Ship detection is a significant application of maritime monitoring and security. To fully explore the potential of wide
coverage of synthetic aperture radar (SAR) image, the ScanSAR Wide image for ship detection is investigated in this
paper. The Radarsat-2 ScanSAR Wide mode image is used as the image source due to its huge coverage and constant
false alarm rate (CFAR) with Gamma distribution is selected as the core detector. Two problems of ScanSAR ship
detection, the unbalanced phenomenon and false alarms of islands, are investigated and solved by a compensation step
and Hessian matrix respectively. For more aspects, the detector also concerns the polarization channel selection and
distribution fitting. Finally, a whole flow chart of ScanSAR ship detection is presented. As test cases, the experimental
image is used to show the efficiency of our method.
This paper presents a novel normalized scanning algorithm for detecting ship wakes in SAR (Synthetic Aperture Radar)
images. Unlike most of wake detection algorithm is based on Radon transform, the proposed algorithm is based on
normalized scanning. The technique takes advantage of the displacement between the ship and perspective wake in
azimuth direction. The proposed algorithm can determine the offset in azimuth direction and the movement direction of
ship. Then we can get the velocity vector of the ship. Although the computational complexity is very small, the
normalized scan algorithm is robust in high noise environment. Experiment work outs are carried over in real SAR
images. Results show that the ship wake detection based on normalized scan is better than traditional technique.
With the globalization there is an increasing degree of concern on the ship traffic monitoring. Civilian ship classification
is an important research area, as it can help to improve sea traffic surveillance and control activities. By making use of
the new generation SAR satellites like COSMO-SkyMed, civilian ship classification in high resolution SAR images is a
hotspot and preceding problem in SAR applications. This paper presents a ship classification method that uses single-pol
COSMO-SkyMed images to categorize civilian ships into three types, including bulk carriers, container ships and oil
tankers. The experimental results based on ship structure features show that the whole classification accuracy is above
80%.
Ship detection in marine area is an important task for the security and monitoring of coastlines. In this paper, a new
physically-based method has been developed to detect ships in marine area with polarimetric SAR data. The method is
based on the difference of the scattering mechanisms between sea clutters and ships. Experiments, accomplished over
Single Look Complex (SLC) RADARSAT-2 Quad Mode data, demonstrate the effectiveness of the method for ship
detection purposes. The proposed method provides a better performance compared with HH-CFAR detector, SPAN
detector, and widely used PWF detector.
A vessel detection method based on gravity enhancement was applied to Synthetic Aperture Radar (SAR) images. With
the method, targets' pixels were enhanced by the interactions between themselves and their neighbors, while the speckle
and background clutter were suppressed after enhancement as well as the contrasts between targets and clutter had been
greatly increased. Then vessels were detected with the improved K-CFAR detector. East China Sea, off the east coast of
Shanghai, China, was chosen as the experiment region. Fine resolution mode and scanSAR mode ALOS PALSAR data
were utilized to validate the method. Experiment results show the method proposed in this paper have good ability for
vessel detection in SAR image.
The devastating Wenchuan Earthquake occurred in Sichuan Province, Southwestern China, with a magnitude of 8.0 on May 12, 2008. Most buildings along the seismic zone were ruined, resulting in infrastructure damage to factories, traffic facilities and power supplies. The earthquake also triggered geological disasters, such as landslides, debris flow, landslide lakes, etc. During the rescue campaign the remote sensing aircrafts of the Chinese Academy of Sciences (CAS), equipped with synthetic aperture radar (SAR) and optical sensors, flew over the disaster area and acquired many high resolution airborne SAR images. We first describe the basic characteristics of SAR imagery. The SAR images of buildings are simulated, and the backscattering mechanism of the buildings is analyzed. Finally, the various disaster phenomena are described and analyzed in the high resolution airborne SAR images. It is shown that certain phenomena of ruins could be identified clearly in high resolution SAR images in proper imaging conditions, while the functional destruction is quite difficult to detect. With calibrated data, the polarmetric SAR interferometry could be used to analyze the scattering mechanism and 3D distribution of the scattering center, which are redound to earthquake damage assessment.
This paper proposed a method that uses a case-based classification of remote sensing images and applied this method to
abstract the information of suspected illegal land use in urban areas. Because of the discrete cases for imagery
classification, the proposed method dealt with the oscillation of spectrum or backscatter within the same land use
category, and it not only overcame the deficiency of maximum likelihood classification (the prior probability of land use
could not be obtained) but also inherited the advantages of the knowledge-based classification system, such as artificial
intelligence and automatic characteristics. Consequently, the proposed method could do the classifying better. Then the
researchers used the object-oriented technique for shadow removal in highly dense city zones. With multi-temporal
SPOT 5 images whose resolution was 2.5×2.5 meters, the researchers found that the method can abstract suspected
illegal land use information in urban areas using post-classification comparison technique.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.