RECURSIVE ESTIMATION OF MOTION, STRUCTURE, AND FOCAL LENGTH

被引：268

作者：

AZARBAYEJANI, A

PENTLAND, AP

机构：

[1] Media Laboratory, Massachusetts Institute o Technology, Cambridge, MA

来源：

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 1995年 / 17卷 / 06期

关键词：

STRUCTURE FROM MOTION; CAMERA MODEL; CAMERA CALIBRATION; RECURSIVE ESTIMATION; 3D REPRESENTATION; 3D MODELING;

D O I：

10.1109/34.387503

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present a formulation for recursive recovery of motion, pointwise structure, and focal length from feature correspondences tracked through an image sequence. In addition to adding focal length to the state vector, several representational improvements are made over earlier structure from motion formulations, yielding a stable and accurate estimation framework which applies uniformly to both true perspective and orthographic projection. Results on synthetic and real imagery illustrate the performance of the estimator.

引用

页码：562 / 575

页数：14

共 32 条

[21] Oliensis J., Thomas J.I., Incorporating motion error in multi-frame structure from motion, IEEE Workshop on Visual Motion, pp. 8-13, (1991)
[22] Poelman C.J., Kanade T., “A paraperspective factorization method for shape and motion recovery,”, (1992)
[23] Shashua A., Projective depth: A geometric invariant for 3D reconstruction from two perspective/orthographic views and for visual recognition, Proc. Fourth Int'l Conf. on Computer Vision, pp. 583-590, (1993)
[24] Soatto S., Perona P., Fraezza R., Picci G., Recursive motion and structure estimation with complete error characterization, 1993 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 428-433, (1993)
[25] Spetsakis M., Aloimonos Y., A multi-frame approach to visual motion perception, Int'l J. of Computer Vision, 6, 3, pp. 245-255, (1991)
[26] Szeliski R., Kang S.B., Recovering 3D shape and motion from image streams using non-linear least squares, 1993 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 752-753, (1993)
[27] Szeliski R., Kang S.B., Recovering 3D shape and motion from image streams using non-linear least squares, (1993)
[28] Tomasi C., Kanade T., Shape and motion from image streams under orthography: a factorization method, Int'l J. of Computer Vision, 9, 2, pp. 137-154, (1992)
[29] Weinshall D., Tomasi C., Linear and incremental acquisition of invariant shape models from image sequences, Proc. Fourth Int'l Conf. on Computer Vision, pp. 675-682, (1993)
[30] Weng J., Ahuja N., Huang T.S., Optimal motion and structure estimation, Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 144-152, (1989)

← 1 2 3 4 →