基于分形特征的高标准农田遥感分类方法研究
|
摘要
目前全国高标准农田面积数量已具一定规模,由于人工解译的工作效率较低,如何实现对全国大面积的高标准农田建后利用情况进行实时、精准遥感监测成为亟待解决的问题。由于监测面积大,精度要求高,迫切需要研究一套遥感自动监测方法在全国推广。以广东省东莞地区作为研究区,选择2017年2月15日的高分二号遥感影像,基于分形图像分割并结合BP神经网络对区域高标准农田进行分类,并加以人工解译和实地验证。结果显示,该分类方法总体精度为80.112 2%,Kappa系数为0.761 1。表明分形图像分割结合BP神经网络的遥感分类方法总体精度较高,能较好地满足高标准农田建后利用情况遥感监测的需求。此方法可以在全国范围推广应用,为高标准农田建成后的实时监管提供技术支撑。
The high-standard farmland area in China has currently reached a considerable scale. The low efficiency of manual interpretation has called for more precise and real-time remote sensing monitoring for the construction of large scale farmland in the country. Because of the large monitoring area and high precision demand,a set of automatic remote sensing monitoring classification method is needed to develop. The study area is located in Dongguan area of Guangdong Province,South China. Using GF-2 remote sensing images( 15 thFebruary,2017),the fractal-based image segmentation combined with the BP neural network remote sensing classification method is studied,which is supported by the artificial interpretation and field verification. The experimental results show that the overall precision of the classification method is 80. 112,2% and the Kappa coefficient is 0. 761,1,which indicates that the overall precision of fractal image segmentation and BP neural network remote sensing classification method is higher. This can better meet the needs of remote sensing monitoring after the construction of the high standard farmland. A nationwide adoption of this method can provide technical support for the real-time monitoring of the high standard farmland.
The high-standard farmland area in China has currently reached a considerable scale. The low efficiency of manual interpretation has called for more precise and real-time remote sensing monitoring for the construction of large scale farmland in the country. Because of the large monitoring area and high precision demand,a set of automatic remote sensing monitoring classification method is needed to develop. The study area is located in Dongguan area of Guangdong Province,South China. Using GF-2 remote sensing images( 15 thFebruary,2017),the fractal-based image segmentation combined with the BP neural network remote sensing classification method is studied,which is supported by the artificial interpretation and field verification. The experimental results show that the overall precision of the classification method is 80. 112,2% and the Kappa coefficient is 0. 761,1,which indicates that the overall precision of fractal image segmentation and BP neural network remote sensing classification method is higher. This can better meet the needs of remote sensing monitoring after the construction of the high standard farmland. A nationwide adoption of this method can provide technical support for the real-time monitoring of the high standard farmland.
引文
[1]孙丹峰,杨冀红,刘顺喜.高分辨率遥感卫星影像在土地利用分类及其变化监测的应用研究[J].农业工程学报,2002,18(2):160-164.
[2]郭文娟,张佳华.利用ASTER遥感资料提取南京城郊土地利用信息的研究[J].农业工程学报,2005,21(9):62-66.
[3]张超,李智晓,李鹏山,等.基于高分辨率遥感影像分类的城镇土地利用规划监测[J].农业机械学报,2015,46(11):323-328.
[4]陈凯,罗兆楠,王小松,等.特高压工程施工利用高分二号遥感影像进行水土保持远程监测研究[J].地理信息世界,2016,23(3):108-113.
[5]吴洪涛,刘晶东.几种基于高分辨率遥感影像分类技术的分析与探讨[J].测绘与空间地理信息,2008,31(2):47-51.
[6]石丽.基于BP神经网络改进算法的遥感图像分类试验[J].科技信息,2014(13):74-75.
[7]陈启浩,刘志敏,刘修国,等.面向基元的高空间分辨率矿区遥感影像土地利用分类[J].地球科学,2010,35(3):453-458.
[8]王华.基于分形理论的路面裂缝检测技术的研究[D].哈尔滨:哈尔滨工业大学,2004.
[9]陈永强,陆安生,胡汉平.基于分形的图像分析方法综述[J].计算机工程与设计,2005(7):1781-1783.
[10]KELLER J M,CHEN S,CROWNOVER R M.Texture description and segmentation through fractal geometry[J].Graphical Models and Image Processing,1989,45:150-166.
[11]闻新,张兴旺,朱亚萍,等.智能故障诊断技术:MATLAB应用[M].北京:北京航空航天大学出版社,2015:9.
[12]张坤华,王敬儒,张启衡.基于分形特征的图像边缘检测方法[J].光电工程,2001(6):52-55.
[13]肖锦成,欧维新,符海月.基于BP神经网络与ETM+遥感数据的盐城滨海自然湿地覆被分类[J].生态学报,2013,33(23):7496-7504.
[14]陈启浩,刘志敏,刘修国.面向基元的高空间分辨率矿区遥感影像土地利用分类[J].地球科学,2010,35(3):453-458.
[15]纪仰慧,李国春,关宏强.土地利用覆盖遥感分类研究综述[J].农业网络信息,2005(8):36-38.
[16]费鲜芸,高祥伟.土地利用/土地覆盖遥感分类研究综述[J].山东农业大学学报,2002,33(3):391-394.
[2]郭文娟,张佳华.利用ASTER遥感资料提取南京城郊土地利用信息的研究[J].农业工程学报,2005,21(9):62-66.
[3]张超,李智晓,李鹏山,等.基于高分辨率遥感影像分类的城镇土地利用规划监测[J].农业机械学报,2015,46(11):323-328.
[4]陈凯,罗兆楠,王小松,等.特高压工程施工利用高分二号遥感影像进行水土保持远程监测研究[J].地理信息世界,2016,23(3):108-113.
[5]吴洪涛,刘晶东.几种基于高分辨率遥感影像分类技术的分析与探讨[J].测绘与空间地理信息,2008,31(2):47-51.
[6]石丽.基于BP神经网络改进算法的遥感图像分类试验[J].科技信息,2014(13):74-75.
[7]陈启浩,刘志敏,刘修国,等.面向基元的高空间分辨率矿区遥感影像土地利用分类[J].地球科学,2010,35(3):453-458.
[8]王华.基于分形理论的路面裂缝检测技术的研究[D].哈尔滨:哈尔滨工业大学,2004.
[9]陈永强,陆安生,胡汉平.基于分形的图像分析方法综述[J].计算机工程与设计,2005(7):1781-1783.
[10]KELLER J M,CHEN S,CROWNOVER R M.Texture description and segmentation through fractal geometry[J].Graphical Models and Image Processing,1989,45:150-166.
[11]闻新,张兴旺,朱亚萍,等.智能故障诊断技术:MATLAB应用[M].北京:北京航空航天大学出版社,2015:9.
[12]张坤华,王敬儒,张启衡.基于分形特征的图像边缘检测方法[J].光电工程,2001(6):52-55.
[13]肖锦成,欧维新,符海月.基于BP神经网络与ETM+遥感数据的盐城滨海自然湿地覆被分类[J].生态学报,2013,33(23):7496-7504.
[14]陈启浩,刘志敏,刘修国.面向基元的高空间分辨率矿区遥感影像土地利用分类[J].地球科学,2010,35(3):453-458.
[15]纪仰慧,李国春,关宏强.土地利用覆盖遥感分类研究综述[J].农业网络信息,2005(8):36-38.
[16]费鲜芸,高祥伟.土地利用/土地覆盖遥感分类研究综述[J].山东农业大学学报,2002,33(3):391-394.