Study of method for fast segmentation based on UAV image

doi:10.6046/gtzyyg.2016.02.12

Abstract
References
Related Articles
Metrics

Download: PDF(2042 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

In order to solve the problem that it is difficult to obtain spatial data in time in the earthquake stricken area, the authors propose in this paper a more efficient new segmentation algorithm on the basis of the own features of unmanned aerial vehicle(UAV) remote sensing images. Firstly, the image is divided into several homogeneous color areas and texture areas through variance detection on the color space. Secondly, preliminary partition of the homogeneous color area is directly achieved by Mean Shift method. Meanwhile, for the texture area, a high dimensional feature space is set up based on the color, texture, and shape information, and the proper bandwidth is calculated according to the normalized distribution density before applying Mean Shift algorithm on the feature space to model classification so as to reach the partition. Finally, an object function is set up to realize area merging and then reach the final partition results by smoothing over partitioned areas. Tests were conducted for high spatial resolution remote sensing image segmentation on UAV images of Lushan earthquake stricken area. A segmentation matching index which considers area and spectrum is proposed to evaluate the segmentation result. The experimental results show that the improved method performs better than the traditional method, and can provide data protection for subsequent damage information extraction.

Keywords rural residential land RapidEye image RS classification RS interpretation Taihe County

:	TP751.1
	P231

Issue Date: 14 April 2016

	Service

	E-mail this article
	E-mail Alert
	RSS
	Articles by authors

	GAO Mengxu
	WANG Juanle
	BAI Zhongqiang
	ZHU Junxiang

Cite this article:

GAO Mengxu,WANG Juanle,BAI Zhongqiang, et al. Study of method for fast segmentation based on UAV image[J]. REMOTE SENSING FOR LAND & RESOURCES, 2016, 28(2): 72-78.

URL:

https://www.gtzyyg.com/EN/10.6046/gtzyyg.2016.02.12 OR https://www.gtzyyg.com/EN/Y2016/V28/I2/72

[1] 鲁恒,李永树,李何超,等.无人机影像数字处理及在地震灾区重建中的应用[J].西南交通大学学报,2010,45(4):533-538. Lu H,Li Y S,Li H C,et al.Digital processing of unmanned aerial vehicle image and its application in reconstruction of Wenchuan earthquake-hit areas[J].Journal of Southwest Jiaotong University,2010,45(4):533-538.

[2] 谭衢霖,刘正军,沈伟.一种面向对象的遥感影像多尺度分割方法[J].北京交通大学学报,2007,31(4):111-114,119. Tan Q L,Liu Z J,Shen W.An algorithm for object-oriented multi- scale remote sensing image segmentation[J].Journal of Beijing Jiaotong University,2007,31(4):111-114,119.

[3] 蔡红玥,姚国清.基于分水岭算法的高分遥感图像道路提取优化方法[J].国土资源遥感,2013,25(3):25-29.doi:10.6046/gtzyyg.2013.03.05. Cai H Y,Yao G Q.Optimized method for road extraction from high resolution remote sensing image based on watershed algorithm[J].Remote Sensing for Land and Resources,2013,25(3):25-29.doi:10.6046/gtzyyg.2013.03.05.

[4] 林辉,莫登奎,熊育久,等.高分辨率遥感图像均值调整法分割技术研究[J].地理研究,2006,26(4):85-88,95. Lin H,Mo D K,Xiong Y J,et al.The method of segmenting high-resolution remote sensing images based on Mean-shift[J].Journal of Central South Forestry University,2006,26(4):85-88,95.

[5] 贾春阳,李卫华,李小春.基于自适应权值FNEA算法的高分辨率遥感图像分割[J].国土资源遥感,2013,25(4):22-25.doi:10.6046/gtzyyg.2013.04.04. Jia C Y,Li W H,Li X C.High-resolution remote sensing image segmentation based on weight adaptive fractal net evolution approach[J].Remote Sensing for Land and Resources,2013,25(4):22-25,doi:10.6046/gtzyyg.2013.04.04.

[6] Fukunaga K,Hostetler L.The estimation of the gradient of a density function,with applications in pattern recognition[J].IEEE Transactions on Information Theory,1975,21(1):32-40.

[7] Cheng Y Z.Mean Shift, mode seeking,and clustering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(8):790-799.

[8] Comaniciu D,Meer P.Mean Shift:A robust approach toward feature space analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619.

[9] Comaniciu D,Meer P.Distribution free decomposition of multivariate data[J].Pattern Analysis and Applications,1999,2(1):22-30.

[10] 肖鹏峰,冯学智,赵书河,等.基于相位一致的高分辨率遥感图像分割方法[J].测绘学报,2007,36(2):146-151,186. Xiao P F,Feng X Z,Zhao S H,et al.Segmentation of high-resolution remotely sensed imagery based on phase Congruency[J].Acta Geodaetica et Cartographica Sinica,2007,36(2):146-151,186.

[11] 李峰,彭嘉雄.基于Wold特征的遥感图像的分割[J].测绘学报,2003,32(4):330-333. Li F,Peng J X.Wold-based remote sensing image segmentation[J].Acta Geodaetica et Cartographica Sinica,2003,32(4):330-333.

[12] Tremeau A,Colantoni P.Regions adjacency graph applied to color image segmentation[J].IEEE Transactions on Image Processing,2000,9(4):735-744.

[13] 于欢,张树清,孔博,等.面向对象遥感影像分类的最优分割尺度选择研究[J].中国图象图形学报,2010,15(2):352-360. Yu H,Zhang S Q Kong B,et al.Optimal segmentation scale selection for object-oriented remote sensing image classification[J].Journal of Image and Graphics,2010,15(2):352-360.

[14] Neubert M,Herold H.Assessment of remote sensing image segment ation quality[C]//International Society for Photogrammetry and Remote Sensing Commission IV,Working Group IV/3.2008.

[15] 鲁恒,李永树,唐敏.面向对象的山地区域多源遥感影像分割尺度选择及评价[J].山地学报,2011,29(6):688-694. Lu H,Li Y S,Tang M.Evaluation and selection of segmentation scale with object-oriented method in multiple source remote sensing image of mountain areas[J].Journal of Mountain Science,2011,29(6):688-694.

[1]	ZOU Yafeng, LYU Changhe, BAI Zhenhao, WANG Haiying. Calculation of land consolidation potential of rural residential land on different models of land consolidation[J]. REMOTE SENSING FOR LAND & RESOURCES, 2016, 28(4): 191-196.
[2]	GAO Mengxu, WANG Juanle, BAI Zhongqiang, ZHU Junxiang. Remote sensing monitoring of rural residential land based on RapidEye satellite images: A case study of Taihe County, Jiangxi Province[J]. REMOTE SENSING FOR LAND & RESOURCES, 2016, 28(1): 130-135.
[3]	LIU Fang, ZHANG Zeng-Xiang, WANG Xiao, WEI Xian-Hu. THE DYNAMIC MONITORING OF RURAL RESIDENTIAL LAND IN BEIJING AND DRIVING FORCE ANALYSIS BASED ON MULTI-SOURCE REMOTE SENSING DATA[J]. REMOTE SENSING FOR LAND & RESOURCES, 2009, 21(3): 88-93.

Viewed

Full text

Abstract

Cited

Shared

Discussed