应用灰板校正提高计算机视觉预测棉花植株含水量的精确度.pdfVIP

棉 花 学 报 Cotton Science 20 15袁27 3 冤院275―282 用灰板校正提高计算机视觉预测棉花植株含水量的精确度 1 1* 1 2 1 1 王娟 危常州 万丹 肖娟 李玮 顾凯 (1. 河子大学农学院农业资源与环境系 新疆石河子832000 曰2. 新疆天业(集团) 有限公司 新疆石河子832000) 摘要院利用灰板校正以消除棉花不同生育期图片颜色特征值的亮度差异 建立适用于不同生育期预测植株含 水量的通用模型 以提高运用计算机视觉技术进行棉花植株含水量预测的精度遥 研究结果表明 由灰板校正 前尧后颜色特征值 建立的最佳预测模型 决定系数分别为0.746 和0.782遥 有效性检验结果表明 灰板校正 前尧 后计算预测值与实测值的决定系数分别为0.739 和0.783 曰RMSE 分别为2.218 和2.03 RE 分别为2.13% 和1.79%遥 基于计算机视觉提取的冠层图片颜色特征值能够预测植株含水量 应用灰板校正颜色特征值能够 提高模型预测精度 可为提高计算机视觉预测植株水分状况的精度提供技术支撑和方法补充遥 关键词院计算机视觉曰灰板校正曰棉花曰植株含水量曰颜色特征值曰模型 中图分类号院S126:TP391 文献标志码院A 文章编号院1002-7807 20 15冤03-0275-08 10.11963/issn.1002-7807.201503012 1 1* 1 2 1 1 Wang Juan , Wei Changzhou , Wan Dan , Wang Xiaojuan , Li Wei , Gu Kai (1. 832000, ; 2. 832000, ) This paper aimed at establishing a rapid, non-destructive and low-cost model to predict cotton water content for whole growth stages based on computer-vision technology. The data of color characteristic parameters extracted from cotton canopy digital image of different growth periods were adjusted by gray board in order to eliminate differences in brightness and to im- prove the prediction precision of the model. The best prediction model is established based on color characteristic parameters G-B by original data or gray board corrected data, the coefficient of determination for the two models was 0.746 and 0.782, re- spectively. Validation test indicated that the prediction accuracy of models based on gray broad calibrated data was improved comparing to model est