结合地形因子与分层策略的喀斯特地区无人机影像分类

doi:10.13474/j.cnki.11-2246.2022.0055

摘要/Abstract

摘要： 西南喀斯特山区地形起伏较大，地物分布较为破碎，致使传统的光谱特征一次分类方法的精度较低。本文基于高分辨率无人机正射影像和地形指标，充分利用无人机遥感影像空间特征、光谱特征、纹理特征及地形特征，采取面向对象CART决策树算法与分层策略提取了研究区土地覆盖类型。研究表明，结合空间地形因子和分层策略的方法减少了破碎区地物间的相干扰，故具有较高的分类精度，总体分类精度达91.2%，Kappa系数为0.87，较传统一次分类精度提高了9.8%，Kappa系数提高了0.13。该方法对西南喀斯特地区土地覆盖解译精度较好，可为土地利用监测提供参考。

关键词: 地形因子, 分层策略, 无人机影像, 多尺度分割, 决策树分类

Abstract: The karst topography in southwestern China is filled with fantastic caves and curved areas. And the classification of groundobject is relatively fragmented, which leads to the reductionin in the accuracy of the traditional one-time classification of spectral features.Based on the high-definition of UAV orthophoto and terrain factor, this paper makes full use of the spatial, spectral, texture and terrain features of UAV remote sensing images and adopts the object-oriented CART decision tree algorithm and hierarchical strategy to pickup the coverage type of the land inspecific study area. The method of combining spatial terrain factors and hierarchical strategies reduces the interference among the fragment edground objects in the karst area actually has a much higher classification accuracy. The whole classification accuracy reach 91.2%and the Kappa coefficient is 0.87, which is respectively 9.8% and 0.13 higher than the traditional one-time classification accuracy and Kappa coefficient. It shows that this method is suitable for decoding land coverage in southwest karst area, which could provide favorable reference for land-use monitoring.

Key words: terrain factor, stratification strategy, UAV image, multi-scale segmentation, decision tree classification

中图分类号:

P237

贾煜, 汪泓, 蔡宏, 张磊. 结合地形因子与分层策略的喀斯特地区无人机影像分类[J]. 测绘通报, 2022, 0(2): 121-127.

JIA Yu, WANG Hong, CAI Hong, ZHANG Lei. Unmanned image classification in karst area combining topographic factors and stratification strategy[J]. Bulletin of Surveying and Mapping, 2022, 0(2): 121-127.

参考文献

[1] 唐华俊,吴文斌,杨鹏,等.土地利用/土地覆被变化(LUCC)模型研究进展[J].地理学报, 2009,64(4):456-468.
[2] 肖艳,姜琦刚,王斌,等.基于ReliefF和PSO混合特征选择的面向对象土地利用分类[J].农业工程学报, 2016, 32(4):211-216.
[3] 李宏力,吕立楠,王文钧,等.基于资源三号卫星影像的面向对象分类方法的关键技术研究[J].测绘与空间地理信息, 2020,43(9):155-158.
[4] 邬亚娟,刘廷玺,童新,等.基于面向对象的干旱半干旱地区植被分类[J].干旱区研究, 2020,3(4):1026-1034.
[5] 刘舒,朱航.基于超高空间分辩率无人机影像的面向对象土地利用分类方法[J].农业工程学报, 2020, 36(2):87-94.
[6] LUDENO G,CATAPANO I,RENGA A, et al. Assessment of a micro-uav system for microwave tomography Radar imaging[J]. Remote Sensing of Environment, 2018, 212:90-102.
[7] 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, 540.
[8] 任泽茜,丁丽霞,刘丽娟,等.利用无人机遥感监测农作物种植面积[J].测绘通报, 2020(7):76-81.
[9] 袁慧洁.基于无人机遥感和面向对象法的简单地物分类研究[J].测绘与空间地理信息, 2020,43(3):113-117, 123.
[10] 乌云德吉,陈瑞卿,敦惠霞.基于eCongnition软件的土地利用分类研究[J].北方农业学报, 2020,48(4):126-134.
[11] 牟昱璇,邬明权,牛铮,等.南方地区复杂条件下的耕地面积遥感提取方法[J].遥感技术与应用,2020, 35(5):1227-1135.
[12] MOUNTRAKIS G, IM J,OGOLE C. Support vector mach-ines in remote sensing:a review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2011, 66(3):247-259.
[13] 娄佩卿,陈晓雨,王疏桐,等.基于无人机影像的喀斯特农耕区地物识别:以桂林市为例[J].国土资源遥感, 2020, 32(1):216-223.
[14] YAO H,QIN R,CHEN X. Unmanned aerial vehicle for remote sensing applicationsa review[J]. Remote Sensing, 2019, 11(12):1421-1443.
[15] SHAO Y, RUNETTA R S. Comparison of support vector machine, neural network, and cart algorithms for the land-cover classification using limited training data points[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2012, 70:78-87.
[16] 廖顺宝,汪珂丽,蒋笑.土地覆被类型空间格局与地形因子的定量关联及其应用[J].地域研究与开发, 2017, 36(5):80-86.
[17] 哈凯,丁庆龙,门明新,等.山地丘陵区土地利用分布及其与地形因子关系:以河北省怀来县为例[J].地理研究, 2015, 34(5):909-921.
[18] 钟德燕,常庆瑞,宋丰骥.黄土丘陵沟壑区土地利用空间分布与地形因子关系研究[J].干旱区资源与环境, 2012, 26(6):102-107.
[19] 贾宁凤,段建南,乔志敏.土地利用空间分布与地形因子相关性分析方法[J].经济地理, 2007, 120(2):310-312.
[20] 黄海洋,杨庆媛,王成.基于DEM的土地利用类型与地形因子关系研究:以重庆市酉阳县麻旺镇为例[J].西南大学学报(自然科学版), 2009, 31(4):159-164.
[21] 张志慧,刘雯,李笑含,等.基于无人机航摄影像的喀斯特地区裸岩信息提取及景观格局分析[J].地球信息科学学报, 2020, 22(12):2436-2444.
[22] 彭旭东,戴全厚,李昌兰.中国西南喀斯特坡地水土流失/漏失过程与机理研究进展[J].水土保持学报, 2017, 31(5):1-8.
[23] 冯朝阳,于勇,高吉喜,等.地形因子对京西门头沟区土地利用/覆盖变化的影响[J].山地学报, 2007(3):274-279.
[24] JOHNSON B,XIE Z. Unsupervised image segmentation evaluation and refinement using a multi-scale approach[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2011, 66(4):473-483.
[25] ESPINDOLA G M, CAMARA G, REIS I A, et al. Para-meter selection for region-growing image segmentation algorithms using spatial autocorrelation[J]. International Journal of Remote Sensing, 2006, 27(14):3035-3040.
[26] 刘兆祎,李鑫慧,沈润平,等.高分辨率遥感图像分割的最优尺度选择[J].计算机工程与应用, 2014, 50(6):144-147.
[27] 肖武,任河,吕雪娇,等.基于无人机遥感的高潜水位采煤沉陷湿地植被分类[J].农业机械学报, 2019, 50(2):177-186.
[28] HAN N, DU H Q, ZHOU G M. Object-based classification using SPOT-5 imagery for moso bamboo forest mapping[J]. International Journal of Remote Sensing, 2014, 35(3):1126-1142.