Hyper-Spectral Characteristics in Support of Object Classification and Verification

被引:1
作者
Zhang, Liren [1 ,2 ]
Lu, Hao [1 ]
Zhang, Hang [1 ]
Zhao, Yuefeng [1 ,2 ]
Xu, Huaqiang [1 ,2 ]
Wang, Jingjing [1 ,2 ]
机构
[1] Shandong Normal Univ, Coll Phys & Elect Sci, Jinan 250014, Shandong, Peoples R China
[2] Shandong Prov Engn & Tech Ctr Light Manipulat, Jinan 250014, Shandong, Peoples R China
关键词
Hyper-spectral image; hyper-spectral image classification; hyper-spectral characteristics; object verification; classification accuracy; SPATIAL CLASSIFICATION; HYPERSPECTRAL IMAGES; RANDOM-FIELDS; REPRESENTATION; CONSTRAINT; FRAMEWORK; MODEL; SVM; CNN;
D O I
10.1109/ACCESS.2019.2936130
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
It is known that a typical hyper-spectral image consists of a sequence of wavelength bands and each wavelength band illustrates a two-dimensional image. This paper presents a HSI classification method including two approaches. The first approach is a probabilistic algorithm for object classification based on the image illustrated by single hyper-spectral wavelength bands, respectively, which generate a sequence of registered object images. Since hyper-spectral images (HSIs) obtained by air-borne or satellite-borne remote sensors has limited size, which may affect the classification accuracy, especially for small objects due to lack of pixels. The second approach investigates the hyper-spectral characteristics for a specific object in terms of uniformed hyper-spectrum energy function in wavelength domain. The hyper-spectral characteristics are applied to object verification, especially for objects which are difficult to distinguish from each other using classic classification methods, so that the accuracy is improved. The classification accuracy for the proposed object-oriented characterization method is evaluated in terms of producer accuracy (PA) and Kappa coefficient based on hyper-spectral images obtained from air-borne or satellite-borne remote sensors, respectively. The numerical results demonstrate that the proposed method can effectively identify and verify objects in hyper-spectral image, especially for those objects that are difficult to be distinguished from each other by classic methods. Furthermore, the proposed object classification method based on hyper-spectral characteristics is compared to conventional methods, including spectral information divergence (SID) method and multiple spectral angle mapper-Markov random fields (MSAM-MRF) method. It can be seen that the accuracy of object classification achieved by the proposed method can be up to 20% higher than that of classic methods.
引用
收藏
页码:119420 / 119429
页数:10
相关论文
共 50 条
[22]   Classification of apple leaf conditions in hyper-spectral images for diagnosis of Marssonina blotch using mRMR and deep neural network [J].
Park, Keunho ;
Hong, Young Ki ;
Kim, Gook Hwan ;
Lee, Joonwhoan .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2018, 148 :179-187
[23]   Enhancing Hyper-Spectral Image Classification with Reinforcement Learning and Advanced Multi-Objective Binary Grey Wolf Optimization [J].
Shoeibi, Mehrdad ;
Nevisi, Mohammad Mehdi Sharifi ;
Salehi, Reza ;
Martin, Diego ;
Halimi, Zahra ;
Baniasadi, Sahba .
CMC-COMPUTERS MATERIALS & CONTINUA, 2024, 79 (03) :3469-3493
[24]   Wood species recognition using hyper-spectral images not sensitive to illumination variation [J].
Wang Cheng-Kun ;
Zhao Peng .
JOURNAL OF INFRARED AND MILLIMETER WAVES, 2020, 39 (01) :72-85
[25]   Identification for weedy rice at seeding stage based on hyper-spectral imaging technique [J].
Chen, S. (srchen@ujs.edu.cn), 1600, Chinese Society of Agricultural Machinery (44) :253-257+163
[26]   Hyper-Spectral Image Analysis With Partially Latent Regression and Spatial Markov Dependencies [J].
Deleforge, Antoine ;
Forbes, Florence ;
Ba, Sileye ;
Horaud, Radu .
IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2015, 9 (06) :1037-1048
[27]   Research on hyper-spectral remote sensing image classification by applying stacked de-noising auto-encoders neural network [J].
Dai, Xiaoai ;
He, Xuwei ;
Guo, Shouheng ;
Liu, Senhao ;
Ji, Fujiang ;
Ruan, Huihua .
MULTIMEDIA TOOLS AND APPLICATIONS, 2021, 80 (14) :21219-21239
[28]   Hierarchical spectrum recognition based on hyper-spectral images -a case study in Lanzhou and Yulin [J].
Liu Wei ;
Sun Hai-Xia ;
Yang Xiao-Bo .
JOURNAL OF INFRARED AND MILLIMETER WAVES, 2020, 39 (01) :99-110
[29]   Research on hyper-spectral remote sensing image classification by applying stacked de-noising auto-encoders neural network [J].
Xiaoai Dai ;
Xuwei He ;
Shouheng Guo ;
Senhao Liu ;
Fujiang Ji ;
Huihua Ruan .
Multimedia Tools and Applications, 2021, 80 :21219-21239
[30]   Hyper-spectral Impulse Denoising: A row-sparse Blind Compressed Sensing Formulation [J].
Majumdar, Angshul ;
Ansari, Naushad ;
Aggarwal, Hemant Kumar .
2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), 2015, :1260-1264