Scholarly record
COMPARISON OF SELECTED METHODS OF OBJECT DETECTION IN SAR IMAGES
Abstract
Detecting objects in images is of widespread interest due to a large number of applications in diverse disciplines, including remote sensing, medical images, geology and civil infrastructure. This paper presents a comparison of selected techniques that may be useful for the object detection connected with ground deformations within large areas using satellite radar interferometry (DInSAR, Differential Interferometry Synthetic Aperture Radar) techniques. The DInSAR method, that exploits two SAR images, derives information about ground deformations that occurred between the time of the two SAR data acquisitions. Using this method the ground deformations can be monitored for large areas with high accuracy and very good spatial and temporal resolutions. The results of DInSAR analysis can be used for areas highly endangered by subsidence phenomenon identification. The problem of detecting objects in the images is very challenging due to many reasons, e.g. speckle, the presence of incomplete and distorted parts of objects, corruption in the quality of edges or lack of a priori information. The main purpose of this paper was to present and compare methods that can be used at various stages of SAR images analysis, such as preprocessing (filtration, noise reduction, edge detection) or object detection (detection of specific objects or shapes).
Publication Impact Profile
- Captures
- Mendeley - Readers: 2
Publication details
References0
Structured references will appear here after the reference import pass. The count is preserved now so the scholarly record is not incomplete.
View or Download full articleAccess options
SWS access login
Login as SWS Scientific CommitteeLogin as SWS Scientific PartnerLogin as SWS AuthorAuthors and approved SWS contributors will read and export their own linked papers after identity matching by SWS profile, email and SGEM GlobalID.
For librarian assistance: [email protected]
Purchase Instant Access
- Article can be downloaded after successful payment.
- Article may be used according to SWS library access terms.
- Article cannot be redistributed.