Abstract
Due to the unique feature of the three-dimensional convolution neural network, it is used in image classification. There are some problems such as noise, lack of labeled samples, the tendency to overfitting, a lack of extraction of spectral and spatial features, which has challenged the classification. Among the mentioned problems, the lack of experimental samples is the main problem that has been used to solve the methods in recent years. Among them, convolutional neural network-based algorithms have been proposed as a popular option for hyperspectral image analysis due to their ability to extract useful features and high performance. The traditional convolutional neural network (CNN) based methods mainly use the two-dimensional CNN for feature extraction, which makes the interband correlations of HSIs underutilized. The 3-D-CNN extracts the joint spectral-spatial information representation, but it depends on a more complex model. To address these issues, the report uses a 3-D fast learning block (depthwise separable convolution block and a fast convolution block) followed by a 2-D convolutional neural network was introduced to extract spectral-spatial features. Using a hybrid CNN reduces the complexity of the model compared to using 3-D-CNN alone and can also perform well against noise and a limited number of training samples. In addition, a series of optimization methods including batch normalization, dropout, exponential decay learning rate, and L2 regularization are adopted to alleviate the problem of overfitting and improve the classification results. To test the performance of this hybrid method, it is performed on the Salinas, University Pavia and Indian Pines datasets, and the results are compared with 2-D-CNN and 3-D-CNN deep learning models with the same number of layers.
Highlights
Due to the unique feature of the three -dimensional convolution neural network, it is used in image classification
Representative classifiers include k-nearest neighbor (KNN) [17], random forest (RF) [18], support vector machine (SVM ) [19], etc
The convolutional neural network (CNN) model has an advantage over other learning models due to its high ability to identify spatial and spectral features and is a significant model in the field of HSI classification, but this model has weaknesses, for example, during the process of gradient descent, it is easy to make the results converge to the local minimum, and the pooling layer will lose a lot of useful information, as it is known, the preprocessing stage plays a vitally important role in the accuracy of classification models, and principal component analysis (PCA) is known as a preprocessing method among HSI classification models and this preprocessing eliminates the non linear features of the image. the 2D CNN alone is not able to extract good discriminating feature maps from the spectral dimensions
Summary
Information and data related to spectral images have been available since the late 1980s, showing the reflective wavelengths in the range of 400 to 2400 nm. The proposed HSI cube data method extracts spectral-spatial properties without relying on any preprocessing or post-processing It requires fewer parameters than other deep learning methods, which are lighter in model and easier to teach. The CNN model has an advantage over other learning models due to its high ability to identify spatial and spectral features and is a significant model in the field of HSI classification, but this model has weaknesses, for example, during the process of gradient descent, it is easy to make the results converge to the local minimum, and the pooling layer will lose a lot of useful information, as it is known, the preprocessing stage plays a vitally important role in the accuracy of classification models, and PCA is known as a preprocessing method among HSI classification models and this preprocessing eliminates the non linear features of the image. It uses many algorithms for optimization, including dropout, batch normalization, exponential decay learning rate, and L2 regularization, so as to make the network more robust and generalized
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 callMore 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.
