基于无人机遥感的荒漠草原微斑块识别研究

doi:10.16088/j.issn.1001-6600.2022022303

摘要/Abstract

摘要： 荒漠草原是草原的极限状态,也是草原向荒漠过渡的一类草原。荒漠草原不同群落斑块之间的识别是评价草原荒漠化的一个重要指标。探索一种高效、快速的识别荒漠草原不同群落斑块之间的分布情况对动态监测草原荒漠化进程和合理开发草地资源有重要意义。本文以无人机搭载高光谱仪进行荒漠草原遥感影像数据采集,利用主成分分析(PCA)对数据进行降维。通过对卷积神经网络进行改进,将不同卷积层的特征进行融合,进而提出一种具有多层特征融合的2D卷积神经网络(MFF-2DCNN)识别方法。结果表明,该模型对荒漠草原微斑块识别总体精度达92.23%,与SVM、KNN和原始2D-CNN相比分别提升4.35、25.71、0.95个百分点。无人机遥感与卷积神经网络的有效结合为荒漠草原不同群落斑块之间的识别分类提供新思路。

关键词: 高光谱图像, 卷积神经网络, 识别分类, 荒漠草原, 微斑块,无人机

Abstract: Desert steppe is the limit state of steppe and the transition from steppe to desert steppe. The identification of patches among different communities in desert steppe areas is important for evaluating grassland desertification. It’s valuabe to explore an efficient and rapid way to identify the distribution of patches among different communities in desert steppe areas for the dynamic monitoring of grassland desertification and the rational use and preservation of grassland resources. In this paper, remote sensing image data from desert grassland areas are collected by a UAV equipped with a high-resolution spectrometer, and principal component analysis (PCA) is used to reduce the dimensionality of the data. After improving the convolutional neural network and fusing the features of different convolutional layers, a 2D convolutional neural network (MFF-2DCNN) recognition method with multilayer feature fusion is proposed. The results show that the overall accuracy of the model for micropatch recognition in desert steppe areas is 92.23%, which is 4.35, 25.71 and 0.95 percentage points higher than that of an SVM, a KNN model and the original 2D-CNN model, respectively. The effective combination of UAV remote sensing and convolution neural network provides a new idea for the identification and classification of different communities in desert steppe.

Key words: hyperspectral image, convolution neural network, recognition and classification, desert steppe, micro-patch;unmanned aerial vehicle

中图分类号:

S812

张涛, 杜建民. 基于无人机遥感的荒漠草原微斑块识别研究[J]. 广西师范大学学报（自然科学版）, 2022, 40(6): 50-58.

ZHANG Tao, DU Jianmin. Research on Micro-patch Identification of Desert Grassland Based on UAV Remote Sensing[J]. Journal of Guangxi Normal University(Natural Science Edition), 2022, 40(6): 50-58.

