|
|
|
|
|
|
Land-Based Hyperspectral Imaging and Core Drive Model for Ground
Object Classification |
WANG Qiang-hui, SHEN Xue-ju, ZHOU Bing*, HUA Wen-shen, YING Jia-ju, ZHAO Jia-le |
Electronic and Optical Engineering Department, Army Engineering University of PLA, Shijiazhuang 050003, China
|
|
|
Abstract Hyperspectral imaging technology is an advanced image acquisition technology which can not only obtain the spatial information of ground objects but also the spectral information of ground objects to obtain the three-dimensional image data of “atlas integration”. Its spectral resolution is very high, and its curve is nearly continuous. It can effectively detect ground objects that cannot be detected in multispectral imaging technology and has been widely used in target detection, ground object classification and image compression. Among them, ground object classification can distinguish different types of ground objects in images, and the classification results are the basic data of thematic mapping, which has achieved good results in military, agricultural, geological and other fields.Ground object classification refers to assigning category labels to pixels in images, that is, assigning the same labels to similar ground objects and different labels to different kinds of ground objects. According to whether the target spectral information has been obtained before classification, ground object classification can be divided into supervised classification, semi-supervised classification and unsupervised classification. However, the spectrum of ground objects is greatly affected by imaging conditions, especially for land-based imaging. The spectrum of ground objects will change to a certain extent under different imaging conditions and is no longer strictly unique so that it cannot be accurately classified according to the spectral data of ground objects under unknown imaging conditions. However, the scattering ratio coefficient of the same ground object is unique, has nothing to do with imaging conditions or detection direction, is not affected by the characteristics of bidirectional reflection, and is only related to the type of ground object. It is a physical quantity reflecting the essential attributes of ground objects, so it can be used as the basis for classifying them. In this paper, the scattering of various ground objects are measured under ground-based imaging conditions, the measurement process of scattering weights is described in detail and the fitting ability of the kernel-driven model is verified. Through comparison, it is found that the scattering coefficients of different ground objects have great differences, and then the method of using scattering coefficients to classify ground objects is put forward.In this paper, two sets of data are used to verify the classification method, and three similarity measures, including projection, distance and amount of information, are used to measure the classification results quantitatively.The experimental results show that the scattering coefficients of the same ground object are almost the same, which has nothing to do with the imaging conditions but only with the type of ground object. The scattering coefficients of different ground objects are different, and using scattering coefficients can effectively achieve the classification of ground objects, and good results have been achieved.
|
Received: 2021-10-14
Accepted: 2022-05-25
|
|
Corresponding Authors:
ZHOU Bing
E-mail: zhbgxgc@163.com
|
|
[1] Lin He, Quan Pan, Wei Di, et al. Pattern Recognition Letters, 2008, 29(9): 1392.
[2] Imani M. IEEE Geoscience & Remote Sensing Letters, 2017, 14(8): 1313.
[3] Zhang Junning, Su Qunxing, Gu Hongqiang, et al. Neurocomputing, 2020, 403: 182.
[4] ZHANG Yan, HUA Wen-shen, HUANG Fu-yu, et al(张 炎,华文深,黄富瑜,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2020, 40(6): 1902.
[5] Rougean J L, Leroy M, Deschamps P Y. Journal of Geophysical Research: Atmospheres, 1992, 97(D18): 20455.
[6] Li Xiaowen, Gao Feng, Wang Jindi, et al. Journal of Geophysical Research Atmospheres, 2001, 106(D11): 11925.
[7] CHENG Chen, YANG Shi-zhi, CUI Sheng-cheng, et al(程 晨,杨世植,崔生成, 等). Journal of Atmospheric and Environmental Optics(大气与环境光学学报), 2016, 11(3): 211.
[8] Chang C I, Heinz D C. IEEE Transactions on Geoscience & Remote Sensing, 2000, 38(3): 1144.
[9] Honkavaar A E,Eskelinen M A,P L Nen I, et al. Geoscience and Remote Sensing, 2016, 9 (54): 5440.
[10] Gao Jianbao, Liu Feiyan, Zhang Jianfang, et al. Entropy, 2013, 15(12): 3396.
