3-D POSITION SENSING USING A PASSIVE MONOCULAR VISION SYSTEM

被引：14

作者：

CARDILLO, J

SIDAHMED, MA

机构：

[1] Dept of Electr Eng, Univ of Windsor,, Ont

来源：

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 1991年 / 13卷 / 08期

关键词：

CAMERA CALIBRATION; COMPUTER VISION; DEPTH RECOVERY; FOCUS BLUR; IMAGE ANALYSIS; ROBOT VISION SYSTEM;

D O I：

10.1109/34.85671

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Passive monocular 3-D position sensing is made possible by a new calibration scheme that relates depth to focus blur through a composite lens and aperture model. A geometric model of the camera's position and orientation in space is used to transform the camera's imaging coordinates into world coordinates. Position accuracies comparable to those in stereo based vision systems are possible without the need for solving the difficult point of correspondence problem.

引用

页码：809 / 813

页数：5

共 7 条

[1] [Anonymous], 1965, PRINCIPLES OPTICS
[2] CARDILLO J, 1988, THESIS U WINDSOR WIN
[3] KIM YC, 1987, IEEE J ROBOT AUTOM, V3, P361
[4] AN ALGORITHM FOR LEAST-SQUARES ESTIMATION OF NONLINEAR PARAMETERS
MARQUARDT, DW
[J]. JOURNAL OF THE SOCIETY FOR INDUSTRIAL AND APPLIED MATHEMATICS, 1963, 11 (02): : 431 - 441
[5] A NEW SENSE FOR DEPTH OF FIELD
PENTLAND, AP
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1987, 9 (04) : 523 - 531
[6] RAY SF, 1976, LENS ACTION
[7] Subbarao M., 1988, Second International Conference on Computer Vision (IEEE Cat. No.88CH2664-1), P149, DOI 10.1109/CCV.1988.589986

← 1 →