Improved balloon snake method for water boundary extraction in remote sensing images

Nengcheng CHEN; Dandan LIU; Wenying DU

doi:10.11834/jrs.20176126

Views : 0 下载量: 124 CSCD: 2 更多指标

PDF
Export
Share
Collection
Album

Improved balloon snake method for water boundary extraction in remote sensing images
Vol. 21, Issue 3, Pages: 425-433(2017)
Published： 2017-5 ，

Accepted： 16 January 2017
DOI： 10.11834/jrs.20176126

扫描看全文

Nengcheng CHEN, Dandan LIU, Wenying DU. Improved balloon snake method for water boundary extraction in remote sensing images. [J]. Journal of Remote Sensing 21(3):425-433(2017)
DOI：

Nengcheng CHEN, Dandan LIU, Wenying DU. Improved balloon snake method for water boundary extraction in remote sensing images. [J]. Journal of Remote Sensing 21(3):425-433(2017) DOI： 10.11834/jrs.20176126.

摘要

相比于正交T-Snake算法，传统Balloon Snake算法不受格网约束，能够更加精确提取高分辨率遥感影像上水体，然而尚不能解决河中岛引起的拓扑冲突问题。由此，本文提出了一种改进Balloon Snake算法(T-Balloon Snake)，设计了目标内部由于空洞引起的拓扑冲突检测与处理机制。算法首先在目标水体内部手动设置一个初始轮廓，在曲线每次膨胀前对曲线进行自相交检测，若存在拓扑冲突则对曲线进行分裂与合并处理，最终直至迭代停止。实验选取了三类湖泊与河流高分影像，实现了复杂遥感影像水体矢量边界的一次性精确提取。实验结果表明，该方法可直接有效提取水体中深凹以及岛状边界，在提取结果正确性和完整性上都优于传统Balloon Snake算法。

Abstract

The traditional balloon snake model is free from the constraints of orthogonal grids compared with the topology-adaptive snake model and thus extracts water boundaries from high-resolution remote sensing images with more accuracy. However

this method cannot detect and handle topological conflict caused by islands in water. To solve this problem

an improved topology-adaptive balloon snake model

which is based on the traditional balloon snake model

is proposed. First

an original contour inside the target water body is manually set. Then

self-intersection detection is conducted each time prior to contour expansion. If holes cause topological conflict

curve deformation will be performed until the iteration stops. The data selected for this experiment were obtained from the GF-1 observing satellite images of three kinds of lakes and rivers

thus realizing the one-off accurate extraction of complex water from remote sensing images. Based on the results of our experiment

the proposed method can efficiently

correctly

and completely extract the boundaries of deeply concave regions and islands.

关键词

遥感影像河中岛边界提取改进Balloon Snake拓扑冲突

Keywords

remote sensing imageriver islandboundary extractionimproved Balloon Snaketopological conflict

references

Abbas Q, Celebi M E and García IF. 2013.Breast mass segmentation using region-based and edge-based methods in a 4-stage multiscale system. Biomedical Signal Processing and Control, 8(2): 204–214

Bischoff S and Kobbelt L P. 2004. Parameterization-free active contour models with topology control. The Visual Computer, 20(4): 217–228

Cohen L D. 1991.On active contour models and balloons. CVGIP: Image Understanding, 53(2): 211–218

Filho P P R, Cortez P C, Barros A C D S and Albuquerque V H C D. 2014.Novel adaptive balloon active contour method based on internal force for image segmentation-A systematic evaluation on synthetic and real images. Expert Systems with Applications, 41(17): 7707–7721

Kass M, Witkin A and Terzopoulos D. 1988.Snakes: active contour models. International Journal of Computer Vision, 1(4): 321–331

Li Z B, Xu X Z, Le Y and Xu F Q. 2014.An improved balloon snake for HIFU image-guided system. Journal of Medical Ultrasonics, 41(3): 291–300

