• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Proceeding of 2009 international workshop on GIS for transportation >ROAD SELF-DIAGNOSIS MODEL BASED ON ROSS-SECTIONAL LINES
【24h】

ROAD SELF-DIAGNOSIS MODEL BASED ON ROSS-SECTIONAL LINES

机译：基于横断面线的道路自诊断模型

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In aerial images, due to the complex condition of the roads, road extraction may not be expected to obtain perfect results, most of the information incorrectly detected needs to be eliminated for subsequent processing. Typically the variance of the estimation of road width is small as the width of road changes slowly in original image. In this paper, with the variance evaluation model based on the initial extraction results, a self-diagnosis model is established to verify the legitimacy of the road in the original image. From the gray value of the original images, we use the cross-sectional line as a statistical unit to calculate the width variance of the road detection,and then verify whether the extracted results are under the constraint. In this method, most of the objects extracted incorrectly can be detected and rejected, and the accuracy and robustness of the extraction are improved significantly.
机译：在航空图像中，由于道路条件复杂，可能无法期望道路提取获得理想的结果，因此需要消除大多数错误检测的信息，以进行后续处理。通常，道路宽度估计的方差很小，因为道路宽度在原始图像中变化缓慢。本文利用基于初始提取结果的方差评估模型，建立了一个自诊断模型，以验证原始图像中道路的合法性。从原始图像的灰度值出发，以横断面线为统计单位，计算出道路检测的宽度方差，然后验证提取的结果是否受约束。这种方法可以检测和剔除大部分错误提取的对象，并大大提高了提取的准确性和鲁棒性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号