Abstract
Remote sensing image target recognition is used in various fields, such as ships, tanks, airplanes, and vehicles, which are closed targets. The features of these targets include target outlines that are obvious and target discriminant features that are significantly different from the surrounding environment, and the targets are characterized as small and dense. Therefore, the recognition of these types of targets is a popular topic. We proposed a recognition framework consisting of a remote sensing image target recognition method based on deep saliency kernel learning analysis, which uses a target region extraction method based on the visual saliency mechanism and implements a nonlinear deep kernel learning saliency feature analysis method to realize target extraction and recognition. Experimental results show that a 95.9% recognition rate is achieved for SAR remote sensing target recognition on the public MSTAR data set, a 96% recognition rate on the UC Merced Land Use data set, and an 85% recognition rate on a self-built visible light remote sensing image data set. The recognition framework can be used for video recognition.
Highlights
In recent years, remote sensing data have been widely used in various fields
This paper proposes a remote sensing image target recognition method based on deep saliency kernel learning analysis that uses target region extraction based on the visual saliency mechanism and uses a nonlinear deep kernel learning saliency feature analysis method to realize target extraction and recognition
Given the problem that single kernel model learning with fixed parameters is no longer suitable for remote sensing image classification, a new deep kernel mapping architecture for remote sensing image classification is proposed by combining kernel mapping and deep learning
Summary
Remote sensing data have been widely used in various fields. Remote sensing images play an important role in many aspects, such as the exploration of geographic information resources [1], important ground information observations, geographic mapping, meteorology, civilianmilitary communications [2], the detection of military information [3], the capture of sensitive information, and battlefield situational awareness [4]. The automatic identification of sensitive targets is a very important research direction in military reconnaissance and military early warning systems. The realization of obtaining information from domestic remote sensing images is at the stage of transformation from traditional manual determination methods to intelligent automatic identification methods. Many units at home and abroad are gradually carrying out platform and systematization work on the technology to extract target information from remote sensing images. An airport identification system was proposed by Liu DH et al [6], and a building group identification system was proposed by Li, Yan et al [7] Most of these studies are highly targeted, aiming at specific targets in specific scenes and achieving good processing effects; the generalization of the system is relatively weak.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
