Abstract | ||
---|---|---|
In this study, the target detection is performed using TerraSAR-X and WorldView-2 high-resolution satellite images, considering the characteristics of targets. The target of our interest is characterized by being stationary and appearing as cluster targets. After the target detection of SAR image based on CFAR (Constant False Alarm Rate) algorithm, a series of processing (target pixel clustering, network clustering and coherence analysis) is performed in order to reduce false alarms. However, the false alarm is still too quite large to narrow down the candidate areas. The fast and effective ellipse detection using Hough transform is developed and applied to an EO (Electro Optical) image. The result helps us to lower significantly the false alarm. Based on the detected ellipse and network analysis the candidates of cluster targets are successfully identified with very low false alarm. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/IGARSS.2014.6946795 | IGARSS |
Keywords | DocType | ISSN |
high-resolution,electro-optical devices,synthetic aperture radar,pattern clustering,image fusion,image resolution,network clustering,effective ellipse detection,remote sensing by radar,pixel clustering,artificial satellites,electro-optical image,stationary target detection,Electro Optical (EO),geophysical image processing,cluster target detection,object detection,WorldView-2,constant false alarm rate,high resolution satellite images,Hough transform,CFAR algorithm,network analysis,Target detection,TerraSAR-X,EO,radar imaging,Synthetic Aperture Radar (SAR),Hough transforms,coherence analysis,high resolution SAR images | Conference | 2153-6996 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
So-yeon Kim | 1 | 19 | 8.45 |
DongHwan Cha | 2 | 0 | 0.34 |
Sang Wan Kim | 3 | 0 | 2.37 |