Abstract
Land cover and its dynamic information is the basis for characterizing surface conditions, supporting land resource management and optimization, and assessing the impacts of climate change and human activities. In land cover information extraction, the traditional convolutional neural network (CNN) method has several problems, such as the inability to be applied to multispectral and hyperspectral satellite imagery, the weak generalization ability of the model and the difficulty of automating the construction of a training database. To solve these problems, this study proposes a new type of deep convolutional neural network based on Landsat-8 Operational Land Imager (OLI) imagery. The network integrates cascaded cross-channel parametric pooling and average pooling layer, applies a hierarchical sampling strategy to realize the automatic construction of the training dataset, determines the technical scheme of model-related parameters, and finally performs the automatic classification of remote sensing images. This study used the new type of deep convolutional neural network to extract land cover information from Qinhuangdao City, Hebei Province, and compared the experimental results with those obtained by traditional methods. The results show that: (1) The proposed deep convolutional neural network (DCNN) model can automatically construct the training dataset and classify images. This model performs the classification of multispectral and hyperspectral satellite images using deep neural networks, which improves the generalization ability of the model and simplifies the application of the model. (2) The proposed DCNN model provides the best classification results in the Qinhuangdao area. The overall accuracy of the land cover data obtained is 82.0%, and the kappa coefficient is 0.76. The overall accuracy is improved by 5% and 14% compared to the support vector machine method and the maximum likelihood classification method, respectively.
Highlights
Land cover is a combination of natural and artificial surface structures and is a key factor affecting the balance of solar radiation energy on the surface [1,2]
Based on the classical deep convolutional neural network (DCNN) model, this paper introduced a cascaded cross-channel parametric pooling and the global average pooling method
A new technical framework for satellite remote sensing land cover mapping based on a deep convolutional neural network was proposed, and a practical image classification and result analysis was performed in Qinhuangdao City, Hebei Province
Summary
Land cover is a combination of natural and artificial surface structures and is a key factor affecting the balance of solar radiation energy on the surface [1,2]. The earliest satellite remote sensing land cover information extraction methods were based on visual interpretation and computer aided image interpretation methods, which relied on satellite image features, such as color, texture and shape information, combined with the natural geography, geomorphology and other related professional knowledge using artificial visual methods to identify various kinds of land cover and land use types [10,11]. These methods generally have high land mapping accuracy but are time-consuming, laborious, and have poor repeatability. As an important branch of ANNs, deep convolutional neural networks (DCNNs) are being widely used in image discrimination and target recognition technology [17,18]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
