Pedestrian tracking from a moving vehicle

被引:31
作者
Philomin, V [1 ]
Duraiswami, R [1 ]
Davis, L [1 ]
机构
[1] Univ Maryland, Inst Adv Comp Studies, Comp Vis Lab, College Pk, MD 20742 USA
来源
PROCEEDINGS OF THE IEEE INTELLIGENT VEHICLES SYMPOSIUM 2000 | 2000年
关键词
D O I
10.1109/IVS.2000.898368
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Intelligent vehicles and unattended driving systems of the future will need the ability to recognize relevant traffic participants (such as other vehicles, pedestrians, bicyclists, etc.) and detect dangerous situations ahead of time. An important component of these systems is one that is able to distinguish pedestrians and track their motion to make intelligent driving decisions. The associated computer vision problem that needs to be so had is defection and tracking of pedestrians from a moving camera, which is extremely challenging. Robust pedestrian tracking performance carl be achieved by temporal integration of the data in a probabilistic setting. We employ a shape model for pedestrian and an efficient variant of the Condensation tracker to achieve these objectives. The tracking is performed in the high-dimensional space of shape model parameters which consists of Euclidean transformation parameters and deformation parameters. Our Condensation tracker employs sampling on quasi-random? points, improving its asymptotic complexity, and robustness, and making it amenable to real-time implementation.
引用
收藏
页码:350 / 355
页数:6
相关论文
共 11 条
[1]  
[Anonymous], P EUR C COMP VIS
[2]  
[Anonymous], P EUR C COMP VIS
[3]  
BAUMBERG A, 1994, P EUR C COMP VIS, P299
[4]  
BLAKE A, 1999, IN PRESS ADV NEURAL, V11
[5]  
COOTES TF, 1993, P 4 INT C COMP VIS, P242
[6]  
FRANKE U, 1997, IN PRESS IEEE EXP SP
[7]  
Gavrila D. M., 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision, P87, DOI 10.1109/ICCV.1999.791202
[8]   PROCRUSTES METHODS IN THE STATISTICAL-ANALYSIS OF SHAPE [J].
GOODALL, C .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL, 1991, 53 (02) :285-339
[9]   CHOOSING NODES IN PARAMETRIC CURVE INTERPOLATION [J].
LEE, ETY .
COMPUTER-AIDED DESIGN, 1989, 21 (06) :363-370
[10]   Pedestrian detection using wavelet templates [J].
Oren, M ;
Papageorgiou, C ;
Sinha, P ;
Osuna, E ;
Poggio, T .
1997 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1997, :193-199