基于改进均值漂移算法的绿色作物图像分割方法

针对绿色农作物图像背景复杂且分割难的问题,提出一种基于改进均值漂移算法的分割方法。采用均值漂移算法对图像进行平滑和分割时,带宽的选择直接影响平滑和分割的结果。传统的均值漂移分割方法需要人为地设定空域带宽和值域带宽这2个参数。该文首先根据绿色作物图像的颜色特点,提取图像的颜色指数;然后采用均值漂移算法,将图像的颜色信息与空间信息结合起来,根据作物图像颜色分布的丰富程度定义自适应空域带宽,采用渐近积分均方差来获得自适应值域带宽,对图像进行平滑滤波;最后采用Otsu方法将平滑后的图像分成两部分：绿色部分和背景部分。试验结果表明,该方法能够有效地分割出绿色作物,并在分割性能上明显优于常规的颜色指数方法...

Full description

Saved in:
Bibliographic Details
Published in农业工程学报 Vol. 30; no. 24; pp. 161 - 167
Main Author 伍艳莲 赵力 姜海燕 郭小清 黄芬
Format Journal Article
LanguageChinese
Published 南京农业大学国家信息农业工程技术中心，南京 210095%南京农业大学信息科学与技术学院,南京,210095 2014
南京农业大学信息科学与技术学院，南京 210095
Subjects
作物
图像分割
均值漂移
带宽
算法
颜色指数
算法
algorithms
color index
mean shift
image segmentation
bandwidth
作物
图像分割
均值漂移
颜色指数
crops
带宽
Online AccessGet full text
ISSN1002-6819
DOI10.3969/j.issn.1002-6819.2014.24.019

Cover

More Information
Summary:针对绿色农作物图像背景复杂且分割难的问题,提出一种基于改进均值漂移算法的分割方法。采用均值漂移算法对图像进行平滑和分割时,带宽的选择直接影响平滑和分割的结果。传统的均值漂移分割方法需要人为地设定空域带宽和值域带宽这2个参数。该文首先根据绿色作物图像的颜色特点,提取图像的颜色指数;然后采用均值漂移算法,将图像的颜色信息与空间信息结合起来,根据作物图像颜色分布的丰富程度定义自适应空域带宽,采用渐近积分均方差来获得自适应值域带宽,对图像进行平滑滤波;最后采用Otsu方法将平滑后的图像分成两部分：绿色部分和背景部分。试验结果表明,该方法能够有效地分割出绿色作物,并在分割性能上明显优于常规的颜色指数方法,作物图像的错分率均小于6.5%。
Bibliography:Digital image processing technology has received considerable attention in many aspects of agriculture, some typical examples including estimation physiological status of crops, disease and insect pest identification, vegetation-cover estimation, and quality detection for agricultural products. One of the most important and essential tasks is the crop image segmentation which separates the green crop material or region of interest from the background. In recent years, green crop image segmentation has been an important research topic and several methods have been proposed. However, green crop image segmentation is still a difficult problem since the green crop images usually involve complicated backgrounds. To deal with this problem, we propose in this paper a novel segmentation method based on Mean shift and color index. Mean shift is an iterative procedure that shifts each data point to the average of data points in its neighborhood. The performance of Mean shift depends heavily on the size of bandwidth whi
ISSN:1002-6819
DOI:10.3969/j.issn.1002-6819.2014.24.019