Convolutional neural network for hyperspectral image classification
Hyperspectral Image Classification is an important research problem in remote sensing.Classification is one of the most popular topic in hyperspectral remote sensing. In the last twenty years, a huge quantity of methods were proposed to deal with the hyperspectral data classification problem. Deep l...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
2016
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/68979 |
| _version_ | 1826121809319165952 |
|---|---|
| author | Yuan, Nanqi |
| author2 | Wang Gang |
| author_facet | Wang Gang Yuan, Nanqi |
| author_sort | Yuan, Nanqi |
| collection | NTU |
| description | Hyperspectral Image Classification is an important research problem in remote sensing.Classification is one of the most popular topic in hyperspectral remote sensing. In the last twenty years, a huge quantity of methods were proposed to deal with the hyperspectral data classification problem. Deep learning has been shown to be very promissing for this problem. However, existing deep learning methods only try to learn features from a pixel/region independently without considering the dependency between different pixels/regions.This project will employ Convolutional Neural Networks for learning features based on the spatial-spectral information of hyperspectral images. Experiments are conducted on benchmark datasets. |
| first_indexed | 2024-10-01T05:38:35Z |
| format | Thesis |
| id | ntu-10356/68979 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:38:35Z |
| publishDate | 2016 |
| record_format | dspace |
| spelling | ntu-10356/689792023-07-04T15:05:09Z Convolutional neural network for hyperspectral image classification Yuan, Nanqi Wang Gang School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing Hyperspectral Image Classification is an important research problem in remote sensing.Classification is one of the most popular topic in hyperspectral remote sensing. In the last twenty years, a huge quantity of methods were proposed to deal with the hyperspectral data classification problem. Deep learning has been shown to be very promissing for this problem. However, existing deep learning methods only try to learn features from a pixel/region independently without considering the dependency between different pixels/regions.This project will employ Convolutional Neural Networks for learning features based on the spatial-spectral information of hyperspectral images. Experiments are conducted on benchmark datasets. Master of Science (Signal Processing) 2016-08-22T06:38:50Z 2016-08-22T06:38:50Z 2016 Thesis http://hdl.handle.net/10356/68979 en 59 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing Yuan, Nanqi Convolutional neural network for hyperspectral image classification |
| title | Convolutional neural network for hyperspectral image classification |
| title_full | Convolutional neural network for hyperspectral image classification |
| title_fullStr | Convolutional neural network for hyperspectral image classification |
| title_full_unstemmed | Convolutional neural network for hyperspectral image classification |
| title_short | Convolutional neural network for hyperspectral image classification |
| title_sort | convolutional neural network for hyperspectral image classification |
| topic | DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing |
| url | http://hdl.handle.net/10356/68979 |
| work_keys_str_mv | AT yuannanqi convolutionalneuralnetworkforhyperspectralimageclassification |