MODEL-BASED SEGMENTATION OF FLIR IMAGES

被引：36

作者：

BHANU, B

HOLBEN, RD

机构：

[1] FORD AEROSP & COMMUN CORP,NEWPORT BEACH,CA 92663

[2] UNIV UTAH,SALT LAKE CITY,UT 84112

[3] ODETICS INC,ANAHEIM,CA 92802

来源：

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS | 1990年 / 26卷 / 01期

关键词：

D O I：

10.1109/7.53409

中图分类号：

V [航空、航天];

学科分类号：

08 ; 0825 ;

摘要：

We present the use of gray scale intensities together with the edge information present in a forward-looking infrared (FLIR) image to obtain a precise and accurate segmentation of a target A model of FLIR images based on gray scale and edge information is incorporated in a gradient relaxation technique which explicitly maximizes a criterion function based on the inconsistency and ambiguity of classification of pixels with respect to their neighbors. Four variations of the basic technique are considered which provide automatic selection of thresholds to segment FLIR images. A comparison of these methods is discussed and several examples of segmentation of ship images are given. © 1990 IEEE

引用

页码：2 / 11

页数：10

共 29 条

[1]

BHANU B, 1983, P SOC PHOTO-OPT INST, V435, P18

[2] SEGMENTATION OF IMAGES HAVING UNIMODAL DISTRIBUTIONS [J].

BHANU, B ;

FAUGERAS, OD .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1982, 4 (04) :408-419

[3]

BHANU B, 1984, P SOC PHOTO-OPT INST, V504, P10, DOI 10.1117/12.944840

[4] AUTOMATIC TARGET RECOGNITION - STATE-OF-THE-ART SURVEY [J].

BHANU, B .

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 1986, 22 (04) :364-379

[5] SEGMENTATION OF NATURAL SCENES [J].

BHANU, B ;

PARVIN, BA .

PATTERN RECOGNITION, 1987, 20 (05) :487-496

[6]

BHANU B, 1990, INT J MACHINE VI JAN

[7]

BHANU B, 1981, USCIPI1030 U SO CAL

[8]

BHANU B, 1983, 1983 P IEEE C COMP V, P502

[9]

COLEMAN GB, 1977, USCIPI750 U SO CAL I

[10] BLOB DETECTION BY RELAXATION [J].

DANKER, AJ ;

ROSENFELD, A .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1981, 3 (01) :79-92

← 1 2 3 →