Motion estimation based on the direction of intensity gradient

被引：14

作者：

Burgi, PY ^{[1
]}

机构：

[1] Ctr Suisse Elect & Microtech SA, CH-2007 Neuchatel, Switzerland

来源：

IMAGE AND VISION COMPUTING | 2004年 / 22卷 / 08期

关键词：

motion field; optical flow constraint; histogramming; intensity gradient direction; parametric estimation;

D O I：

10.1016/j.imavis.2004.01.003

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The optical flow constraint (OFC) equation has been extensively studied in computer vision to estimate motion from image sequences. Traditionally the OFC relies on spatio-temporal brightness variations caused by motion. However, many other features are in principle appropriate, including gradient directions of the image intensity. Given gradient directions are more tolerant to changes in lighting, they seem to be an adequate choice for computing optical flows. Their applicability in the OFC is, however, not straightforward as the gradient direction is independent of the gradient magnitude, and is not defined in homogeneous areas. To palliate to these difficulties, a form of OFC equation based on probability distributions of gradient directions is proposed. The performance of the approach is assessed by experiments realized on synthetic and real world images. (C) 2004 Elsevier B.V. All rights reserved.

引用

页码：637 / 653

页数：17

共 38 条

[1]

[Anonymous], 1993, Motion and structure from image sequences

[2] The minimal local-asperity hypothesis of early retinal lateral inhibition [J].

Balboa, RM ;

Grzywacz, NM .

NEURAL COMPUTATION, 2000, 12 (07) :1485-1517

[3] A 100 x 100 pixel silicon retina for gradient extraction with steering filter capabilities and temporal output coding [J].

Barbaro, M ;

Burgi, PY ;

Mortara, A ;

Nussbaum, P ;

Heitger, F .

IEEE JOURNAL OF SOLID-STATE CIRCUITS, 2002, 37 (02) :160-172

[4] PERFORMANCE OF OPTICAL-FLOW TECHNIQUES [J].

BARRON, JL ;

FLEET, DJ ;

BEAUCHEMIN, SS .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 1994, 12 (01) :43-77

[5] Estimating optical flow in segmented images using variable-order parametric models with local deformations [J].

Black, MJ ;

Jepson, AD .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1996, 18 (10) :972-986

[6] The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields [J].

Black, MJ ;

Anandan, P .

COMPUTER VISION AND IMAGE UNDERSTANDING, 1996, 63 (01) :75-104

[7] Improved accuracy in gradient-based optical flow estimation [J].

Brandt, JW .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 1997, 25 (01) :5-22

[8] Probabilistic motion estimation based on temporal coherence [J].

Burgi, PY ;

Yuille, AL ;

Grzywacz, NM .

NEURAL COMPUTATION, 2000, 12 (08) :1839-1867

[9] Simultaneous motion estimation and segmentation [J].

Chang, MM ;

Tekalp, AM ;

Sezan, MI .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 1997, 6 (09) :1326-1333

[10]

Chen HF, 2000, PROC CVPR IEEE, P254, DOI 10.1109/CVPR.2000.855827

← 1 2 3 4 →