参考文献

[1] 张庆, 刘璐瑶, 徐雪, 等. 内蒙古草原家庭牧场可持续发展研究[J]. 草业学报, 2021,30(9): 168-181. DOI: 10.11686/cyxb2021058.
[2] 刘荣荣, 王平, 代心灵, 等. 不同密度布氏田鼠对内蒙古典型草原菌根真菌群落的影响[J]. 草业学报, 2021,30(11): 76-86. DOI: 10.11686/cyxb2021113.
[3] BAI Y F, WU J G, PAN Q M, et al. Positive linear relationship between productivity and diversity: evidence from the Eurasian steppe[J]. The Journal of Applied Ecology, 2007,44(5): 1023-1034. DOI: 10.1111/j.1365-2664.2007.01351.x.
[4] ZHANG X M, JOHNSTON E R, BARBERÁN A, et al. Decreased plant productivity resulting from plant group removal experiment constrains soil microbial functional diversity[J]. Global Change Biology, 2017,23(10): 4318-4332. DOI: 10.1111/gcb.13783.
[5] SHANG C W, WU T, HUANG G L, et al. Weak sustainability is not sustainable: socioeconomic and environmental assessment of Inner Mongolia for the past three decades[J]. Resources, Conservation and Recycling, 2019,141: 243-252. DOI: 10.1016/j.resconrec.2018.10.032.
[6] HE D, HUANG X L, TIAN Q J, et al. Changes in vegetation growth dynamics and relations with climate in Inner Mongolia under more strict multiple pre-processing (2000-2018)[J]. Sustainability, 2020,12(6): 2534. DOI: 10.3390/su12062534.
[7] WANG C W, CHEN Q, FAN H S, et al. Evaluating satellite hyperspectral (Orbita) and multispectral (Landsat 8 and Sentinel-2) imagery for identifying cotton acreage[J]. International Journal of Remote Sensing, 2021,42(11): 4042-4063. DOI: 10.1080/01431161.2021.1887543.
[8] LI K, WANG L, YIN D M. Deriving corn and soybeans fractions with land remote-sensing satellite (system, Landsat) imagery by accounting for endmember variability on Google Earth Engine[J]. International Journal of Remote Sensing, 2021,42(12): 4493-4513. DOI: 10.1080/01431161.2021.1897184.
[9] 陈千, 陈利霞. 基于张量环分解的非局部高光谱图像去噪算法[J].桂林电子科技大学学报,2021,41(2):146-153.DOI: 10.16725/j.cnki.cn45-1351/tn.2021.02.010.
[10] 王丽,王威,刘勃妮.基于免疫克隆的图像稀疏分解算法研究[J].电子设计工程,2021,29(7):1-5.DOI: 10.14022/j.issn1674-6236.2021.07.001.
[11] 郭棚跃,刘振丙.一种基于栈式压缩自编码的高光谱图像分类方法[J].桂林电子科技大学学报,2021,41(4):298-304.DOI: 10.16725/j.cnki.cn45-1351/tn.2021.04.007.
[12] CHEN S Z, GAO Y, FAN K, et al. Prediction of drought-induced components and evaluation of drought damage of tea plants based on hyperspectral imaging[J]. Frontiers in Plant Science, 2021,12: 695102. DOI: 10.3389/fpls.2021.695102.
[13] ACHARYA B S, BHANDARI M, BANDINI F, et al. Unmanned aerial vehicles in hydrology and water management: applications, challenges, and perspectives[J]. Water Resources Research, 2021,57(11): e2021WR029925. DOI: 10.1029/2021WR029925.
[14] ZHOU J F, PAVEK M J, SHELTON S C, et al. Aerial multispectral imaging for crop hail damage assessment in potato[J]. Computers and Electronics in Agriculture, 2016,127: 406-412. DOI: 10.1016/j.compag.2016.06.019.
[15] 康拥朝, 毕玉革, 杜建民, 等. 基于高光谱MNF-SVM法荒漠化草原地表微斑块识别研究[J]. 内蒙古农业大学学报(自然科学版), 2021,42(06): 76-81. DOI: 10.16853/j.cnki.1009-3575.2021.06.013.
[16] 皮伟强, 杜建民, 陈程, 等. 基于高光谱SMPI法的草原地表微斑块识别与分类[J]. 光电子·激光, 2018,29(11): 1237-1243. DOI: 10.16136/j.joel.2018.11.0032.
[17] 朱相兵, 毕玉革, 刘浩, 等. 基于高光谱遥感的荒漠草原鼠洞识别方法研究[J]. 土壤通报, 2020,51(2): 263-268. DOI: 10.19336/j.cnki.trtb.2020.02.02.
[18] CHEN C, ZHANG J J, ZHENG C H, et al. Classification of hyperspectral data using a multi-channel convolutional neural network[C]// Intelligent Computing Methodologies, Cham: Springer, 2018: 81-92. DOI: 10.1007/978-3-319-95957-3_10.
[19] CAI H J, CHEN T. Multi-dimension CNN for hyperspectral image classificaton[C]// IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium. Piscataway: IEEE, 2020: 1275-1278. DOI: 10.1109/IGARSS39084.2020.9323561.
[20] 靳宇曦, 刘芳, 张新杰, 等. 短花针茅荒漠草原生态系统净碳交换对载畜率的响应[J]. 生态环境学报, 2018,27(4): 643-650. DOI: 10.16258/j.cnki.1674-5906.2018.04.007.
[21] 尚天浩, 毛鸿欣, 张俊华, 等. 基于PCA敏感波段筛选与SVM建模的银川平原土壤有机质高光谱估算[J]. 生态学杂志, 2021,40(12): 4128-4136. DOI: 10.13292/j.1000-4890.202112.017.
[22] 欧阳爱国, 万启明, 李雄, 等. 高光谱成像的水稻螟虫蛀入检测方法[J]. 光谱学与光谱分析, 2021,41(12): 3844-3850.
[23] HAQUE M F, KANG D S. PPCNN: object detection using fine-grained feature extraction and localization[J]. Journal of Korean Institute of Information Technology, 2021,19(2): 29-37. DOI: 10.14801/jkiit.2021.19.2.29.

相关文章 12

[1]	潘海明, 陈庆锋, 邱杰, 何乃旭, 刘春雨, 杜晓敬. 基于卷积推理的多跳知识图谱问答算法[J]. 广西师范大学学报（自然科学版）, 2023, 41(1): 102-112.
[2]	田晟, 宋霖. 基于CNN和Bagging集成的交通标志识别[J]. 广西师范大学学报（自然科学版）, 2022, 40(4): 35-46.
[3]	周圣凯, 富丽贞, 宋文爱. 基于深度学习的短文本语义相似度计算模型[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 49-56.
[4]	彭涛, 唐经, 何凯, 胡新荣, 刘军平, 何儒汉. 基于多步态特征融合的情感识别[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 104-111.
[5]	马铖旭, 曾上游, 赵俊博, 陈红阳. 基于卷积神经网络的逆光图像增强研究[J]. 广西师范大学学报（自然科学版）, 2022, 40(2): 81-90.
[6]	陈文康, 陆声链, 刘冰浩, 李帼, 刘晓宇, 陈明. 基于改进YOLOv4的果园柑橘检测方法研究[J]. 广西师范大学学报（自然科学版）, 2021, 39(5): 134-146.
[7]	杨州, 范意兴, 朱小飞, 郭嘉丰, 王越. 神经信息检索模型建模因素综述[J]. 广西师范大学学报（自然科学版）, 2021, 39(2): 1-12.
[8]	邓文轩, 杨航, 靳婷. 基于注意力机制的图像分类降维方法[J]. 广西师范大学学报（自然科学版）, 2021, 39(2): 32-40.
[9]	严浩, 许洪波, 沈英汉, 程学旗. 开放式中文事件检测研究[J]. 广西师范大学学报（自然科学版）, 2020, 38(2): 64-71.
[10]	范瑞,蒋品群,曾上游,夏海英,廖志贤,李鹏. 多尺度并行融合的轻量级卷积神经网络设计[J]. 广西师范大学学报（自然科学版）, 2019, 37(3): 50-59.
[11]	武文雅, 陈钰枫, 徐金安, 张玉洁. 基于高层语义注意力机制的中文实体关系抽取[J]. 广西师范大学学报（自然科学版）, 2019, 37(1): 32-41.
[12]	薛洋,曾庆科,夏海英,王文涛. 基于卷积神经网络超分辨率重建的遥感图像融合[J]. 广西师范大学学报（自然科学版）, 2018, 36(2): 33-41.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed