능동 특징점 모델을 이용한 스테레오 영상 기반의 실시간 객체 추적
Stereo Images-Based Real-time Object Tracking Using Active Feature Model
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 논문에서는 스테레오 영상 기반에서 능동 특징점 모델(active feature model)과 광류(optical flow)를 이용한 객체 추적 기술을 제안한다. 스테레오의 기하학적 정보와 변위를 이용하여 관심 객체와 특징점의 2.5차원 이동 정보(translation information)를 계산한다. 이 정보를 이용하여 폐색 객체의 특징점의 이동 정보를 예측하여 추적 성능을 개선하였다. 정형(rigid) 및 비정형(non-rigid) 객체에 실험을 하였다. 실험 결과 복잡한 배경 속에서의 실시간 객체 추적이 가능하였다. 또한 정형, 비정형 객체에 관계없이 추적이 가능 하였으며 폐색 상황에 향상된 결과를 보였다.
Abstract
In this thesis, an object tracking method based on the active feature model and the optical flow in stereo images is proposed. We acquired the translation information of object of interest and the features of object by utilizing the geometric information and depth of stereo images. Tracking performance is improved for the occlude object with this information by predicting the movement information of features of the occlude object. Rigid and non-rigid objects are experimented. From the result of experiment, the OOI can be real-time tracked from complicate back ground. Besides, we got the improved result of object tracking in any occlusion state, no matter what it is rigid or non-rigid object.
참고문헌 (19)
- Kunsoo Huh, "A stereo vision-based obstacle detection system in vehicles", Optics and Lasers in Engineering, 46(2), pp.168~178 (2008)
- D. Comaniciu, "Kernel-based object tracking", IEEE Trans. On Pattern Analysis and Machine Intelligence, 25(5), pp.564~577 (2003)
- R. Plankers, "and Modeling People in Video Sequences", pp.285~302 (2001), Computer Vision and Image Understanding
- S. McKenna, "Tracking Contour Object Using Adaptive Mixture Models", pp.225~231 (1999), Image and Vision Computing
- I. Haritaoglu, "W-4: Real- time surveillance of people and their activities", IEEE Trans. Pattern Anal. Machine Intell., 22, pp.809~830 (2000)
- A. M. Baumberg, "Learning deformable models for tracking human motion", 박사, pp.1995
- T. J. Cootes, "Training models of shape form sets of examples", In British Machine Vision Conference, pp.9~18 (1992)
- Kass, M, "Snake: Active Contour Models", Int’l J. Computer Vision, 1(4), pp.321~331 (1987)
- J.Shi, "Good features to track", In Proceedings of the Conference on Computer Vision and Pattern Recognition, pp.592~600 (1994)
- Detection and Tracking of Point Features, "Carlo Tomasi", Carnegie Mellon University, ~, pp.Technical Report CMU-CS-91-132 (1991)
- T. Tommasini, "Making “Good Features Track Better”", Proc. IEEE Conf. Computer Vision, pp.683~689 (2001)
- Stan Birchfield, "Derivation of Kanade-Lucas-Tomasi Tracking Equation" (1996), Unpublished
- P. J. Bert, "Object Tracking with a Moving Camera", Proc. of Workshop on Visual Motion, pp.201~12 (1989)
- Kim, S. H, "Object Segmentation Algorithm Using Snakes in Stereo Images", Optical Engineering, 45(3) (2006)
- Kim, S. H, "Snake- Based Object Tracking in Stereo Sequences with the Optimization of the Number of Snake Points", ICIP2006, pp.193~196 (2006)
- A.Grun, "Adaptive least squares correlation: a powerful image matching technique", South African Journal of photogrammetry on Remote Sensing and Cartography, pp.175~187 (1985)
- P.Fua, "A parallel stereo algorithm that produces dense depth maps and preserves image features", Machine Vision and Applications, pp.35~49 (1993)
- M.Hannah, "Digital stereo image matching techniques", International Archives of Photogrammetry and Remote Sensing, pp.280~293 (1988)
- M.Hannah, "A system for digital stereo image matching", pp.1765~1770 (1989), Photogrammetric Engineering and Remote Sensing