账户: 密码:
基于无人机遥感影像芨芨草盖度的图像分割方法
详细信息    查看全文 | 推荐本文 | 收藏本文
摘要
根据像素比计算芨芨草面积占区域总面积的百分比,由此整体估算呼伦贝尔草原芨芨草的盖度。图像分割采用了最大类间方差法,得到类间最大方差值,即最佳阈值。利用阈值对灰度化图像进行分割得到芨芨草和非芨芨草两类物的二值化图像。采用中值滤波和数学形态学相结合的边缘检测法,提取芨芨草图像,将其与非芨芨草图像分割。基于无人机影像,采用图像分割方法,能够有效提取芨芨草图像,与实测芨芨草盖度相比,估算结果准确度高达97.3%。
        The proposed image segmentation method mainly includes three stages: the first stage is using Otsu method to get the maximum variance of gray image between clusters,namely the optimal threshold. The second stage is gray image is segmented by the obtained threshold to generate achnatherum splendens and non achnatherum splendens binary image. The third stage is utilizing edge detection method combines mean filtering with mathematical morphological to extract achnatherum splendens image. and divide it with non achnatherum image.Based on unmanned aerial vehicle(UAV) image,use image segmentation method,achnatherum splendens can be extracted effectively.Results of estimation can obtain a higher accuracy of 97.3 % compared with measured achnatherum splendens coverage.
引文
[1]顾祝军,曾志远.遥感植被盖度研究[J].水土保持研究,2005,12(2):18-21.
    [2]李德仁,李明.无人机遥感系统的研究进展与应用前景[J].武汉大学学报:信息科学版,2014,39(5):505-513.
    [3]张艳玲,何鑫驰,李立.基于最大类间方差与形态学的淋巴结图像分割[J].计算机科学,2013,40(8):296-299.
    [4]Chen J,Yi S,Qin Y,et al.Improving estimates of fractional vegetation cover based on UAV in alpine grassland on the QinghaiTibetan Plateau[J].International Journal of Remote Sensing,2016,37(8):1922-1936.
    [5]谢鹏鹤.图像阈值分割算法研究[D].长沙:湘潭大学,2012.
    [6]Otsu N.A threshold selection method from gray-Level histogram[J].IEEE Transactions on Systems Man&Cybernetics,2001,9(1):62-66.
    [7]Huang D Y.Optimal multi-level thresholding using a two-stage ostu optimization approach[J].Pattern Recognition Letters,2009,30:275-284.
    [8]王香菊.基于中值滤波和小波变换的图像去噪方法研究[D].西安:西安科技大学,2008.
    [9]夏剑峰.基于数学形态学的癌细胞的分割与识别[J].电子科技,2016,29(10):36-38.
    [10]Simoncelli E P.Image denoising using a local Gaussian scale mixture model in the wavelet domain[J].Proceedings of SPIE—The International Society for Optical Engineering,2009,4119(11):1338-1351.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅:66554900、66554949;咨询服务:66554800;科技查新:66554700