[11] Cheah T C, Shanmugam S A, Ang L M. Journal of Medical Imaging and Health Informatics, 2012, 2(3): 313.
|
[1] |
CHU Bing-quan1, 2, LI Cheng-feng1, DING Li3, GUO Zheng-yan1, WANG Shi-yu1, SUN Wei-jie1, JIN Wei-yi1, HE Yong2*. Nondestructive and Rapid Determination of Carbohydrate and Protein in T. obliquus Based on Hyperspectral Imaging Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3732-3741. |
[2] |
LIU Xin-peng1, SUN Xiang-hong2, QIN Yu-hua1*, ZHANG Min1, GONG Hui-li3. Research on t-SNE Similarity Measurement Method Based on Wasserstein Divergence[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3806-3812. |
[3] |
YUAN Wei-dong1, 2, JU Hao2, JIANG Hong-zhe1, 2, LI Xing-peng2, ZHOU Hong-ping1, 2*, SUN Meng-meng1, 2. Classification of Different Maturity Stages of Camellia Oleifera Fruit
Using Hyperspectral Imaging Technique[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3419-3426. |
[4] |
SHEN Ying, WU Pan, HUANG Feng*, GUO Cui-xia. Identification of Species and Concentration Measurement of Microalgae Based on Hyperspectral Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3629-3636. |
[5] |
YANG Lei1, 2, 3, ZHOU Jin-song1, 2, 3, JING Juan-juan1, 2, 3, NIE Bo-yang1, 3*. Non-Uniformity Correction Method for Splicing Hyperspectral Imager Based on Overlapping Field of View[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3582-3590. |
[6] |
DONG Jian-jiang1, TIAN Ye1, ZHANG Jian-xing2, LUAN Zhen-dong2*, DU Zeng-feng2*. Research on the Classification Method of Benthic Fauna Based on
Hyperspectral Data and Random Forest Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3015-3022. |
[7] |
WEI Zi-kai, WANG Jie, ZHANG Ruo-yu, ZHANG Meng-yun*. Classification of Foreign Matter in Cotton Using Line Scan Hyperspectral Transmittance Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3230-3238. |
[8] |
SUN Bang-yong1, YU Meng-ying1, YAO Qi2*. Research on Spectral Reconstruction Method From RGB Imaging Based on Dual Attention Mechanism[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(09): 2687-2693. |
[9] |
JIN Chun-bai1, YANG Guang1*, LU Shan2*, LIU Wen-jing1, LI De-jun1, ZHENG Nan1. Band Selection Method Based on Target Saliency Analysis in Spatial Domain[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(09): 2952-2959. |
[10] |
MAO Yi-lin1, LI He1, WANG Yu1, FAN Kai1, SUN Li-tao2, WANG Hui3, SONG Da-peng3, SHEN Jia-zhi2*, DING Zhao-tang1, 2*. Quantitative Judgment of Freezing Injury of Tea Leaves Based on Hyperspectral Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(07): 2266-2271. |
[11] |
LIU Gang1, LÜ Jia-ming1, NIU Wen-xing1, LI Qi-feng2, ZHANG Ying-hu2, YANG Yun-peng2, MA Xiang-yun2*. Detection of Sulfur Content in Vessel Fuel Based on Hyperspectral
Imaging Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(06): 1697-1702. |
[12] |
LI Bin, HAN Zhao-yang, WANG Qiu, SUN Zhao-xiang, LIU Yan-de*. Research on Bruise Level Detection of Loquat Based on Hyperspectral
Imaging Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(06): 1792-1799. |
[13] |
HU Hui-qiang1, WEI Yun-peng1, XU Hua-xing1, ZHANG Lei2, MAO Xiao-bo1*, ZHAO Yun-ping2*. Identification of the Age of Puerariae Thomsonii Radix Based on Hyperspectral Imaging and Principal Component Analysis[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(06): 1953-1960. |
[14] |
ZHANG Fan1, WANG Wen-xiu1, ZHANG Yu-fan1, HU Ze-xuan1, ZHAO Dan-yang1, MA Qian-yun1, SHI Hai-yan2, SUN Jian-feng1*. Hyperspectral and Ensemble Learning Method for Rapid Identification of Black Spot in Yali Pear at Gley Stage[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(05): 1541-1549. |
[15] |
GUO Feng1, ZHAO Dong-e1*, YANG Xue-feng1, CHU Wen-bo2, ZHANG Bin1, ZHANG Da-shun3MENG Fan-jun3. Research on Hyperspectral Image Recognition of Iron Fragments[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(04): 997-1003. |
|
|
|
|