Spectral-Spatial Hyperspectral Image Classification Using Robust Dual-Stage Spatial Embedding

Abstract

Recently, many spectral-special classification models have emerged one after another in the remote sensing community. These models aim to introduce the spatial information of the pixel to improve the accuracy of the class attribute of the pixel. However, for the spectral-spatial classification algorithms, not all pixels need to introduce the corresponding spatial information since the use of a large amount of spatial information has a costly time. To solve this problem, this paper proposes a robust dualstage spatial embedding (RDSSE) model for spectral-spatial classification of hyperspectral image, which is composed of the following several main steps: First, an over-segmentation algorithm is employed to cluster original hyperspectral image into many superpixel blocks with shape adaptive characteristics. Then, we design a k-peak criterion to fuse the spectral feature of pixels within and between superpixels. Next, a low time-consumption spectral classifier is introduced to conduct primary classification for a testing pixel to achieve the corresponding probability distribution. Specifically, the difference between the probability of the largest class and that of the second-largest class is served as class confidence. Finally, the predicted label of the low-confidence testing pixels is reclassified based on a high-accuracy spectral-spatial classification method. Experimental results on several real images illustrated that the proposed RDSSE can obtain superior performance with respect to several competitive methods.

cFL：Data distribution edge clustering algorithm based on deep Federated learning

“…The network between end devices and cloud servers, in contrast, has two issues: first, a limited amount of network bandwidth and the high cost of servers for high bandwidth services; and second, an asymmetric network connection between local and cloud where the upstream speed is typically much slower than the downstream speed. Therefore, when a large number of end devices are involved in federation learning, high concurrent access increases the communication latency of model transmission, and the instability of the network can lead to bottlenecks in the training process [5]. On the other hand, there is heterogeneity in the devices involved in federation learning, and their local data tend to obey a non-independent homogeneous distribution [6].Because of this, the local models created using these tools and data are frequently of poor quality and are referred to as "dirty models."…”