• Corpus ID: 219177478

Integrating global spatial features in CNN based Hyperspectral/SAR imagery classification

@article{Zhang2020IntegratingGS,
  title={Integrating global spatial features in CNN based Hyperspectral/SAR imagery classification},
  author={Fan Zhang and MinChao Yan and Chen Hu and Jun Ni and Fei Ma},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.00234}
}
The land cover classification has played an important role in remote sensing because it can intelligently identify things in one huge remote sensing image to reduce the work of humans. However, a lot of classification methods are designed based on the pixel feature or limited spatial feature of the remote sensing image, which limits the classification accuracy and universality of their methods. This paper proposed a novel method to take into the information of remote sensing image, i.e… 

References

SHOWING 1-10 OF 25 REFERENCES

Land-cover classification with high-resolution remote sensing images using transferable deep models

  • Xin-Yi TongGuisong Xia Liangpei Zhang
  • Environmental Science, Mathematics
    Remote Sensing of Environment
  • 2020

Land Cover Classification for Satellite Images Through 1D CNN

  • Yang SongZhifei Zhang H. Qi
  • Environmental Science, Mathematics
    2019 10th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS)
  • 2019
TLDR
A 1D convolution neural network-based framework applied to each pixel in the spectral domain where it is shown that superior classification accuracy is demonstrated through comparison with traditional unmixing-based and neural network methods using just limited number of training samples.

Classification of multitemporal SAR images using convolutional neural networks and Markov random fields

TLDR
This study investigates the use of Convolutional Neural Networks which can effectively learn a bank of spatial filters to simultaneously reduce speckle noise, and extract spatial-contextual features to characterize texture and scattering mechanism.

Evaluation of Deep Learning CNN Model for Land Use Land Cover Classification and Crop Identification Using Hyperspectral Remote Sensing Images

  • K. BhosleV. Musande
  • Environmental Science, Computer Science
    Journal of the Indian Society of Remote Sensing
  • 2019
TLDR
Examination of the use of deep learning CNN for LULC classification on Indian Pines dataset and for crop identification on study area dataset demonstrates that CNN works well in practice for unstructured data as well as for small size dataset.

A Hybrid DBN and CRF Model for Spectral-Spatial Classification of Hyperspectral Images

TLDR
Experiments show that the proposed DBN-CRF model outperforms the most recent approaches in hyperspectral image classification and can fully use the strength of both DBN and CRF.

Deep Learning-Based Classification of Hyperspectral Data

TLDR
The concept of deep learning is introduced into hyperspectral data classification for the first time, and a new way of classifying with spatial-dominated information is proposed, which is a hybrid of principle component analysis (PCA), deep learning architecture, and logistic regression.

Fusion of hyperspectral and LiDAR data using random feature selection and morphological attribute profiles

TLDR
This paper presents a new fusion approach based on random feature selection (RFS) and morphological attribute profiles (AP) derived from first return LiDAR data collected over the Samford ecological research facility, Queensland, Australia and indicates that the proposed approach yields excellent classification results.

SAR Target Small Sample Recognition Based on CNN Cascaded Features and AdaBoost Rotation Forest

TLDR
An improved CNN model is proposed to solve the limited sample issue via the feature augmentation and ensemble learning strategies and can improve the recognition accuracy by about 20% under the condition of ten training samples per class.

Multifrequency Polsar Image Classification Using Dual-Band 1D Convolutional Neural Networks

TLDR
This work proposes a novel classification approach based on dual-band one-dimensional Convolutional Neural Networks for classification of multifrequency polarimetric SAR (PolSAR) data that yields a superior computational efficiency compared to the deep 2D-CNN based approaches.

Research on mangrove recognition based on hyperspectral unmixing

Mangrove is one of the typical vegetation at the junction of land and sea which is of great significance to the ecological environment protection of the waterfront and surrounding area. The existing