Convolutional neural networks (CNNs) can automatically learn features from the hyperspectral image (HSI) data, avoiding the difficulty of manually extracting features. However, the number of training samples for the classification of HSIs is always limited, making it difficult for CNN to obtain effective features and resulting in low classification accuracy. To solve this problem, a pixel cluster CNN and spectral-spatial fusion (PC-CNN-SSF) algorithm for hyperspectral image classification (HSIC) with small-size training samples is proposed in this paper. Firstly, spatial information is extracted by the Gray Level Co-occurrence Matrix (GLCM). Then spatial information and spectral information are fused by means of bands superposition, forming spectral-spatial features. To expand the number of training samples, the pixels after spectral-spatial fusion are combined into pixel clusters according to a certain rule. Finally, a CNN framework is utilized to extract effective features from the pixel clusters. Experiments based on three standard HSIs demonstrate that the proposed algorithm can get better performance than the conventional CNN and also outperforms other studied algorithms in the case of small training set.
To overcome the shortcomings of grey wolf optimization algorithm (GWO) such as being easy to fall into the local optimum, and the slow convergence rate in the later stage, an adaptive weighted grey-wolf optimization algorithm based on the Circle map is proposed. Firstly, in this algorithm, Circle chaotic map, which enhances the diversity of the initialization population, is introduced into the initialization of population, therefore, the search space can be searched more thoroughly; Secondly, trigonometric function and the beta distribution are introduced in the convergence factor ‘a’ and the population position update formula, which improve the convergence speed in the later period of the algorithm; Finally, the simulation experiments on the four common test functions on CEC2017 show that under the same experimental conditions, the improved grey wolf optimization algorithm improves the solution accuracy and convergence speed significantly, and its performance is obviously better than other smart optimization algorithms and other improved GWO algorithms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.