Abstract
This paper proposes a change detection algorithm on multi-spectral images based on feature-level U-Net. A low-complexity pan-sharpening method is proposed to employ not only panchromatic images, but also multi-spectral images for enhancing the performance of the deep neural network. The high-resolution multi-spectral (HRMS) images are then fed into the proposed feature-level U-Net. The proposed feature-level U-Net consists of two-stages: a feature-level subtracting network and U-Net. The feature-level subtracting network is used to extract dynamic difference images (DI) for the use of low-level and high-level features. By employing this network, the performance of change detection algorithms can be improved with a smaller number of layers for U-Net with a low computational complexity. Furthermore, the proposed algorithm detects small changes by taking benefits of both geometrical and spectral resolution enhancement and adopting an intensity-hue-saturation (IHS) pan-sharpening method. A modified of IHS pan-sharpening algorithm is introduced to solve spectral distortion problem by applying mean filtering in high frequency. We found that the proposed change detection on HRMS images gives a better performance compared to existing change detection algorithms by achieving an average F-1 score of 0.62, a percentage correct classification (PCC) of 98.78%, and a kappa of 61.60 for test datasets.
Highlights
Change detection is an important task in the field of remote sensing
The proposed algorithm enhances low-resolution multispectral images to produce highresolution multi-spectral (HRMS) ones by applying a modified IHS pan-sharpening algorithm. This proposed pan-sharpening is introduced by applying a low-pass filtering in IHS high-frequency image to remove spectral distortion
The high-resolution multi-spectral (HRMS) is analyzed for change detection by employing a feature-level U-Net algorithm for low complexity
Summary
Change detection is an important task in the field of remote sensing. It can benefit both civil and military applications, including environmental monitoring, disaster evaluation, urban expansion monitoring, and reconnaissance. Image-based change detection algorithms with a deep learning network have been studied by training temporal images to generate a segmented land cover change [18]–[24]. U-Net segmentation models are employed by contracting and expanding the feature maps to produce a segmented land cover change through end-to-end training and yield reasonably good performances. They remain subject to complex and small changes, and are not resilient to distortions such as radiometric and geometric distortions. The proposed algorithm covers small changes by taking benefits of both geometrical and spectral resolution enhancement and adopting an intensity-hue-saturation (IHS) pansharpening method This method propagates high-resolution information of the PAN image into the low-resolution MS images to produce high-resolution multi-spectral (HRMS) images.
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.
