Deep Learning Method for Spectral Classification
Authors: 
Tianxu Zhang, Yao Ma, Hang LinAuthors Info & Claims
Tianxu Zhang, Yao Ma, Hang LinAuthors Info & ClaimsPages 61 - 65
Abstract
Spectral images contain both spatial information and spectral information. The resolution of spectral information is very high, generally reaching nanometer level, but the spatial resolution is relatively low. Spectral image classification is a pixel level classification problem [1]. Specifically, it is to classify each pixel in the image and confirm the category of the pixel.Spectral image classification can be divided into unsupervised classification and supervised classification (including semi supervised classification) [2]. Unsupervised classification in deep learning refers to the classification (clustering) of spectral images without data labels in advance. The main idea is to classify similar pixels into one group according to the characteristic information (spatial information, spectral information and characteristics, etc.) that can represent the characteristics of pixels [3]. Supervised classification refers to the classification of spectral images when there are pre-labeled data as supervisory signals. The main idea is to use the labeled data to learn the intrinsic relationship between pixel feature information and pixel categories, and then use this relationship to classify the unlabeled data to determine the pixel category [4].
References
[1]
Zhang Tianxu, Fang Zheng, Liu Xiangyan, etc. A multi-band moving target spectral feature detection and identification method and device. Invention patent, Chinese invention patent grant number: ZL 201110430969.9, US international patent application number: PCT/CN2012/070094, publication number : WO2013091286 A1.
[2]
W. Li, G. Wu, Q. Du, “Transferred Deep Learning for Anomaly Detection in Hyperspectral Imagery,” IEEE Geoscience and Remote Sensing Letters, vol. 14, no. 5, 597-601, May 2017.
[3]
X. Xu, W. Li, Q. Ran, Q. Du, L. Gao, and B. Zhang,“Multisource Remote Sensing Data Classification Based on Convolutional Neural Network,” IEEE Transactions on Geoscience and Remote Sensing, vol. 56, no.2, pp.937-949,Feb 2018.
[4]
M. Zhang, W. Li, Q. Du, L. Gao, and B. Zhang, “FeatureExtraction for Classification of Hyperspectral and LiDAR Data Using Patch-to-Patch CNN,” IEEE Transactions on Cybernetics, vol. 50, no.1, pp.100-111,January 2020.
[5]
Qiu Yunfei, Wang Xingping, Wang Chunyan, Meng Lingguo. Hyperspectral image classification using cascade multi-classifier[J]. Journal of Image and Graphics, 2019, 24(11): 2021-2034.
[6]
Liu Wanjun, Yin Xiu, Qu Haicheng, Liu Lamei. Variable- dimensional convolutional neural network for improving the classification performance of small-sample hyperspectral images[J]. Journal of Image and Graphics, 2019, 24(9):1604-1618.
[7]
Li Yu, Zhen Chang, Shi Xue, Zhao Quanhua. Hyperspectral image classification based on entropy weighted K-means global information clustering[J]. Journal of Image and Graphics, 2019, 24(4): 630-638
[8]
Fang Shuai, Zhu Fengjuan, Dong Zhangyu, Zhang Jing.Hyperspectral image classification based on sample optimization[J]. Journal of Image and Graphics, 2019, 24(1):135-148.
[9]
Ran Qiong, Yu Haoyang, Gao Lianru, Li Wei, Zhang Bing.Hyperspectral image classification combining super-pixel and subspace projection support vector machine[J]. Journal of Image and Graphics, 2018,23(1): 95-105 .
[10]
Zhao Jiewen, Liu Jianhua, Chen Quansheng, etc. Using hyperspectral image technology to detect minor damage to fruits[J]. Transactions of the Chinese Society of Agricultural Machinery, 2008, 39(01): 106-109.
[11]
Li Xueke. Research on geometric processing technology of imaging spectrum data of rotary-wing UAV[D]. Beijing:University of Chinese Academy of Sciences, 2014
[12]
Liu Zhe, Hao Chongyang, Liu Xiaoxiang, etc. Research on the Pixel-Level Fusion of Multispectral Image and Panchromatic Image[J]. Data Acquisition and Processing,2003, 18(03): 296-301.
[13]
W. Li, G. Wu, F. Zhang, Q. Du, “Hyperspectral Image Classification Using Deep Pixel-Pair Features,” IEEE Transactions on Geoscience and Remote Sensing, vol. 55, no. 2, 844-853, Feb. 2017
Index Terms
- Deep Learning Method for Spectral Classification
Index terms have been assigned to the content through auto-classification.
Recommendations
Effects of the deep learning-based super-resolution method on thermal image classification applications
AbstractThermal imaging can be used in many sectors such as public security, health, and defense in image processing. However, thermal imaging systems are very costly, limiting their use, especially in the medical field. Also, thermal camera systems ...
Deep learning for multisensor image resolution enhancement
GeoAI '17: Proceedings of the 1st Workshop on Artificial Intelligence and Deep Learning for Geographic Knowledge DiscoveryWe describe a deep learning convolutional neural network (CNN) for enhancing low resolution multispectral satellite imagery without the use of a panchromatic image. For training, low resolution images are used as input and corresponding high resolution ...
Improved classification with allocation method and multiple classifiers
We propose a new allocation method for building a classification ensemble.Allocation method uses multiple classifiers: the allocator and micro classifiers.Allocator separates the dataset and allocates them to one of micro classifiers.Allocator is based ...
Comments
Information & Contributors
Information
Published In
November 2020
191 pages
ISBN:9781450388368
DOI:10.1145/3441250
Copyright © 2020 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 29 May 2021
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ICAIP 2020
ICAIP 2020: 2020 4th International Conference on Advances in Image Processing
November 13 - 15, 2020
Chengdu, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 30Total Downloads
- Downloads (Last 12 months)7
- Downloads (Last 6 weeks)0
Reflects downloads up to 27 Jan 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format