红外, 2014, 35 (3): 43, 网络出版: 2014-03-31  

多光谱图像技术在土壤酸碱度检测中的应用

Application of Multispectral Image Technology in Detection of Soil pH Value
作者单位
浙江工业大学信息工程学院, 浙江 杭州 310032
摘要
提出了一种利用多光谱图像的颜色特征对土壤酸碱度(pH值)进行快速无损检测的方法。 首先,利用2 CCD多光谱成像仪获取每个土壤样本的R、G、B、NIR图像各一幅,并对多光谱图像进行颜色空间转 换,即从RGB色彩空间分别转换到HSV颜色空间和Lab颜色空间;然后提取不同颜色空间中多光谱图像的颜色特征; 最后,分别将提取的颜色特征作为模型的输入变量,建立PLS和LS-SVM算法的土壤酸碱度预测模型。实验结果表 明,利用多光谱图像技术对土壤酸碱度进行检测是可行的。预测模型的最佳结果如下:决定系数(R2)为0.91,预测均 方根误差(RMSEP)为0.34。
Abstract
A method for fast and non-destructively detecting soil pH by using the color features in multispectral images is proposed. First, a 2 CCD multispectral imager is used to obtain the R, G, B and NIR images of each soil sample respectively. The multispectral images are converted in color space, i.e. the RGB color spaces are converted to the HSV color space and the Lab color space. Then, the color features of the multispectral images are extracted in different color spaces. Finally, the extracted color features are used as input variables, so as to establish a prediction model of soil pH by using PLS and LS-SVM algorithms. The experimental result shows that it is feasible to detect soil pH by using the multispectral image technology. The best result is given by the prediction model established. Its determination coefficient (R2) and root mean square error (RMSEP) value are 0.91 and 0.34 respectively.
参考文献

[1] Fernandez-Calvino D, Rousk J, Brookes P C, et al. Bacterial pH-optima for Growth Track Soil pH, But Are Higher Than Expected at Low pH [J]. Soil Biology & Biochemistry, 2011, 43(2): 1569-1575.

[2] Aciego Pietri J C, Brookes P C. Substrate Inputs and pH As Factors Controlling Microbial Biomass, Activity and Community Structure in an Arable Soil [J]. Soil Biology & Biochemistry, 2009, 41(1): 1396-1405.

[3] 黄玉松. 土壤对杨梅生长结果的影响分析 [J]. 农业科技通讯, 2012, 6(7): 224-225.

[4] Indrasumunar A, Menzies N W, Dart P J. Laboratory Prescreening of Bradyrhizobium Japonicum for Low pH, Al and Mn Tolerance Can Be Used to Predict Their Survival in Acid Soils [J]. Soil Biology & Biochemistry, 2012, 48(2): 135-141.

[5] 肖武, 李小昱, 李培武, 等. 近红外光谱和机器视觉信息融合的土壤含水率检测 [J]. 农业工程学报, 2009, 25(8): 14-17.

[6] 吴建. 基于最小二乘支持向量机的土壤含水量检测的研究与分析 [J]. 电脑知识与技术, 2008, 3(9): 2043-2044.

[7] 吴沿友, 周秋月, 向忠平, 等. 基于图像分析的土壤速效磷的测定 [J]. 农业环境科学学报, 2008, 27(6): 2504-2508.

[8] 张荣标, 何加祥, 吴涛, 等. 基于图像处理的土壤表层含水率在线检测方法研究 [J]. 农业工程学报, 2007, 23(10): 57-61.

[9] Bartholomeus H, Kooistra L, Stevens A, et al. Soil Organic Carbon Mapping of Partially Vegetated Agricultural Fields with Imaging Spectroscopy [J]. International Journal of Applied Earth Observation and Geoinformation, 2011, 13(1): 81-88.

[10] 许新征, 丁世飞, 史忠植, 等. 图像分割的新理论和新方法 [J]. 电子学报, 2010, 38(2A): 76-82.

[11] 黄长专, 王彪, 杨忠. 图像分割方法研究 [J]. 计算机技术与发展, 2009, 19(6): 76-79.

[12] 庞晓敏, 闵子健, 阚江明. 基于HSI和LAB颜色空间的彩色图像分割 [J]. 广西大学学报(自然科学版), 2011, 36(6): 976-980.

李云, 杨海清. 多光谱图像技术在土壤酸碱度检测中的应用[J]. 红外, 2014, 35(3): 43. LI Yun, YANG Hai-qing. Application of Multispectral Image Technology in Detection of Soil pH Value[J]. INFRARED, 2014, 35(3): 43.

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!