Spectral-Spatial Classification of Hyperspectral Images Using Label Dependence

Abstract

Hyperspectral images are rich in both spectral information and spatial dependence information between pixels; however, hyperspectral images are characterized by the high dimensionality of small data sets and the spectral variance. Facing these problems, spatial dependence information as supplementary information is a relatively effective means to solve them. And the label dependence characteristic of hyperspectral images is excellent spatial dependence information. Therefore, to address the above issues, based on residual network and spatial information extractor(RAS), which is based on a residual network, pixel embedding(PE), and a spatial information extractor(SIE). At the stage of mining spectral information, we use the residual network to mine spectral features; At the stage of mining spatial information, we utilize the label dependency characteristic to feed the set of pixels containing the target pixels into PE. Then, a pixel vector with location information and self-defined dimensionality is obtained. Next, this vector is fed into our proposed SIE to mine the spatial dependency information. In multi-group ablation experiments, our proposed model achieves overall accuracy (OA) scores of 79.16% on the 5% Indian Pines test set, 90.82% on the 1% Pavia University test set, and 92.17% on the 1% Salinas test set. Especially, the experimental results demonstrate that the joint spectral-spatial approach is effective in improving the accuracy of hyperspectral image classification. INDEX TERMSDeep learning, hyperspectral image, image classification, pattern recognition.

A Multilabel Learning-Based Automatic Annotation Method for Semantic Roles in English Text

“…Wu G [15] introduces the multi-label learning algorithm for sample association relations (ML-K-Nearest Neighbor, MLKNN), i.e., the k-nearest neighbor method is used to measure the degree of similarity of samples to reason about their multi-label sets. Ameer I [16] analyzed two types of label dependencies using contextual information in a multilabel dataset.…”

Identification and Comprehensive Evaluation of Resistant Weeds Using Unmanned Aerial Vehicle-Based Multispectral Imagery

“…For example, UAVs have been used for physiological and geometric plant characterization ( Zhang et al, 2020 ; Meiyan et al, 2022 ), as well as for pest and disease classification ( Dai et al, 2020 ; Xia et al, 2021 ) and resistant weed identification ( Eide et al, 2021a ). In addition, remote sensing imagery is linked to specific farm problems through deep learning for the identification of biological and non-biological stresses in crops ( Francesconi et al, 2021 ; Ishengoma et al, 2021 ; Jiang et al, 2021 ; Zhou et al, 2021 ), segmentation, and classification ( He et al, 2021 ; Osco et al, 2021 ; Vong et al, 2021 ). These studies show that the combination of UAV remote sensing and deep learning provides the scope for large-scale resistant weed evaluation ( Krähmer et al, 2020 ; Wang et al, 2022 ).…”