3D pose estimation by directly matching polyhedral models to gray value gradients

被引:75
作者
Kollnig, H [1 ]
Nagel, HM [1 ]
机构
[1] FRAUNHOFER INST INFORMAT & DATENVERARBT, D-76131 KARLSRUHE, GERMANY
关键词
D O I
10.1023/A:1007927317325
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This contribution addresses the problem of pose estimation and tracking of vehicles in image sequences from traffic scenes recorded by a stationary camera. In a new algorithm, the vehicle pose is estimated by directly matching polyhedral vehicle models to image gradients without an edge segment extraction process. The new approach is significantly more robust than approaches that rely on feature extraction since the new approach exploits more information from the image data. We successfully tracked vehicles that were partially occluded by textured objects, e.g., foliage, where a previous approach based on edge segment extraction failed. Moreover, the new pose estimation approach is also used to determine the orientation and position of the road relative to the camera by matching an intersection model directly to image gradients. Results from various experiments with real world traffic scenes are presented.
引用
收藏
页码:283 / 302
页数:20
相关论文
共 36 条
[1]  
Bar-Shalom Y., 1988, Tracking and Data Association
[2]   A FRAMEWORK FOR SPATIOTEMPORAL CONTROL IN THE TRACKING OF VISUAL CONTOURS [J].
BLAKE, A ;
CURWEN, R ;
ZISSERMAN, A .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1993, 11 (02) :127-145
[3]   MOTION-BASED RECOGNITION - A SURVEY [J].
CEDRAS, C ;
SHAH, M .
IMAGE AND VISION COMPUTING, 1995, 13 (02) :129-155
[4]   TRACKING LINE SEGMENTS [J].
DERICHE, R ;
FAUGERAS, O .
IMAGE AND VISION COMPUTING, 1990, 8 (04) :261-270
[5]  
DU L, 1993, P 4 INT C COMP VIS I, P632
[6]   CONTOUR EXTRACTION OF MOVING-OBJECTS IN COMPLEX OUTDOOR SCENES [J].
DUBUISSON, MP ;
JAIN, AK .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1995, 14 (01) :83-105
[7]  
Gelb A., 1974, Applied Optimal Estimation
[8]   VISUAL TRACKING OF KNOWN 3-DIMENSIONAL OBJECTS [J].
GENNERY, DB .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1992, 7 (03) :243-270
[9]  
Grimson W.E.L., 1990, OBJECT RECOGNITION C
[10]  
HENRICSSON O, 1994, LECT NOTES COMPUTER, V801, P371