Journal of Convergence for Information Technology (융합정보논문지)

Convergence Society for SMB (중소기업융합학회)
권호 표지
DOI QR코드

DOI QR Code

Obstacle Detection and Recognition System for Autonomous Driving Vehicle

자율주행차를 위한 장애물 탐지 및 인식 시스템

  • Han, Ju-Chan (Department of Computer Science, Chungbuk National University) ;
  • Koo, Bon-Cheol (Department of Computer Science, Chungbuk National University) ;
  • Cheoi, Kyung-Joo (Department of Computer Science, Chungbuk National University)
  • 한주찬 (충북대학교 소프트웨어학과) ;
  • 구본철 (충북대학교 소프트웨어학과) ;
  • 최경주 (충북대학교 소프트웨어학과)
  • Received : 2017.11.20
  • Accepted : 2017.12.20
  • Published : 2017.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

In recent years, research has been actively carried out to recognize and recognize objects based on a large amount of data. In this paper, we propose a system that extracts objects that are thought to be obstacles in road driving images and recognizes them by car, man, and motorcycle. The objects were extracted using Optical Flow in consideration of the direction and size of the moving objects. The extracted objects were recognized using Alexnet, one of CNN (Convolutional Neural Network) recognition models. For the experiment, various images on the road were collected and experimented with black box. The result of the experiment showed that the object extraction accuracy was 92% and the object recognition accuracy was 96%.

최근 물체를 인식하기 위해 많은 데이터를 기반으로 학습하여 인식하는 연구가 활성화 되고 있다. 본 논문에서는 도로주행 영상에서 장애물이라고 생각되는 객체를 추출하여 자동차, 사람, 오토바이로 구분하여 인식하는 시스템을 제안한다. 이동한 방향과 크기를 고려한 상태에서 광류 추정 알고리즘을 이용하여 객체를 추출하였으며, 추출한 객체를 CNN(Convolutional Neural Network) 인식 모델 중 하나인 AlexNet을 이용하여 인식하였다. 실험을 위해 도로 위의 다양한 영상을 블랙박스로 수집하여 실험하였고, 실험 결과 객체 추출 정확도는 92%, 객체 인식 정확도는 96%의 결과를 보였다.

Keywords

References

  1. S. J. Choi. (2017). Utilization of Insurance System as a Legal Response to Autonomous Vehicles. Graduate School of Gachon National University, Gyeonggi.
  2. K. I. Lim. (2009). Design of Distributed Control System and Development of Autonomous Driving Algorithm for Unmanned Ground Vehicle. Graduate School of Kookmin National University, Seoul.
  3. S. Y. Han. (2015). The Research of Autonomous Vehicle of Preceding Vehicle Detection Technique using the LRF Sensor and Camera for Effective Obstacle Classification. Graduate School of Kookmin National University, Seoul.
  4. M. C. Kim. (2008). A Vehicle Detection Using Optical Flow At Corner Point of Image. Graduate School of Kyungpook National University, Seoul.
  5. S. Y. Kim. (2003). Automatic Extraction of Central Objects for Object-Based Image Retrieval. Graduate School of Pusan National University, Pusan.
  6. J. H. Kim. (2007). Object based image retrieval using extraction of salient points and image segmentation. Graduate School of Hanyang National University, Seoul.
  7. A. Krizhevsky, I. Sutskever & G. E. Hinton. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, 1106-1114.
  8. B. J. Kim. (2017). License Plate Detection System Using Faster R-CNN method for Outdoor Images. Graduate School of Chonbuk National University, Chonbuk.
  9. J. H. Kang. (2017). Design of Programmable CNN Accelerator for Vehicular Image Recognition. Graduate School of Soongsil National University, Seoul.
  10. M. J. Go. (2017). Detecting vehicles that are illegally driving on road shoulders using faster R-CNN. Graduate School of Yonsei University, Seoul.
  11. M. I. Sarker. (2017). Farm Land Weeds Detection with Region-based Deep Convolutional. Chonbuk National University, Chonbuk.
  12. J. Shi & C. Tomasi. (1994). Good features to track, 593-600. USA : IEEE. DOI : 10.1109/CVPR.1994.323794