基于无人机成像的棉田判别与面积估测  

Cotton field discrimination and area estimation by using unmanned aerial vehicle imaging

在线阅读下载全文

作  者:邹昆霖 张若宇[1] 江英兰[1] Zou Kunlin;Zhang Ruoyu;Jiang Yinglan(College of Mechanical and Electrical Engineering/Key Laboratory of Northwest Agricultural Equipment,Ministry of Agriculture,Shihezi,Xinjiang 832003 China)

机构地区:[1]石河子大学机械电气工程学院/农业部西北农业装备重点实验室

出  处:《石河子大学学报(自然科学版)》2018年第6期753-760,共8页Journal of Shihezi University(Natural Science)

基  金:国家自然科学基金项目(31560341);石河子大学国际科技合作推进计划(GJHZ201705);农业部农业物联网重点实验室开放课题(2017AIOT-07)

摘  要:准确测量棉花种植面积和空间分布,对棉花产业发展有重要意义。无人机近地面成像因其空间分辨率高、成本低、周期短和可重复性强等特点,在土地和作物信息监测等方面逐步得到应用。本文提出采用无人机成像的方式进行棉田种植面积估测,首先采用无人机搭载可见光相机,对棉田及周边地区进行成像,并计算图像植被指数和纹理等共36项特征;其次通过主成分分析算法综合分析各个类型特征的优势并筛选有效特征,再采用最大似然分类法识别棉田;最后计算棉田面积,棉田面积总误差为0.51%,其中脱叶棉田面积误差为0.72%,未脱叶棉田面积误差为0.32%。上述结果表明:该方法可有效判别棉田像素点并计算棉田面积,可为收获期棉田面积测量和空间分布分析提供参考。Accurate measurement of cotton planting area and distribution is of great significance for cotton field management. Due to its high spatial resolution, low cost, short cycle and high repeatability, unmanned aerial vehicle near-ground imaging has been gradually applied in land and crop information monitoring. This work demonstrates a method to estimate the cotton field area by the UAV imaging. First, Images of the cotton field and surrounding areas was collected by the visible light camera installed on the UAV. Then, a total of 36 features such as vegetation index and texture were calculated. Secondly, the principal component analysis algorithm was used to analyze the advantages of each type of feature and screen the effective features, then these features were used to discriminate the cotton field by the maximum likelihood classification method. Finally, the area of the cotton field was calculated. The total error of cotton field extraction was 0.51%, the error of defoliated cotton field was 0.72%, and the error of undefoliated cotton field was 0.32%. The results show that the method can effectively identify and estimate the cotton field area, which provided a reference for the area estimation and spatial distribution analysis of cotton field during harvest.

关 键 词:无人机 棉田判别 面积估测 纹理特征 植被指数 

分 类 号:S127[农业科学—农业基础科学]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象