UNSUPERVISED SEABED SEGMENTATION OF SYNTHETIC APERTURE SONAR IMAGERY VIA WAVELET FEATURES AND SPECTRAL CLUSTERING

被引:17
作者
Williams, David P. [1 ]
机构
[1] NATO Undersea Res Ctr, I-19126 La Spezia, SP, Italy
来源
2009 16TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-6 | 2009年
关键词
Seabed segmentation; spectral clustering; synthetic aperture sonar; wavelet features; unsupervised learning;
D O I
10.1109/ICIP.2009.5413910
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
An unsupervised seabed segmentation algorithm for synthetic aperture sonar (SAS) imagery is proposed. Each 2 m x 2 m area of seabed is treated as a unique data point. A set of features derived from the coefficients of a wavelet decomposition are extracted for each data point. Spectral clustering is then performed with this data, which assigns the data points to clusters. This clustering result is then used directly to effect a segmentation of the SAS image into different seabed types. Experimental results on four real, measured SAS images demonstrate the promise of the proposed approach. Importantly, accurate image segmentation results are achieved on the large, challenging images without the aid of any training data or parameter estimation.
引用
收藏
页码:557 / 560
页数:4
相关论文
共 10 条
[1]  
[Anonymous], 1999, A Wavelet Tour of Signal Processing
[2]  
Beal MJ, 2003, BAYESIAN STATISTICS 7, P453
[3]   Seabed classification through multifractal analysis of sidescan sonar imagery [J].
Carmichael, DR ;
Linnett, LM ;
Clarke, SJ ;
Calder, BR .
IEE PROCEEDINGS-RADAR SONAR AND NAVIGATION, 1996, 143 (03) :140-148
[4]  
Meila M, 2001, ADV NEUR IN, V13, P873
[5]   Sonar image segmentation using an unsupervised hierarchical MRF model [J].
Mignotte, M ;
Collet, C ;
Pérez, P ;
Bouthemy, P .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2000, 9 (07) :1216-1231
[6]  
Ng AY, 2002, ADV NEUR IN, V14, P849
[7]   The fusion of large scale classified side-scan sonar image mosaics [J].
Reed, Scott ;
Ruiz, Ioseba Tena ;
Capus, Chris ;
Petillot, Yvan .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2006, 15 (07) :2049-2060
[8]  
Sugiyama M, 2007, J MACH LEARN RES, V8, P985
[9]   Estimating the number of clusters in a data set via the gap statistic [J].
Tibshirani, R ;
Walther, G ;
Hastie, T .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 2001, 63 :411-423
[10]   Unsupervised segmentation using a self-organizing map and a noise model estimation in sonar imagery [J].
Yao, KC ;
Mignotte, M ;
Collet, C ;
Galerne, P ;
Burel, G .
PATTERN RECOGNITION, 2000, 33 (09) :1575-1584