|
|
|
|
|
|
| Extraction of Impervious Surfaces in Towns Based on UAV Hyperspectral Imagery |
| ZHANG Yi-ting1, 2, LU Dong-hua1, 2*, WU Ding1, 2, GAO Yan1, 2 |
1. National Key Laboratory of Uranium Resource Exploration-Mining and Nuclear Remote Sensing，Beijing 100029, China
2. Beijing Research Institute of Uranium Geology，Beijing 100029, China
|
|
|
|
|
Abstract Remote sensing images acquired by UAV-mounted hyperspectral sensors have the advantages of rich spectral information and high spatial resolution, which can provide more effective data for extracting impervious surfaces in towns and cities. However, hyperspectral images contain many bands, information redundancy increases the complexity of model training, and the volume of data space grows exponentially with data dimensions. The limited sample size will be sparsely distributed in high-dimensional space, easily leading to model overfitting. In addition, the traditional extraction method has limited feature learning capability, is ineffective in dealing with high-dimensional data, and fails to focus on the specific material information of the impervious surface. To make more effective use of UAV hyperspectral data to obtain information on impervious surfaces in towns and assess the development of town construction, this study selects Donghuayuan Town, Huailai County, Zhangjiakou City, Hebei Province, as the study area and acquires 150 effective bands from airborne hyperspectral remote sensing data. On this basis, the hyperspectral feature bands applicable to extracting impervious surfaces in towns were selected using stepwise discriminant analysis, validated, and comprehensively analyzed using principal component analysis, band standard deviation, and inter-band correlation, and 14 representative bands were finally identified. Subsequently, a remote sensing impervious surface extraction method based on a convolutional neural network was proposed. By improving the AlexNet network architecture, a deep learning network model containing four convolutional layers, one pooling layer, and two fully connected layers was constructed. Finally, two sets of comparison experiments were designed in the study area to compare the information extraction accuracy of impervious surfaces in hyperspectral raw images with selected feature bands and the information extraction accuracy of the proposed network model with common impervious surface extraction methods, respectively. The experimental results show that the selected combination of feature bands can be used as the best combination of bands for impervious surface extraction, which significantly improves the extraction accuracy of various methods. Meanwhile, the network model proposed in this study is the optimal method for impervious surface extraction, and combined with the optimal band combination, the overall accuracy and Kappa coefficient of the final classification reach 99.07% and 0.988 3, respectively, showing excellent performance. The research results in this paper are of great significance for the sustainable development of town construction and ecological and environmental protection and can provide strong support for research in related fields.
|
|
Received: 2024-04-08
Accepted: 2024-08-11
|
|
|
|
Corresponding Authors:
LU Dong-hua
E-mail: alexgreat@126.com
|
|
[1] XU Han-qiu, WANG Mei-ya(徐涵秋, 王美雅). National Remote Sensing Bulletin(遥感学报), 2016, 20(5): 1270.
[2] Liu Ting, Yang Xiaojun. Remote Sensing of Environment, 2013, 133: 251.
[3] Bian G D, Du J K, Song M M, et al. Catena, 2017, 157: 268.
[4] Lu Dengsheng, Weng Qihao. Photogrammetric Engineering & Remote Sensing, 2004, 70(9): 1053.
[5] Van der Linden S, Okujeni A, Canters F, et al. Surveys in Geophysics, 2019, 40(3): 471.
[6] Van der Linden S, Hostert P. Remote Sensing of Environment, 2009, 113(11): 2298.
[7] Cao Jingjing, Leng Wanchun, Liu Kai, et al. Remote Sensing, 2018, 10(1): 89.
[8] Tang Fei, Xu Hanqiu. Remote Sensing, 2017, 9(6): 550.
[9] Li Wenliang. Remote Sensing, 2020, 12(1): 94.
[10] Carlson T N, Arthur S T. Global and Planetary Change, 2000, 25(1-2): 49.
[11] Xu Hanqiu. Photogrammetric Engineering & Remote Sensing, 2010, 76(5): 557.
[12] Sun Zhongchang, Wang Cuizhen, Guo Huadong, et al. Remote Sensing, 2017, 9(9): 942.
[13] Zhang Lihao, Tian Yugang, Liu Qingwei. Remote Sensing, 2021, 13(1): 3.
[14] Im Jungho, Lu Zhenyu, Rhee Jinyoung, et al. Remote Sensing of Environment, 2012, 117: 102.
[15] Parent Jason R, Volin John C, Civco Daniel L. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 104: 18.
[16] HE Jia-jun，LIU Xiang-tong，TU Li-ping, et al（何佳君, 刘向铜, 涂梨平, 等）. Bulletin of Surveying and Mapping（测绘通报）, 2020，(8): 1.
[17] Sun Zhongchang, Guo Huadong, Li Xinwu, et al. Journal of Applied Remote Sensing, 2011, 5(1): 053501.
[18] Okujeni Akpona, van der Linden Sebastian, Hostert Patrick. Remote Sensing of Environment, 2015, 158: 69.
[19] Pandey Dwijendra, Tiwari K C. Geocarto International, 2022, 37(6): 1722.
[20] Guo Xiaojiao, Zhang Chengcai, Luo Weiran, et al. IEEE Access, 2020, 8: 226609.
[21] Dong Xuegang, Meng Zhiguo, Wang Yongzhi, et al. Remote Sensing, 2021, 13(1): 153.
[22] SUN Gen-yun，WANG Xin，AN Na, et al（孙根云, 王 鑫, 安 娜, 等）. Acta Geodaetica et Cartographica Sinica（测绘学报）, 2023, 52(2): 272.
[23] Fu Yongyong, Liu Kunkun, Shen Zhangquan, et al. Remote Sensing, 2019, 11(3): 280.
