A cluster-based approach for detecting man-made objects and changes in imagery

被引:222
作者
Carlotto, MJ [1 ]
机构
[1] Gen Dynam Adv Informat Syst, Arlington, VA 22209 USA
来源
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2005年 / 43卷 / 02期
关键词
change detection; Gaussian processes; image analysis; image representations; image sequence analysis; object detection; pattern clustering methods; vector quantization;
D O I
10.1109/TGRS.2004.841481
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
A new unified approach to object and change detection is presented that involves clustering and analyzing the distribution of pixel values within clusters over one or more images. Cluster-based anomaly detection (CBAD) can detect man-made objects that are: 1) present in a single multiband image; 2) appear or disappear between two images acquired at different times; or 3) manifest themselves as spectral differences between two sets of bands acquired at the same time. Based on a Gaussian mixture model, CBAD offers an alternative to compute-intensive, sliding-window algorithms like Reed and Yu's RX-algorithm for single-image object detection. It assumes that background pixel values within clusters can be modeled as Gaussian distributions about mean values that vary cluster-to-cluster and that anomalies (man-made objects) have values that deviate significantly from the distribution of the cluster. This model is valid in situations where the frequency of occurrence of man-made objects is low compared to the background so that they do not form distinct clusters, but are instead split up among multiple background clusters. CBAD estimates background statistics over clusters, not sliding windows, and so can detect objects of any size or shape. This provides the flexibility of filtering detections at the object level. Examples show the ability to detect small compact objects such as vehicles as well as large, spatially extended features (e.g., built-up and bomb-damaged areas). Unlike previous approaches to change detection, which compare pixels, vectors, features, or objects, cluster-based change detection involves no direct comparison of images. In fact, it is identical to the object detection algorithm, different only in the way it is applied. Preliminary results show cluster-based change detection is less sensitive to image misregistration errors than global change detection. The same cluster-based algorithm can also be used for cross-spectral anomaly detection. An example showing the detection of thermal anomalies in Landsat Thematic Mapper imagery is provided.
引用
收藏
页码:374 / 387
页数:14
相关论文
共 37 条
[1]  
[Anonymous], 1983, New York
[2]   MONITORING LAND-COVER CHANGE BY PRINCIPAL COMPONENT ANALYSIS OF MULTITEMPORAL LANDSAT DATA [J].
BYRNE, GF ;
CRAPPER, PF ;
MAYO, KK .
REMOTE SENSING OF ENVIRONMENT, 1980, 10 (03) :175-184
[3]   Detection and analysis of change in remotely sensed imagery with application to wide area surveillance [J].
Carlotto, MJ .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 1997, 6 (01) :189-202
[4]   Nonlinear background estimation and change detection for wide-area search [J].
Carlotto, MJ .
OPTICAL ENGINEERING, 2000, 39 (05) :1223-1229
[5]   Nonlinear mean-square estimation with applications in remote sensing [J].
Carlotto, MJ .
ALGORITHMS FOR MULTISPECTRAL AND HYPERSPECTRAL IMAGERY II, 1996, 2758 :206-217
[6]   Reducing the effects of space-varying, wavelength-dependent scattering in multispectral imagery [J].
Carlotto, MJ .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 1999, 20 (17) :3333-3344
[7]   Spatial enhancement of elevation data using a single multispectral image [J].
Carlotto, MJ .
OPTICAL ENGINEERING, 2000, 39 (02) :430-437
[8]  
CARLOTTO MJ, 1988, P SPIE NOV, P38
[9]  
CARLOTTO MJ, 2002, P SPIE, V4729
[10]   A HYPOTHETICAL MODEL ON THE MECHANISM OF ANESTHESIA [J].
CHENG, SC ;
BRUNNER, EA .
MEDICAL HYPOTHESES, 1987, 23 (01) :1-9