Endmember Bundle Extraction Method Based on Multi-modal and Multi-objective Optimization

被引：0

作者：

Lin J. ^{[1
,2
]}

Chen J. ^{[3
,4
]}

Luo T. ^{[1
,5
]}

Xu Z. ^{[1
,6
]}

机构：

[1] Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, Shenzhen

[2] Key Laboratory of Spatial-temporal Big Data Analysis and Application of Natural Resources in Megacities, Ministry of Natural Resources, Shanghai

[3] College of Engineering, China Agricultural University, Beijing

[4] Shenzhen Key Laboratory of Intelligent Micro satellite Constellation, Shenzhen

[5] State Key Laboratory oj Clean Energy Utilization, Zhejiang University, Hangzhou

[6] Key Laboratory of Intelligent Equipment and Robotics for Agriculture of Zhejiang Province, Zhejiang University, Hangzhou

来源：

Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery | 2023年 / 54卷 / 07期

关键词：

endmember bundle extraction; hyperspectral image; multi-modaland multi-objective optimization algorithm; spectral unmixing;

D O I：

10.6041/j.issn.1000-1298.2023.07.023

中图分类号：

学科分类号：

摘要：

Hyperspectral image has continuous spectral information of ground objects, which is an essential means of remote sensing monitoring. On this basis, the endmembers of the features can be extracted by decomposing the mixed pixel spectrum and exploring the degree of each endmember participates in the mixing. However, specific spectral changes cause trouble for spectral unmixing due to the sensor and the image's resolution. To solve this problem, an endmember bundle extraction method based on multi-modal and multi-objective particle swarm optimization by special crowding distance(MOPSOSCD) was proposed. Firstly, for a three-dimensional hyperspectral image, the label coding was carried out pixel by pixel, and the index-based ring topology was used for individual interaction in different neighborhoods. Secondly, for particle velocity and position update, the position update method of PSO was adopted and the particle swarm velocity update method and the integer particle position update were improved through neighborhood optimization. The objective function selection was measured by two RMSEs, that was, the unconstrained least squares method was used to solve the RMSE of the abundance map anti-mixing and the original map, and the fully constrained least squares method was used to solve the RMSE of the abundance map anti-mixing and the original map. At the same time, according to the spatial characteristics of hyperspectral images, decision space diversity was improved by improving the crowded distance of decision space. Finally, the crowding distances of the decision space and the target space were combined and sorted, and the particles were updated according to the sorting results. When the particle directional movement probability was 0. 2, the number of particles was 30, and the number of iterations was 400, the results of RMSE and mSAD on the MUUFL dataset were 0. 008 8 and 0. 111 2, respectively. Through the comparative test, the method had higher extraction accuracy and efficiency than VCA and DPSO, providing a more accurate end beam extraction method for hyperspectral unmixing. © 2023 Chinese Society of Agricultural Machinery. All rights reserved.

引用

页码：234 / 242

页数：8

共 31 条

[1] WANG Shubo, HAN Yu, CHEN Jian, Et al., Weed classification of remote sensing by UAV in ecological irrigation areas based on deep learning [J], Journal of Drainage and Irrigation Machinery Engineering, 36, 11, pp. 1137-1141, (2018)
[2] ZHANG Zichao, HAN Yu, CHEN Jian, Et al., Information extraction of ecological canal system based on remote sensing data of unmanned aerial vehicle [J], Journal of Drainage and Irrigation Machinery Engineering, 36, 10, pp. 1006-1011, (2018)
[3] LIU Libo, WANG Tao, ZHANG Peng, Yield estimation method of Ningxia wolfberry using hyperspectral images based on CNN-S-GPR[J], Transactions of the Chinese Society for Agricultural Machinery, 53, 8, pp. 250-257, (2022)
[4] LIU Mingxing, LI Changchun, LI Zhenhai, Et al., Estimation of dry aerial mass of winter wheat based on coupled hyperspectral remote sensing and SAFY model[J], Transactions of the Chinese Society for Agricultural Machinery, 51, 2, pp. 192-202, (2020)
[5] GAO Lianru, SUN Xu, LUO Wenfei, Et al., Swarm intelligence algorithms for spectral unmixing in hyperspectral image [J], Journal of Nanjing University of Information Science & Technology (Natural Science Edition), 10, 1, pp. 81-91, (2018)
[6] THESEIRA M A, THOMAS G, TAYLOR J C, Et al., Sensitivity of mixture modelling to end-member selection, International Journal of Remote Sensing, 24, 7, pp. 1559-1575, (2003)
[7] SOMERS B, ZORTEA M, PLAZA A, Et al., Automated extraction of image-based endmember bundles for improved spectral unmixing, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 5, 2, pp. 396-408, (2012)
[8] CANHAM K, SCHLAMM A, ZIEMANN A, Et al., Spatially adaptive hyperspectral unmixing, IEEE Transactions on Geoscience and Remote Sensing, 49, 11, pp. 4248-4262, (2011)
[9] YE G, LIU S, XU M, Et al., An endmember bundle extraction method based on multiscale sampling to address spectral variability for hyperspectral unmixing, Remote Sensing, 13, 19, (2021)
[10] UEZATO T, MURPHY R J, MELKUMYAN A, Et al., A novel endmember bundle extraction and clustering approach for capturing spectral variability within endmember classes, IEEE Transactions on Geoscience and Remote Sensing, 54, 11, pp. 6712-6731, (2016)

← 1 2 3 4 →