Mean shift is a bound optimization

被引：96

作者：

Fashing, M ^{[1
]}

Tomasi, C ^{[1
]}

机构：

[1] Duke Univ, Dept Comp Sci, Durham, NC 27707 USA

来源：

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 2005年 / 27卷 / 03期

基金：

美国国家科学基金会;

关键词：

mean shift; bound optimization; Newton's method; adaptive gradient descent; mode seeking;

D O I：

10.1109/TPAMI.2005.59

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We build on the current understanding of mean shift as an optimization procedure. We demonstrate that, in the case of piecewise constant kernels, mean shift is equivalent to Newton's method. Further, we prove that, for all kernels, the mean shift procedure is a quadratic bound maximization.

引用

页码：471 / 474

页数：4

共 10 条

[1] MEAN SHIFT, MODE SEEKING, AND CLUSTERING [J].

CHENG, YZ .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1995, 17 (08) :790-799

[2]

Collins RT, 2003, PROC CVPR IEEE, P234

[3] Mean shift: A robust approach toward feature space analysis [J].

Comaniciu, D ;

Meer, P .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (05) :603-619

[4]

Comaniciu D., 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision, P1197, DOI 10.1109/ICCV.1999.790416

[5]

FUKUNAGA K, 1975, IEEE T INFORM THEORY, V21, P32, DOI 10.1109/TIT.1975.1055330

[6]

Georgescu B, 2003, NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS I AND II, PROCEEDINGS, P456

[7]

Neal RM, 1998, NATO ADV SCI I D-BEH, V89, P355

[8]

PALUMBO GGC, 1983, CATALOGUE RADIAL VEL

[9]

Ramanan D, 2003, PROC CVPR IEEE, P467

[10]

Ramanan D, 2003, NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS I AND II, PROCEEDINGS, P338

← 1 →