DEPTH FROM FOCUS USING A PYRAMID ARCHITECTURE

被引：23

作者：

DARELL, T

WOHN, K

机构：

[1] Grasp Laboratory, Department of Computer and Information Science, University of Pennsylvania, Philadelphia

来源：

PATTERN RECOGNITION LETTERS | 1990年 / 11卷 / 12期

基金：

美国国家科学基金会;

关键词：

MACHINE VISION; DEPTH-FROM-FOCUS; MULTIRESOLUTION PYRAMID;

D O I：

10.1016/0167-8655(90)90032-W

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A method is presented for depth recovery through the analysis of scene sharpness across changing focus position. Modeling a defocused image as the application of a low pass filter on a properly focused image of the same scene, we can compare the high spatial frequency content of regions in each image and determine the correct focus position. Recovering depth in this manner is inherently a local operation, and can be done efficiently using a pipelined image processor. Laplacian and Gaussian pyramids are used to calculate sharpness maps which are collected and compared to find the focus position that maximizes high spatial frequencies for each region.

引用

页码：787 / 796

页数：10

共 8 条

[1] THE LAPLACIAN PYRAMID AS A COMPACT IMAGE CODE [J].

BURT, PJ ;

ADELSON, EH .

IEEE TRANSACTIONS ON COMMUNICATIONS, 1983, 31 (04) :532-540

[2] DEPTH FROM FOCUS [J].

GROSSMANN, P .

PATTERN RECOGNITION LETTERS, 1987, 5 (01) :63-69

[3]

Horn B., 1986, ROBOT VISION, DOI DOI 10.1137/1030032

[4]

KROTKOV E, 1987, INT J COMPUT VISION, V1, P223, DOI 10.1007/BF00127822

[5]

MCIVOR A, 1985, THESIS HARVARD U

[6] A NEW SENSE FOR DEPTH OF FIELD [J].

PENTLAND, AP .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1987, 9 (04) :523-531

[7]

SUBBARAO M, 1988, JUN P COMP VIS PATT, P498

[8]

VANDEWAL G, 1985, P SPIE, P579

← 1 →