• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Annual International Meeting of the American Society of Agricultural and Biological Engineers >Assessing color representation methods for segmentation of vegetation in color photographs
【24h】

Assessing color representation methods for segmentation of vegetation in color photographs

机译：评估颜色照片分割的颜色表示方法

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Papers dealing with vegetation segmentation from RGB images confounded the effect of color representation with a clustering algorithm. In this paper, various color representation of RGB images are compared. On a set of images, vegetation and soil pixels were manually isolated to form two known populations for each image. For each pixel in the populations, Mahalanobis distances were computed and each pixel was assigned to the population (soil or vegetation) corresponding to the smallest Mahalanobis distance. The comparison between color representation methods was based on classification errors. Two image sets were used. One was under controlled flash illumination and the other one was under uncontrolled outdoor lighting. Images acquired under controlled illumination were transformed to simulate illuminants corresponding to other correlated color temperature covering most situations that can be encountered under natural lighting in the field. Under controlled illumination, the choice of the color representation method was not critical. Under uncontrolled outdoor lighting, color representations that remove completely intensity information performed better.
机译：从RGB图像处理植被分割的论文将颜色表示与聚类算法的效果混为一谈。在本文中，比较了RGB图像的各种颜色表示。在一组图像上，手动分离植被和土壤像素以形成每个图像的已知群体。对于群体中的每个像素，计算Mahalanobis距离，并且每个像素被分配给对应于最小的Mahalanobis距离的群体（土壤或植被）。颜色表示方法之间的比较是基于分类错误。使用了两个图像集。一个受到控制的闪光照明，另一个是在不受控制的户外照明下。转化在受控照射下获得的图像以模拟与其他相关色温对应的照明剂，覆盖在场上的自然照明下可以遇到的大多数情况。在受控照明下，颜色表示方法的选择并不重要。在不受控制的户外照明下，删除完全强度信息的颜色表示更好。

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