Abstract:
A novel method for high-precision ground object recognition is proposed in this study. The method addresses the issue of insufficient attention to spatial features when extracting joint spectral features in hyperspectral ground object recognition models. The proposed method employs a hybrid convolutional neural network architecture that combines the use of three-dimensional convolutional neural network (3DCNN) and two-dimensional convolutional neural network (2DCNN). Additionally, an attention mechanism is introduced in the 2D convolution stage to construct the AFCNet ground object recognition model. This enables effective attention and activation of spatial features while extracting joint spectral features. To prevent overfitting and speed up the convergence rate of the model, the proposed model employs batch normalization layers (BN) in conjunction with 3D and 2D convolution kernels. The proposed method improves noise suppression capability and achieves excellent ground object recognition results compared to traditional convolutional network models.To validate the proposed method, experiments were conducted on two publicly available hyperspectral datasets: Salinas and Pavia University & Center datasets. The results showed that the proposed method achieved remarkable ground object recognition accuracies of 99.96% and 99.87%, respectively, demonstrating the effectiveness of the proposed method.