DOI QR코드

DOI QR Code

A Study on Improvement of Dynamic Object Detection using Dense Grid Model and Anchor Model

고밀도 그리드 모델과 앵커모델을 이용한 동적 객체검지 향상에 관한 연구

  • Yun, Borin (Dept. of Computer Science and Engineering, Univ. of Inha) ;
  • Lee, Sun Woo (Dept. of Computer Science and Engineering, Univ. of Inha) ;
  • Choi, Ho Kyung (Dept. of Information and Electronic Engineering, Univ. of Mokpo) ;
  • Lee, Sangmin (Dept. of Electronic Engineering, Univ. of Inha) ;
  • Kwon, Jang Woo (Dept. of Computer Science and Engineering, Univ. of Inha)
  • 윤보른 (인하대학교 컴퓨터공학과) ;
  • 이선우 (인하대학교 컴퓨터공학과) ;
  • 최경호 (목포대학교 정보전자공학과) ;
  • 이상민 (인하대학교 전자공학과) ;
  • 권장우 (인하대학교 컴퓨터공학과)
  • Received : 2018.04.09
  • Accepted : 2018.06.13
  • Published : 2018.06.30

Abstract

In this paper, we propose both Dense grid model and Anchor model to improve the recognition rate of dynamic objects. Two experiments are conducted to study the performance of two proposed CNNs models (Dense grid model and Anchor model), which are to detect dynamic objects. In the first experiment, YOLO-v2 network is adjusted, and then fine-tuned on KITTI datasets. The Dense grid model and Anchor model are then compared with YOLO-v2. Regarding to the evaluation, the two models outperform YOLO-v2 from 6.26% to 10.99% on car detection at different difficulty levels. In the second experiment, this paper conducted further training of the models on a new dataset. The two models outperform YOLO-v2 up to 22.40% on car detection at different difficulty levels.

본 논문은, 동적인 객체의 인식률 향상을 위해 고밀도 그리드 모델과 앵커 모델을 제안하였다. 두 가지 실험은 수행하여 제안하는 CNN 모델들을 제안하였다. 첫 번째 실험에 있어서, YOLO-v2모델을 KITTI 데이터 셋에 적용시켜 보았고, 고밀도 그리드 모델과 앵커 모델을 기존 YOLO-v2와 비교하였다. 실험에 있어서, 본 논문에서 제안하는 두 가지 모델은 기존의 YOLO-v2모델에 비하여 '어려움' 난이도의 자동차 검지에 있어서 6.26%에서 10.99%까지 우수한 성능을 나타낸 것을 확인하였다. 두 번째 실험에 있어서는 새로운 데이터 셋을 학습하였고, 두 가지 모델은 기존의 YOLO-v2모델보다 22.4%까지 '어려움' 난이도의 자동차 인식률 향상이 있음을 확인할 수 있었다.

Keywords

References

  1. Eichenseer A.(2016), "A data set providing synthetic and real-world fisheye video sequences," In Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on, pp.1541-1545.
  2. Geiger A.(2012), "Are we ready for autonomous driving? the kitti vision benchmark suite," In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pp.3354-3361.
  3. Molton N.(1998), "A stereo vision-based aid for the visually impaired," Image and vision computing, vol. 16, no. 4, pp.251-263. https://doi.org/10.1016/S0262-8856(97)00087-5
  4. Rao S. K.(2012), Stereo acoustic perception based on real time video acquisition for navigational assistance, arXiv preprint arXiv:1208.1880.
  5. Redmon J.(2016), YOLO9000: better, faster, stronger, arXiv preprint, 1612.
  6. Wong F.(2003), "Application of stereovision in a navigation aid for blind people," In Information, Communications and Signal Processing, 2003 and Fourth Pacific Rim Conference on Multimedia. Proceedings of the 2003 Joint Conference of the Fourth International Conference on, vol. 2, pp.734-737.
  7. World Health Organization, http://www.who.int/mediacentre/factsheets/fs282/en/ 2017.10.
  8. Yun B.(2018), "Dynamic Obstacle Detection to Improve BVI Pedestrian's Navigation Decision using CNNs," Paper presented at Society for Information Display's Display Week 2018, Los Angeles, CA.