[24] Huang Fenghua, Yu Ying, Feng Tinghao. Journal of Visual Communication and Image Representation, 2019, 58: 453.
[25] Parekh Jash R, Poortinga Ate, Bhandari Biplov, et al. Remote Sensing, 2021, 13(16): 3166.
[26] Zheng Zezhong, Yang Boya, Liu Shijie, et al. Remote Sensing Applications: Society and Environment, 2023, 30: 100974.
[27] Donoho David L. High-Dimensional Data Analysis: The curses and Blessings of Dimensionality. AMS Math Challenges Lecture, 2000.
[28] LI Ya-fei，DONG Hong-bin（李亚飞, 董红斌）. CAAI Transactions on Intelligent Systems（智能系统学报）, 2018, 13(4): 550.
|
| [1] |
CHEN Xin-gang1, 2, ZHANG Wen-xuan1, MA Zhi-peng1*, ZHANG Zhi-xian1, WAN Fu3, AO Yi1, ZENG Hui-min1. Improved Convolutional Neural Network Quantification of Mixed Fault Characterization Gases in Transformers Based on Raman Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(04): 932-940. |
| [2] |
CHEN Jin-ni, TIAN Gu-feng*, LI Yun-hong, ZHU Yao-lin, CHEN Xin, MEN Yu-le, WEI Xiao-shuang. Near-Infrared Spectral Prediction Model for Cashmere and Wool Based on Two-Way Multiscale Convolution[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(03): 678-684. |
| [3] |
ZHAO Xin1, 4, SHI Yu-na1, LIU Yi-tong1, JIANG Hong-zhe2, CHU Xuan3, ZHAO Zhi-lei1, 4, WANG Bao-jun1, 4*, CHEN Han1. Key Feature Analysis in Identification and Authenticity of Ziziphi Spinosae Semen by Using Hyperspectral Images Based on 1DCNN and PLSDA[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(03): 869-877. |
| [4] |
TANG Qing-ju1, 2, GU Zhuo-yan1, BU Hong-ru2, XU Gui-peng2, TAN Xin-jie2, XIE Rui2. Infrared Thermography Detection of GFRP/NOMEX Honeycomb
Sandwich Structure Defects Based on Convolutional Neural Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(02): 542-550. |
| [5] |
GUO Li-xiao1, 2, CHEN Zhi-chao1*, MA Yan-peng1, 2, BIAN Ming-bo1, 2, FAN Yi-guang2, CHEN Ri-qiang2, LIU Yang2, FENG Hai-kuan2, 3*. Estimation of Potato LAI Using UAV Multispectral and Multiband
Combined Textures[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(12): 3443-3454. |
| [6] |
JIA Tong-hua1, CHENG Guang-xu1*, YANG Jia-cong1, CHEN Sheng2, WANG Hai-rong3, HU Hai-jun1. Research of Chlorine Concentration Inversion Method Based on 1D-CNN Using Ultraviolet Spectral[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(11): 3109-3119. |
| [7] |
SHI Rui1, 2, ZHANG Han2, WANG Cheng1, 2, KANG Kai2, LUO Bin1, 2*. Detection of Wheat Single Seed Vigor Using Hyperspectral Imaging and Spectrum Fusion Strategy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(11): 3206-3212. |
| [8] |
LIU Yu-juan1, 2, 3, LIU Yan-da1, 2, 3, YAN Zhen1, 4, ZHANG Zhi-yong1, 2, 3, CAO Yi-ming1, 2, 3, SONG Ying1, 2, 3*. Classification of Hybrid Convolution Hyperspectral Images Based on
Attention Mechanism[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(10): 2916-2922. |
| [9] |
DENG Yun1, 2, WU Wei1, 2, SHI Yuan-yuan3, CHEN Shou-xue1, 2*. Red Soil Organic Matter Content Prediction Model Based on Dilated
Convolutional Neural Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(10): 2941-2952. |
| [10] |
HAN Bo-chong1, 2, SONG Yi-han1, 2*, ZHAO Yong-heng1, 2. Classification of Star Spectrum Based on Multi-Scale Feature Fusion[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(08): 2284-2288. |
| [11] |
LI Hao1, YU Hao1, CAO Yong-yan1, HAO Zi-yuan1, 2, YANG Wei1, 2*, LI Min-zan1, 2. Hyperspectral Prediction of Soil Organic Matter Content Using
CARS-CNN Modelling[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(08): 2303-2309. |
| [12] |
LIAN Bing-rui1, 2, LI Ya-hao1, 3, ZHANG Jing2, LI Chang-qing4, YANG Xiao-dong5*, WANG Ji-qing2, ZOU Guo-yuan1, Thompson Rodney6, YANG Jun-gang1*. Prediction of Total Nitrogen Content of Lettuce Based on UAV
Multi-Spectral Vegetation Index[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(08): 2318-2325. |
| [13] |
LI Rong1, CAO Guan-long1*, PU Yuan2*, QIU Bo1, WANG Xiao-min1, YAN Jing1, WANG Kun1. TDSC-Net: A Two-Dimensional Stellar Spectra Classification Model Based on Attention Mechanism and Feature Fusion[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(07): 1968-1973. |
| [14] |
QIAO Zhi1, JIANG Qun-ou1, 2*, LÜ Ke-xin1, GAO Feng1. Retrieval Model for Water Quality Parameters of Miyun Reservoir Based on UAV Hyperspectral Remote Sensing Data and Deep Neural Network
Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(07): 2066-2074. |
| [15] |
YU Shui1, HUAN Ke-wei1*, LIU Xiao-xi2, WANG Lei1. Quantitative Analysis Modeling of Near Infrared Spectroscopy With
Parallel Convolution Neural Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(06): 1627-1635. |
|
|
|
|
