DOI QR코드

DOI QR Code

Moving Object Detection and Tracking Techniques for Error Reduction

오인식률 감소를 위한 이동 물체 검출 및 추적 기법

  • Hwang, Seung-Jun (School of Electronics and Information Engineering, Korea Aerospace University) ;
  • Ko, Ha-Yoon (School of Electronics and Information Engineering, Korea Aerospace University) ;
  • Baek, Joong-Hwan (School of Electronics and Information Engineering, Korea Aerospace University)
  • 황승준 (한국항공대학교 항공전자정보공학부) ;
  • 고하윤 (한국항공대학교 항공전자정보공학부) ;
  • 백중환 (한국항공대학교 항공전자정보공학부)
  • Received : 2018.01.10
  • Accepted : 2018.02.23
  • Published : 2018.02.28

Abstract

In this paper, we propose a moving object detection and tracking algorithm based on multi-frame feature point tracking information to reduce false positives. However, there are problems of detection error and tracking speed in existing studies. In order to compensate for this, we first calculate the corner feature points and the optical flow of multiple frames for camera movement compensation and object tracking. Next, the tracking error of the optical flow is reduced by the multi-frame forward-backward tracking, and the traced feature points are divided into the background and the moving object candidate based on homography and RANSAC algorithm for camera movement compensation. Among the transformed corner feature points, the outlier points removed by the RANSAC are clustered and the outlier cluster of a certain size is classified as the moving object candidate. Objects classified as moving object candidates are tracked according to label tracking based data association analysis. In this paper, we prove that the proposed algorithm improves both precision and recall compared with existing algorithms by using quadrotor image - based detection and tracking performance experiments.

본 논문에서는 오인식률 감소를 위한 다중 프레임 특징점 추적 정보 기반 이동 물체 검출 및 추적 알고리즘을 제안한다. 기존의 연구에서는 이동 물체 탐지의 오인식과 추적의 속도 문제가 존재 하였다. 본 연구에서는 이를 보완하기 위해 먼저, 카메라 이동 보상과 물체의 추적을 위해 다중 프레임의 코너 특징점과 옵티컬 플로우를 계산한다. 다음으로 다중 프레임 전-후방향 추적으로 옵티컬 플로우의 추적 오류를 감소시키고, 카메라 이동 보상을 위해 호모그래피와 RANSAC 알고리즘 기반으로 추적된 코너 특징점을 배경영역과 이동 물체 후보 영역으로 구분한다. 변환된 코너 특징점들 중 RANSAC에 의해 제거되는 이상점들을 군집화하고 일정 크기 이상의 이상점 군집 영역을 이동 물체 후보군으로 구분한다. 이동 물체 후보군으로 구분된 물체는 라벨 추적 기반 데이터 상관 분석에 따라 라벨 번호를 할당하고 추적한다. 이동 물체 후보군으로 구분된 물체는 라벨 추적 기반 데이터 상관 분석에 따라 라벨 번호를 할당하고 추적한다. 본 논문에서는 제안한 알고리즘이 기존 알고리즘에 비해 Precision과 Recall 모두 향상됨을 쿼드로터 영상기반 탐지 및 추적 성능 실험으로 확인하였다.

Keywords

References

  1. Kamate, Shreyamsh, and N. Yilmazer, "Application of object detection and tracking techniques for unmanned aerial vehicles," Procedia Computer Science, Vol. 61, pp. 436-441, 2015. https://doi.org/10.1016/j.procs.2015.09.183
  2. Ali, Saad, and M. Shah, "COCOA: tracking in aerial imagery," in Proceedings of SPIE, Orlando:FL, Vol. 6209. 2006.
  3. H. Mao, C. Yang, J. Si and G. P. Abousleman, "Automated multiple target detection and tracking in UAV videos," in Proc. SPIE, Orlando:FL, Vol. 7668, 2010.
  4. Siam, Menna, R. ElSayed, and M. ElHelw, "On-board multiple target detection and tracking on camera-equipped aerial vehicles," in Robotics and Biomimetics (ROBIO), 2012 IEEE International Conference on IEEE, Guangzhou:China, 2012.
  5. Siam, Mennatullah, and M. Elhelw, "Enhanced target tracking in uav imagery with pn learning and structural constraints," in Proceedings of the IEEE International Conference on Computer Vision Workshops, Sydney:Australia, 2013.
  6. R. Canosa, G. R. , et al, "A real-time method to detect and track moving objects(DATMO) from unmanned aerial vehicles(UAVs) using a single camera," Remote Sensing, Vol. 4, pp.1090-1111, 2012. https://doi.org/10.3390/rs4041090
  7. Z. Kalal, J. Matas, and K. Mikolajczyk, "P-N Learning: Bootstrapping Binary Classifiers by Structural Constraints." in IEEE Conference on Computer Vision and Pattern Recognition(CVPR), San Francisco:CA, 2010.
  8. Teutsch, Michael, and W. Kruger. "Detection, segmentation, and tracking of moving objects in UAV videos," in Advanced Video and Signal-Based Surveillance (AVSS), in 2012 IEEE Ninth International Conference on. IEEE, Beijing:China, 2012.
  9. E. Dubrofsky, "Homography estimation," Master, University of British Columbia, Vancouver, 2009.
  10. M. Ester, et al. "A density-based algorithm for discovering clusters in large spatial databases with noise," in KDD Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, Portland:OR, pp. 226-231, 1996.
  11. J. H. Baek "A Study on the Obstacle Recognition and Collision Avoidance of the Rotary wing UAVs," in Korea Aerospace Research Institute, South Korea, Technical Report 2017-025, pp 19-24, 2017.