Abstract
For remote sensing scene image classification, many convolution neural networks improve the classification accuracy at the cost of the time and space complexity of the models. This leads to a slow running speed for the model and cannot realize a trade-off between the model accuracy and the model running speed. As the network deepens, it is difficult to extract the key features with a sample double branched structure, and it also leads to the loss of shallow features, which is unfavorable to the classification of remote sensing scene images. To solve this problem, we propose a dual branch multi-level feature dense fusion-based lightweight convolutional neural network (BMDF-LCNN). The network structure can fully extract the information of the current layer through 3 × 3 depthwise separable convolution and 1 × 1 standard convolution, identity branches, and fuse with the features extracted from the previous layer 1 × 1 standard convolution, thus avoiding the loss of shallow information due to network deepening. In addition, we propose a downsampling structure that is more suitable for extracting the shallow features of the network by using the pooled branch to downsample and the convolution branch to compensate for the pooled features. Experiments were carried out on four open and challenging remote sensing image scene data sets. The experimental results show that the proposed method has higher classification accuracy and lower model complexity than some state-of-the-art classification methods and realizes the trade-off between model accuracy and model running speed.
Highlights
Remote sensing images with high resolution have been applied to many fields such as remote sensing scene classification [1], hyperspectral image classification [2], change detection [3,4], geographic image, and land use classification [5,6], etc
The purpose of this study is to find a simple and efficient lightweight network model, which can accurately understand the semantics of remote sensing images and efficiently classify remote sensing scene images
The RSSCN dataset is a remote sensing image dataset from Wuhan University with seven categories consisting of 2800 images, with 400 × 400
Summary
Remote sensing images with high resolution have been applied to many fields such as remote sensing scene classification [1], hyperspectral image classification [2], change detection [3,4], geographic image, and land use classification [5,6], etc. Remote sensing images’ complex spatial patterns and geographical structure bring great difficulties to image classification. It is important to understand the semantic content of remote sensing images effectively. The purpose of this study is to find a simple and efficient lightweight network model, which can accurately understand the semantics of remote sensing images and efficiently classify remote sensing scene images. In order to effectively extract image features, researchers have proposed many methods. In order to solve the disadvantages brought by the method of manually extracting features, researchers proposed some unsupervised feature learning methods that can automatically extract shallow detail features from images, such as principal component analysis (PCA), sparse coding [13], autoencoders [14], Latent Dirichlet allocation [15], and probabilistic latent
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.
