• 主题
高级搜索  >
历史搜索 清空历史
首页> 美国卫生研究院文献>Sensors (Basel Switzerland) >Automated Field-of-View Illumination and Recognition Algorithm Design of a Vision System for Pick-and-Place Considering Colour Information in Illumination and Images
【2h】

Automated Field-of-View Illumination and Recognition Algorithm Design of a Vision System for Pick-and-Place Considering Colour Information in Illumination and Images

机译：考虑照明和图像中颜色信息的取放视觉系统的自动视场照明和识别算法设计

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。
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Machine vision is playing an increasingly important role in industrial applications, and the automated design of image recognition systems has been a subject of intense research. This study has proposed a system for automatically designing the field-of-view (FOV) of a camera, the illumination strength and the parameters in a recognition algorithm. We formulated the design problem as an optimisation problem and used an experiment based on a hierarchical algorithm to solve it. The evaluation experiments using translucent plastics objects showed that the use of the proposed system resulted in an effective solution with a wide FOV, recognition of all objects and 0.32 mm and 0.4° maximal positional and angular errors when all the RGB (red, green and blue) for illumination and R channel image for recognition were used. Though all the RGB illumination and grey scale images also provided recognition of all the objects, only a narrow FOV was selected. Moreover, full recognition was not achieved by using only G illumination and a grey-scale image. The results showed that the proposed method can automatically design the FOV, illumination and parameters in the recognition algorithm and that tuning all the RGB illumination is desirable even when single-channel or grey-scale images are used for recognition.
机译：机器视觉在工业应用中扮演着越来越重要的角色，并且图像识别系统的自动化设计一直是研究的主题。这项研究提出了一种系统，用于自动设计摄像机的视野（FOV），照明强度和识别算法中的参数。我们将设计问题表述为优化问题，并使用基于分层算法的实验来解决该问题。使用半透明塑料物体进行的评估实验表明，所建议的系统的使用产生了一种有效的解决方案，具有宽视场，可识别所有物体以及在所有RGB（红色，绿色和蓝色）下均具有0.32 mm和0.4°的最大位置和角度误差）进行照明，并使用R通道图像进行识别。尽管所有RGB照明和灰度图像也都可以识别所有对象，但是只选择了一个狭窄的FOV。此外，仅使用G照明和灰度图像无法完全识别。结果表明，所提出的方法可以自动设计识别算法中的视场，照度和参数，即使使用单通道或灰度图像进行识别，也需要调整所有RGB照度。

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