Hyperspectral Image Classification with Markov Random Fields and a Convolutional Neural Network
This addresses classification accuracy for remote sensing applications, but it is incremental as it combines existing techniques like CNNs and Markov Random Fields.
The paper tackles hyperspectral image classification by integrating spectral and spatial information in a Bayesian framework, achieving better performance than state-of-the-art methods on one synthetic and two benchmark datasets.
This paper presents a new supervised classification algorithm for remotely sensed hyperspectral image (HSI) which integrates spectral and spatial information in a unified Bayesian framework. First, we formulate the HSI classification problem from a Bayesian perspective. Then, we adopt a convolutional neural network (CNN) to learn the posterior class distributions using a patch-wise training strategy to better use the spatial information. Next, spatial information is further considered by placing a spatial smoothness prior on the labels. Finally, we iteratively update the CNN parameters using stochastic gradient decent (SGD) and update the class labels of all pixel vectors using an alpha-expansion min-cut-based algorithm. Compared with other state-of-the-art methods, the proposed classification method achieves better performance on one synthetic dataset and two benchmark HSI datasets in a number of experimental settings.