Abstract
High-resolution remote sensing images have the advantage of timeliness, and they can display feature information in more detail. Deep learning embodies its unique characteristics in land cover classification, target recognition, and other fields, which can automatically learn the in-depth feature information of images and make accurate classification decisions. However, when deep learning models extract high-dimensional abstract feature information, they often ignore and lose part of the underlying features essential for classification accuracy. This article proposes a dual-channel fully convolutional network (D-FCN), whose two channels, respectively, take image data and low-level features such as color, texture, and shape as the different input data to combine the underlying features with high-dimensional abstract features. To reduce the complexity of the model, we add a large number of skip connections between the model and make full use of the advantages of weight sharing and local connections to connect spatial context information. We used multifeature information as the model input and compared and analyzed the impact of different features on the land cover classification accuracy, and finally obtained the most suitable combination of multifeature information. In addition, we provide a small-scale land cover classification dataset with labels to verify the applicability and transferability of the D-FCN, and use the optimal combination of multifeature information to conduct comparative experiments on the small-scale dataset. The experimental results show that D-FCN has outstanding applicability and transferability. Compared with other state-of-the-art models, D-FCN has a more challenging performance and greatly reduces model complexity.
Highlights
REMOTE sensing images are formed by sensors receiving electromagnetic waves reflected from objects
The accuracy of image classification can be effectively improved by taking advantage of the high spatial resolution of remote sensing images and comprehensively using multiple feature information such as spectrum, texture, shape, and color to assist image classification
The public dataset Gaofen Image Dataset (GID) and the small-scale land cover classification dataset Gaofen Changchun Dataset (GCD) are used to verify the performance of the dual-channel fully convolutional network (D-FCN) and the influence of multi-feature information on the classification results
Summary
REMOTE sensing images are formed by sensors receiving electromagnetic waves reflected from objects. As an essential means to analyze and predict the changes in the earth’s surface, remote sensing images have been widely used in land use surveys, urban planning, precision agriculture, and atmospheric research [1,2,3]. Target recognition and classification is an im-. Manuscript received ___; revised ___; accepted ___. Date of publication __; date of current version __. Portant research content of remote sensing technology. Since high-resolution remote sensing images have a large amount of complex feature information, they will be affected by various external or internal factors during the classification process [4, 5]. Traditional visual interpretation methods rely too much on the professional's classification experience and professional knowledge, which is time-consuming, inefficient, and more susceptible to subjective awareness [6]
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.