Abstract
Classification of remote sensing (RS) images is a key technology for extracting information on ground objects using RS methods. Inspired by the success of deep learning (DL) in artificial intelligence, researchers have proposed different algorithms based on DL to improve the performance of classification. At present, a DL model represented by the convolutional neural networks (CNNs) can extract the abstract feature, but it loses the spatial context of the ground objects. To solve the problem of lack of spatial information in CNNs, the Capsule network takes the form of vectors that convey location transformation information. This article proposes using a Capsules-Unet model, which incorporates Capsules within the U-net architecture for classification of RS images. The aim is to train better models by encapsulating the multidimensional features of the objects in the form of Capsules, and to reduce parameter space by improving the dynamic routing algorithm. Experiments are conducted on ISPRS Vaihingen and Potsdam datasets. Capsules-Unet slightly outperforms all other approaches with far fewer parameters, a reduction in parameters of over 81.8% compared with U-net and over 13.8% compared with Capsule network.
Highlights
C LASSIFICATION is a fundamental task in remote sensing (RS), and it is a complex data processing process [1]
Capsules–Unet slightly outperforms all other compared approaches with far fewer parameters: a reduction in parameters of over 81.8% from U-net and over 13.8% compared with Capsule network
The experiments have proved the effectiveness of the proposed method for the classification using two common datasets
Summary
C LASSIFICATION is a fundamental task in remote sensing (RS), and it is a complex data processing process [1]. Image classification is similar to semantic segmentation tasks. It refers to the recognition of different objects based on their spectral and shape information, and the assignment of each pixel in the image to its real object category [2]–[4]. Classification was for low resolution (10–30 m) images and pixel-leveled images, mainly comprising unsupervised classification (e.g., ISODATA [5] and K-means [6]) and supervised classification (e.g., neural networks [7] and Random Forest [8]).
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: 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.