Affiliation:
1. College of Physics and Electronic Information, Gannan Normal University, Ganzhou 341000, China
Abstract
Traditional hyperspectral image semantic segmentation algorithms can not fully utilize the spatial information or realize efficient segmentation with less sample data. In order to solve the above problems, a U-shaped hyperspectral semantic segmentation model (DCCaps-UNet) based on the depthwise separable and conditional convolution capsule network was proposed in this study. The whole network is an encoding–decoding structure. In the encoding part, image features are firstly fully extracted and fused. In the decoding part, images are then reconstructed by upsampling. In the encoding part, a dilated convolutional capsule block is proposed to fully acquire spatial information and deep features and reduce the calculation cost of dynamic routes using a conditional sliding window. A depthwise separable block is constructed to replace the common convolution layer in the traditional capsule network and efficiently reduce network parameters. After principal component analysis (PCA) dimension reduction and patch preprocessing, the proposed model was experimentally tested with Indian Pines and Pavia University public hyperspectral image datasets. The obtained segmentation results of various ground objects were analyzed and compared with those obtained with other semantic segmentation models. The proposed model performed better than other semantic segmentation methods and achieved higher segmentation accuracy with the same samples. Dice coefficients reached 0.9989 and 0.9999. The OA value can reach 99.92% and 100%, respectively, thus, verifying the effectiveness of the proposed model.
Funder
National Natural Science Foundation of China
Subject
General Earth and Planetary Sciences
Reference47 articles.
1. Three decades of hyperspectral remote sensing of the earth: A personal view;Goetz;Remote Sens. Environ.,2009
2. Multilayer nmf for blind unmixing of hyperspectral imagery with additional constraints;Chen;Photogramm. Eng. Remote Sens.,2017
3. A local mahalanobis-distance method based on tensor decomposition for hyperspectral anomaly detection;Zhao;Geocarto Int.,2019
4. Li, C., Wang, Y., Zhang, X., Gao, H., Yang, Y., and Wang, J. (2019). Deep belief network for spectral-spatial classification of hyperspectral remote sensor data. Sensors, 19.
5. A research review on hyperspectral data processing and analysis algorithms;Kale;Proc. Natl. Acad. Sci. India Sect. A-Phys. Sci.,2017
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献