首页> 外文会议>International conference on image processing, computer vision, pattern recognition >Object Description and Finding of Geometric Structures on the Base of Extracted Straight Edge Segments in Digital Images
【24h】

Object Description and Finding of Geometric Structures on the Base of Extracted Straight Edge Segments in Digital Images

机译:基于数字图像中提取的直边段的对象描述和几何结构查找

获取原文

摘要

We present a novel method of grouping straight line segments to describe objects in digital images after straight edges extraction by oriented filtering edge-based algorithm. This method uses crossings in the ordered segments as the main property and it also takes into consideration some specific properties of grouped lines such as anti-parallelism, proximity and adjacency. Structures obtained by this method present an intermediate-level description of interesting objects which have polygonal view (buildings, parts of roads, bridges and some natural places of landscape). At the first step simple structures are obtained by lines grouping taking into consideration all crossing lines or only part of them. At the second step simple structures are joined allowing for restrictions. Application with real aerial and satellite images shows a good ability to separate and extract specific objects like buildings and other line-segment-rich structures.
机译:我们提出了一种新的方法,将直线段分组以通过基于定向滤波边缘的算法在直线边缘提取后描述数字图像中的对象。此方法使用有序段中的交叉作为主要属性,并且还考虑了分组线的某些特定属性,例如反平行性,邻近性和邻接性。通过这种方法获得的结构呈现了对具有多边形视图的有趣对象(建筑物,道路的一部分,桥梁和某些自然景观)的中级描述。第一步,通过考虑所有交叉线或仅部分交叉线的线分组来获得简单结构。在第二步中,将简单的结构连接起来以考虑限制。结合实际的航空和卫星图像,可以显示出很好的分离和提取特定对象(如建筑物和其他富含线段的结构)的能力。

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