 2 Temperature change before/after control PC tuning

JCOJAX_2019_v11n2_35_f0003.png 이미지

Fig. 3 Structure of the autonomous vehicles system

JCOJAX_2019_v11n2_35_f0004.png 이미지

Fig. 4 Software architecture of Hye Ahn program

JCOJAX_2019_v11n2_35_f0005.png 이미지

Fig. 8 SVM decision tree

JCOJAX_2019_v11n2_35_f0006.png 이미지

Fig. 9 Grid for SVM feature extraction

JCOJAX_2019_v11n2_35_f0007.png 이미지

Fig. 10 Accuracy of MVP-CS with conventional method by Distance

JCOJAX_2019_v11n2_35_f0008.png 이미지

Fig. 11 Accuracy of MVP-CS and MVP-YOLO by distance

JCOJAX_2019_v11n2_35_f0009.png 이미지

Fig. 12 ROI for obstacle detection

JCOJAX_2019_v11n2_35_f0010.png 이미지

Fig. 13 Setting the length of the ROI

JCOJAX_2019_v11n2_35_f0011.png 이미지

Fig. 14 Setting the offset value

JCOJAX_2019_v11n2_35_f0012.png 이미지

Fig. 15 Setting the candidate of danger point

JCOJAX_2019_v11n2_35_f0013.png 이미지

Fig. 16 Operation principle of obstacle avoid algorithm

JCOJAX_2019_v11n2_35_f0014.png 이미지

Fig. 17 The areas where avoidance algorithm cannot work

JCOJAX_2019_v11n2_35_f0015.png 이미지

Fig. 5 (a) Before and (b) after applying HIX algorithm

JCOJAX_2019_v11n2_35_f0016.png 이미지

Fig. 6 (a) Input Image, (b) ELIX rescan, (c) ILT rescan 1 and (d) ILT rescan 2

JCOJAX_2019_v11n2_35_f0017.png 이미지

Fig. 7 (a) Before and (b) after applying NPC algorithm

Table 1 Specifications of the sensors

JCOJAX_2019_v11n2_35_t0001.png 이미지

Table 2 Detail components of the controller

JCOJAX_2019_v11n2_35_t0002.png 이미지

Table 3 Average processing time of 10 executions

JCOJAX_2019_v11n2_35_t0003.png 이미지

References

  1. 정동규, 김선형, 2016, "지능형 자동차 현황과 향후 전망", 한국정보기술학회지, Vol. 14, No. 2, pp. 21-26.
  2. 이민채, 한재현, 장철훈, 선우명호, 2013, "영상 및 레이저레이더 정보융합을 통한 자율주행자동차의 주행환경인식 및 추적방법", 한국지능시스템학회지, Vol. 23, No. 1, pp. 35-45.
  3. Choi, G., Lee, C., Lee, J., Lim, Y., Seo, J. and Shin, k., 2018, "Study on Sensors and Algorithms for Autonomous Vehicle", ESIT, Vol. 3, No. 80.
  4. Chang, F., Chen, Z, 2014, and Liu, C., "Rapid Multiclass Traffic Sign Detection in High-Resolution Images", IEEE Transactions on Intelligent Transportation Systems, Vol. 15, No. 6, pp. 2394-2403. https://doi.org/10.1109/TITS.2014.2314711
  5. Ahn, H. and Kim, J., 2011, Corporate credit rating using multiclass classification models with order information. World Academy of Science, Engineering and Technology, Vol. 5, No. 12, pp. 1783-1788.
  6. Zhu, Z., Liang, D., Zhang, S., Huang, X., Li, B., Hu, S., 2016, "Traffic-Sign Detection and Classification in the Wild", IEEE Conference on Computer Vision and Pattern Recognition, pp. 2110-2118, doi:10.1109/cvpr.2016.232.
  7. Farhadi, A. and Redmon, J., 2018, "YOLOv3: An incremental improvement", arXiv: 1803.10827.
  8. Timothy Masters, 2015, "Deep Belief Nets in C++ and CUDA C", Apress, Vol. 3.
  9. 이호준, 채흥석, 서호태, 이경수, 2018, "자율주행을 위한 레이더 기반 인지 알고리즘의 정량적 분석", 한국자동차안전학회, Vol. 10, No. 2, pp. 29-35. https://doi.org/10.22680/KASA2018.10.2.029
  10. Han, J., Kim, D., Lee, M. and Sunwoo, M., 2012, "Enhanced road boundary and obstacle detection using a downward-looking LiDAR sensor", IEEE Transactions on Vehicular Technology, Vol. 61, No. 3, pp. 971-985. https://doi.org/10.1109/TVT.2012.2182785