首页> 外文OA文献 >A detection method of intersections for determining overlapping using active vision
【2h】

A detection method of intersections for determining overlapping using active vision

机译:一种利用主动视觉确定重叠的路口检测方法

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。

摘要

Sometimes, the presence of objects difficult the observation of other neighboring objects. This is becausepart of the surface of an object occludes partially the surface of another, increasing the complexitiy in therecognition process. Therefore, the information which is acquired from scene to describe the objects is oftenincomplete and depends a great deal on the view point of the observation. Thus, when any real scene isobserved, the regions and the boundaries which delimit and dissociate objects from others are not perceivedeasily. In this paper, a method to discern objects from others, delimiting where the surface of each objectbegins and finishes is presented. Really, here, we look for detecting the overlapping and occlusion zones oftwo or more objects which interact among each other in a same scene. This is very useful, on the one hand,to distinguish some objects from others when the features like texture colour and geometric form are notsufficient to separate them with a segmentation process. On the other hand, it is also important to identifyoccluded zones without a previous knowledge of the type of objects which are wished to recognize. Theproposed approach is based on the detection of occluded zones by means of structured light patternsprojected on the object surfaces in a scene. These light patterns determine certain discontinuities of thebeam projections when they hit against the surfaces becoming deformed themselves. So that, suchdiscontinuities are taken like zones of boundary of occlusion candidate regions.
机译:有时,物体的存在很难观察到其他相邻物体。这是因为物体表面的一部分会部分遮挡另一个物体的表面,从而增加了识别过程的复杂性。因此,从场景获得的用于描述对象的信息通常是不完整的,并且在很大程度上取决于观察的观点。因此,当观察到任何真实场景时,难以将物体与其他物体界定和分离的区域和边界。在本文中,提出了一种区分对象与其他对象的方法,该方法确定了每个对象的表面的起点和终点。实际上,在这里,我们寻找的是检测在同一场景中相互交互的两个或多个对象的重叠和遮挡区域。一方面,当诸如纹理颜色和几何形状之类的特征不足以通过分割过程将它们分开时,这对于区分某些对象与其他对象非常有用。另一方面,在没有事先知道希望识别的物体类型的情况下识别遮挡区域也很重要。所提出的方法基于借助于投射在场景中的物体表面上的结构化光图案对遮挡区域的检测。当它们撞击到自身变形的表面时,这些光图案确定了光束投影的某些不连续性。因此,这种不连续性就像遮挡候选区域的边界区域一样。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
代理获取

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