光谱学与光谱分析
光譜學與光譜分析
광보학여광보분석
SPECTROSCOPY AND SPECTRAL ANALYSIS
2014年
5期
1378-1382
,共5页
赵艳茹%余克强%李晓丽%何勇
趙豔茹%餘剋彊%李曉麗%何勇
조염여%여극강%리효려%하용
南瓜叶片%高光谱成像%SPAD%霜霉病
南瓜葉片%高光譜成像%SPAD%霜黴病
남과협편%고광보성상%SPAD%상매병
Pumpkin leaves%Hyperspectral image%SPAD%Downy mildew epidemic
叶绿素浓度是植物生长的指示剂,而叶片的SPAD值则可以反映植物叶绿素含量,从而监测植物的生长状况。本文采用可见-近红外(380~1030 nm)高光谱成像技术可以实现南瓜叶片SPAD值的可视化,同时根据叶片霜霉病疫情与叶绿素含量呈显著正相关进而可以快速诊断霜霉病疫情。通过测定健康叶片和感染不同霜霉病疫情的叶片光谱曲线,采用竞争性自适应重加权算法(CARS)进行特征波段的选择,可以得到10条特征波段,再结合偏最小二乘回归法(PLSR)进行南瓜叶片SPAD的预测。结果表明,通过对48个样本的训练,对23个样本进行预测,可以得到南瓜叶片SPAD 较好的预测效果,其中 RC =0.918,RM-SECV=3.932;RCV =0.846,RMSECV=5.254;RP =0.881,RMSEP=3.714。根据叶片光谱特征波段与SPAD之间的线性回归方程可以计算叶片各个像素点的SPAD值,最后采用图像处理技术可以得到南瓜叶片SPAD的可视化分布图,同时也反映了霜霉病的感染分布,进而判断南瓜叶片的霜霉病疫情。该研究为监测植物生长状况及判别南瓜叶片霜霉病疫情奠定了理论基础。
葉綠素濃度是植物生長的指示劑,而葉片的SPAD值則可以反映植物葉綠素含量,從而鑑測植物的生長狀況。本文採用可見-近紅外(380~1030 nm)高光譜成像技術可以實現南瓜葉片SPAD值的可視化,同時根據葉片霜黴病疫情與葉綠素含量呈顯著正相關進而可以快速診斷霜黴病疫情。通過測定健康葉片和感染不同霜黴病疫情的葉片光譜麯線,採用競爭性自適應重加權算法(CARS)進行特徵波段的選擇,可以得到10條特徵波段,再結閤偏最小二乘迴歸法(PLSR)進行南瓜葉片SPAD的預測。結果錶明,通過對48箇樣本的訓練,對23箇樣本進行預測,可以得到南瓜葉片SPAD 較好的預測效果,其中 RC =0.918,RM-SECV=3.932;RCV =0.846,RMSECV=5.254;RP =0.881,RMSEP=3.714。根據葉片光譜特徵波段與SPAD之間的線性迴歸方程可以計算葉片各箇像素點的SPAD值,最後採用圖像處理技術可以得到南瓜葉片SPAD的可視化分佈圖,同時也反映瞭霜黴病的感染分佈,進而判斷南瓜葉片的霜黴病疫情。該研究為鑑測植物生長狀況及判彆南瓜葉片霜黴病疫情奠定瞭理論基礎。
협록소농도시식물생장적지시제,이협편적SPAD치칙가이반영식물협록소함량,종이감측식물적생장상황。본문채용가견-근홍외(380~1030 nm)고광보성상기술가이실현남과협편SPAD치적가시화,동시근거협편상매병역정여협록소함량정현저정상관진이가이쾌속진단상매병역정。통과측정건강협편화감염불동상매병역정적협편광보곡선,채용경쟁성자괄응중가권산법(CARS)진행특정파단적선택,가이득도10조특정파단,재결합편최소이승회귀법(PLSR)진행남과협편SPAD적예측。결과표명,통과대48개양본적훈련,대23개양본진행예측,가이득도남과협편SPAD 교호적예측효과,기중 RC =0.918,RM-SECV=3.932;RCV =0.846,RMSECV=5.254;RP =0.881,RMSEP=3.714。근거협편광보특정파단여SPAD지간적선성회귀방정가이계산협편각개상소점적SPAD치,최후채용도상처리기술가이득도남과협편SPAD적가시화분포도,동시야반영료상매병적감염분포,진이판단남과협편적상매병역정。해연구위감측식물생장상황급판별남과협편상매병역정전정료이론기출。
Visible/near-infrared (380~1 030 nm ) hyperspectral imaging technique was used to realize SPAD visualization of pumpkin leaves in the present study .Downy mildew could be diagnosed rapidly according to significant positive correlation be-tween downy mildew epidemic and chlorophyll content .Leaves uninfected and infected with different level downy mildew were used to acquire hyperspectral images and extract spectral information .Competitive adaptive reweighted sampling (CARS) was applied to select optimal wavelengths and finally 10 optimal wavelengths were obtained .Partial least squares regression (PLSR) was employed to establish SPAD prediction model .Results showed that ,through the analysis of calibration of 48 samples and prediction of 23 samples ,CARS-PLSR could obtain good results with RC =0.918 ,RMSECV=3.932 ;RCV =0.846 ,RMSECV=5.254;RP =0.881 ,and RMSEP=3.714 .Regression model was gained based on the relationship between SPAD and spectral of pumpkin leaves .While SPAD of each pixel was calculated with PLSR regression equation ,then SPAD distribution map of pumpkin was visualized using imaging processing technology .Final downy mildew infection could be diagnosed based on SPAD distribution map .This study provided a theoretical reference for effective monitoring plant growth and downy mildew epidemic .