基于颜色矩的典型草原牧草特征提取与图像识别

针对内蒙古乌兰察布市荒漠化草原牧草监测与数字化程度较低的问题,该文实现了2种典型牧草的特征提取与图像识别,为多牧草种类识别与草业管理提供依据。利用智能导航车采集草原原始图像,对羊草和灰绿藜2种牧草图像提取RGB与HSV颜色矩特征并建立相应的规则库,数据表明二者的颜色矩特征具有明显区别。采用2G-B-R色差特征的模糊C-均值聚类算法对图像进行背景分割后,构建了一种3层BP神经网络模型,通过主成分分析法（principal component analysis,PCA）将15维输入特征参数降为10维以提高识别速度,且最终的整体识别率达到89.5%,实现了羊草与灰绿藜图像的有效分类识别,同时得到灰绿...

Full description

Saved in:
Bibliographic Details
Published in农业工程学报 Vol. 32; no. 23; pp. 168 - 175
Main Author 韩丁 武佩 张强 韩国栋 通霏
Format Journal Article
LanguageChinese
Published 内蒙古大学电子信息工程学院，呼和浩特 010021%内蒙古农业大学机电工程学院,呼和浩特,010018%加拿大曼尼托巴大学工程学院，温尼伯市 R3T 5V6%内蒙古农业大学生态环境学院,呼和浩特,010018 2016
内蒙古农业大学机电工程学院，呼和浩特 010018
Subjects
BP神经网络
主成分分析法
图像识别
牧草
特征提取
颜色矩
特征提取
BP neural network
主成分分析法
BP神经网络
feature extraction
牧草
color moment
图像识别
pasture
颜色矩
image recognition
principal component analysis
Online AccessGet full text
ISSN1002-6819
DOI10.11975/j.issn.1002-6819.2016.23.023

Cover

More Information
Summary:针对内蒙古乌兰察布市荒漠化草原牧草监测与数字化程度较低的问题,该文实现了2种典型牧草的特征提取与图像识别,为多牧草种类识别与草业管理提供依据。利用智能导航车采集草原原始图像,对羊草和灰绿藜2种牧草图像提取RGB与HSV颜色矩特征并建立相应的规则库,数据表明二者的颜色矩特征具有明显区别。采用2G-B-R色差特征的模糊C-均值聚类算法对图像进行背景分割后,构建了一种3层BP神经网络模型,通过主成分分析法（principal component analysis,PCA）将15维输入特征参数降为10维以提高识别速度,且最终的整体识别率达到89.5%,实现了羊草与灰绿藜图像的有效分类识别,同时得到灰绿藜与羊草在测试图像中的植被覆盖度分别约为9.78%、34.21%。试验结果表明,利用颜色矩特征为基础,模糊C-均值聚类算法与BP（back propagation,BP）神经网络模型为分割、识别手段能够有效地实现典型牧草的图像分类研究。自动识别牧草是草业数字化的重要组成部分,可为监测植被物种多样性、草种退化及病虫草害的控制提供科学依据,是实现现代草原生态环境保护,发展草原经济的重要途径。
Bibliography:11-2047/S
image recognition; feature extraction; pasture; color moment; principal component analysis; BP neural network
To improve pasture monitoring and low-level digitization in Inner Mongolia Ulanqab desert steppe, the feature extraction and image recognition for two typical pastures were conducted in this paper so as to provide a basis for grass species identification and grassland management. The grass images were collected in the desert steppe of Siziwang banner of Inner Mongolia at 3 pm on August 15, 2014, where belongs to the middle temperate semi-arid continental monsoon climate zone. Under the natural sunlight intensity, 100 original images of varying blade sizes and shapes were taken as training and testing samples from prairie by using an intelligent navigation data acquisition vehicle. The method of color moment was used considering that it can reflect the color distribution information comprehensively. The process doesn＇t need to quantify the color space, and the feature vector dimension is low wh
ISSN:1002-6819
DOI:10.11975/j.issn.1002-6819.2016.23.023