基于变分水平集方法的浒苔绿潮面积信息提取

发布时间：2018-03-07 08:46

本文选题：绿潮　切入点：信息提取　出处：《海洋学报》2017年09期 　论文类型：期刊论文

【摘要】：绿潮面积信息提取是绿潮遥感监测中极其重要的环节,其结果将直接影响后续的统计分析和预测预警工作。目前科研人员一般基于传统阈值方法对绿潮面积信息进行提取,其提取结果具有不稳定、效率低、人为因素影响大等缺点。针对上述问题,本文基于变分水平集的对偶方法和分裂Bregman投影方法对绿潮面积信息进行了提取,并提出一种对上述两种方法提取出的绿潮面积信息结果进行量化的新方法。分别基于传统阈值方法、变分水平集的对偶方法和分裂Bregman投影方法进行了3幅影像的绿潮信息提取实验,对提取结果进行了比对分析。实验结果表明,对分辨率较高的卫星遥感数据,无论从运行效率还是从绿潮面积信息提取结果的精确性及稳定性上,基于变分水平集的对偶方法和分裂Bregman投影方法均优于基于传统阈值方法。
[Abstract]:The extraction of green tide area information is an extremely important link in the remote sensing monitoring of green tide, and its results will directly affect the subsequent statistical analysis and prediction and early warning work. At present, researchers usually extract the green tide area information based on traditional threshold method. The extraction results are unstable, inefficient, and influenced by human factors. In this paper, based on the dual method of variational level set and split Bregman projection method, the area information of green tide is extracted. A new method for quantifying the results of the green tide area information extracted by the two methods is proposed, which is based on the traditional threshold method, respectively. Based on the dual method of variational level set and split Bregman projection method, the green tide information extraction experiments of three images are carried out, and the results are compared and analyzed. The experimental results show that, for satellite remote sensing data with high resolution, The dual method based on variational level set and the split Bregman projection method are superior to the traditional threshold method in terms of the accuracy and stability of the operation efficiency and the extraction results of the green tide area information.
【作者单位】：国家海洋局北海预报中心;山东省海洋生态环境与防灾减灾重点实验室;青岛大学计算机科学技术学院;
【基金】：国家自然科学基金项目(41306028)
【分类号】：TP751

【相似文献】