吕红宇, 马竞峰, 包尚联. 2006. 一种使用膨胀气球模型的Snakes多目标分割方法. 中国医学影像技术, 22(3): 458–460

Lv H Y, Ma J F and Bao S L. 2006.A multi-object segmentation algorithm for snakes using inflating balloon model. Chinese Journal of Medical Imaging Technology, 22(3): 458–460

McInerney T and Terzopoulos D. 2000.T-snakes: topology adaptive snakes. Medical Image Analysis, 4(2): 73–91

孟令奎, 吕琪菲. 2015. 复杂水体边界提取的改进正交T-Snake模型. 测绘学报, 44(6): 670–677

Meng L K and Lv Q F. 2015.Improved orthogonal T-Snake model for complex water boundary extraction. Acta Geodaetica et CartographicaSinica, 44(6): 670–677

孟伟灿, 朱述龙, 朱宝山, 曹闻, 司毅博. 2011. 区域生长与GVF Snake模型相结合的水域边界提取. 测绘科学技术学报, 28(4): 262–265

Meng W C, Zhu S L, Zhu B S, Cao W and Si Y B. 2011. Water area boundary extraction based on GVF Snake model and region growth. Journal of Geomatics Science and Technology, 28(4): 262–265

孟伟灿. 2012. 遥感影像水域边界智能化提取方法研究. 郑州: 解放军信息工程大学: 10–11

Meng W C. 2012. Intelligent Water Boundary Extraction from Remote Sensing Image. Zhengzhou: PLA Information Engineering University: 10–11

吴欢, 易永红, 王啸, 陈秀万. 2006. 基于活动轮廓模型的高分辨率影像河道边界提取算法研究. 遥感技术与应用, 21(5): 407–413

Wu H, Yi Y H, Wang X and Chen X W. 2006. A river bank extracting algorithm based on active contour model from high-resolution satellite images. Remote Sensing Technology and Application, 21(5): 407–413

Xu C Y and Prince J L. 1998.Snakes, shapes, and gradient vector flow. IEEE Transactions on Image Processing, 7(3): 359–369

杨树文, 薛重生, 刘涛, 李轶鲲. 2010. 一种利用TM影像自动提取细小水体的方法. 测绘学报, 39(6): 611–617

Yang S W, Xue C S, Liu T and Li Y K. 2010.A method of small water information automatic extraction from TM remote sensing images.ActaGeodaetica et CartographicaSinica, 39(6): 611–617

张荣国, 刘焜, 蔡江辉, 刘小君. 2012. 变形曲线曲面主动轮廓模型方法. 北京: 国防工业出版社

Zhang R G, Liu K, Cai J H and Liu X J. 2012. Active contour model for deformable curves and surfaces. Beijing: National Defence Industry Press

Zheng S. 2010. An intensive restraint topology adaptive snake model and its application in tracking dynamic image sequence. Information Sciences, 180(16): 2940–2959

周亚男, 朱志文, 沈占锋, 程熙. 2012. 融合纹理特征和空间关系的TM影像海岸线自动提取. 北京大学学报(自然科学版), 48(2): 273–279

Zhou Y N, Zhu Z W, Shen Z F and Cheng X. 2012.Automatic extraction of coastline from TM image integrating texture and spatial elationship. Acta Scientiarum Naturalium Universitatis Pekinensis, 48(2): 273–279

朱述龙, 孟伟灿, 朱宝山. 2013. 运用GVF Snake算法提取水域的不规则边界. 遥感学报, 17(4): 742–758

Zhu S L, Meng W C and Zhu B S. 2013.Irregular water boundary extraction using GVF Snake. Journal of Remote Sensing, 17(4): 742–758

Alert me when the article has been cited

提交

Road extraction method of high-resolution remote sensing image on the basis of the spatial information perception semantic segmentation model

Review of deep learning in optical and SAR image fusion

Extracting glacier information from remote sensing imageries by automatic threshold method of Gaussian mixture model

Scene classification of remote sensing image using ensemble convolutional neural network

Research progress on methods of automatic coastline extraction based on remote sensing images