【摘要】：表型信息是農(nóng)作物品種、生長狀況的直觀表現(xiàn),也是影響農(nóng)作物產(chǎn)量的重要因素。隨著全球人口基數(shù)不斷增大,糧食需求量與日俱增,糧食供給問題日益嚴(yán)峻。快速精確提取大尺度農(nóng)田中農(nóng)作物的表型信息,監(jiān)測作物的生長狀況,并及時采取有效的管理措施,對選育高產(chǎn)優(yōu)質(zhì)的作物品種,維護(hù)我國糧食安全具有深遠(yuǎn)意義。然而,目前多采用人工實地測量的方法獲取表型信息,雖準(zhǔn)確性高,但區(qū)域覆蓋度低,不適合大區(qū)域尺度育種試驗田。隨著遙感技術(shù)的飛速發(fā)展,使實時、快速、無損的獲取大區(qū)域尺度的地表信息成為可能。本研究旨在為基于微小型無人機(jī)高通量遙感平臺獲取作物表型信息提供一定的理論依據(jù),為研究玉米品種基因型與表型信息關(guān)聯(lián)規(guī)律提供輔助支持。于2015年6月至9月在“國家精準(zhǔn)農(nóng)業(yè)示范研究基地”玉米育種研究區(qū)開展了關(guān)于微小型無人機(jī)高通量表型信息獲取試驗,進(jìn)行了圖像特征提取(玉米株高、抽雄時間、植被覆蓋度、葉色變化)及LAI反演研究。主要研究工作及研究結(jié)果如下:(1)利用無人機(jī)高通量遙感平臺獲取的高清數(shù)碼照片數(shù)據(jù),采用ISODATA方法、SVM方法、基于HSV色彩空間變換的決策樹分類三種方法進(jìn)行冠層覆蓋度提取,總精度和Kappa系數(shù)分別為59.06%、0.26,92.70%、0.96,98.32%、0.96�？梢娀贖SV色彩空間變換的決策樹分類精度最高,可利用該方法進(jìn)行多生育期影像冠層覆蓋度提取。(2)利用基于HSV色彩空間變換的決策樹分類和面向?qū)ο蠓诸?結(jié)合紋理、HSV色彩空間變換、NDI植被指數(shù)、幾何信息)兩種方法進(jìn)行玉米雄穗提取,分類總精度分別為83.79%、85.91%,相比于基于HSV色彩空間變換的決策樹分類方法,面向?qū)ο蠓诸惙椒ň容^高。因此,利用面向?qū)ο蠓诸惙椒ㄌ崛∮衩仔鬯?進(jìn)而提取玉米的抽雄時間,提取精度為65.62%,可見利用該方法進(jìn)行玉米抽雄時間的提取、監(jiān)測是可行的。(3)利用基于HSV色彩空間變換的決策樹分類進(jìn)行多生育期玉米葉色變化提取。利用影像的色調(diào)值可以顯著區(qū)分葉片的顏色,從而達(dá)到提取玉米葉色的需求。(4)利用多光譜影像提取的8種植被指數(shù)反演LAI時,對單變量模型而言,NDVI反演的多生育期LAI效果好于其他植被指數(shù),其中線性模型和冪模型反演結(jié)果的R2和RMSE分別為0.525、0.711,0.530、0.717,可以用NDVI來監(jiān)測多生育期玉米LAI的變化情況;在多變量反演過程中,首先對8種植被指數(shù)進(jìn)行主成分分析得到主成分變量,然后對主成分變量進(jìn)行多元線性回歸和BP神經(jīng)網(wǎng)絡(luò)分析。結(jié)果顯示,BP神經(jīng)網(wǎng)絡(luò)對玉米LAI具有較好的反演能力,R2為0.608,RMSE為0.745,可以較好的預(yù)測多生育期玉米LAI的變化情況。(5)在提取株高的過程中,DSM影像提取的6884份育種材料株高值與實測株高值具有很好的線性關(guān)系,R2為0.527,RMSE為0.223。因此通過該方法可以代替?zhèn)鹘y(tǒng)的人工田間測量株高方式;通過生成的株高分布圖,可以更直觀的看到株高的分布及變化情況等信息。
[Abstract]:Phenotypic information is the visual expression of crop variety and growth condition, and it is also an important factor affecting crop yield. With the global population base increasing, food demand is increasing, food supply problem is becoming more and more serious. Rapid and accurate extraction of phenotypic information of crops in large-scale farmland, monitoring of crop growth, and timely and effective management measures are of far-reaching significance for breeding high yield and high quality crop varieties and maintaining food security in China. However, at present, artificial field measurements are used to obtain phenotypic information. Although the accuracy is high, but the area coverage is low, it is not suitable for large-scale breeding field. With the rapid development of remote sensing technology, it is possible to obtain large scale surface information in real time, fast and lossless. The purpose of this study is to provide a theoretical basis for obtaining crop phenotypic information based on the micro-UAV high-throughput remote sensing platform, and to provide auxiliary support for studying the correlation between genotype and phenotypic information of maize varieties. From June to September 2015, an experiment on obtaining high-throughput phenotypic information of micro-UAV was carried out in the Maize breeding Research area of the National Precision Agriculture demonstration Research Base. Vegetation coverage, leaf color change) and LAI inversion. The main research work and results are as follows: (1) using high-throughput remote sensing platform of UAV to obtain high-definition digital photo data, using ISODATA method, SVM method, Three methods of decision tree classification based on HSV color space transform were used to extract canopy coverage. The total accuracy and Kappa coefficient were 59.06 and 0.2692.70 respectively. It can be seen that the classification accuracy of decision tree based on HSV color space transformation is the highest, and this method can be used to extract canopy coverage of multi-growth image. (2) decision tree classification based on HSV color space transformation and object oriented classification (combined with texture). HSV color space transformation, NDI vegetation index and geometric information are used to extract maize male ear. The total classification accuracy is 83.79 and 85.91, respectively, compared with the decision tree classification method based on HSV color space transformation. The accuracy of object-oriented classification method is high. Therefore, using the object oriented classification method to extract the male ear of maize, and then to extract the heading time of maize, the extraction accuracy is 65.622. It can be seen that this method is used to extract the heading time of maize. Monitoring is feasible. (3) the decision tree classification based on HSV color space transformation is used to extract the color change of maize leaves in multi-growth period. The color of leaves can be distinguished significantly by using the hue value of image. (4) when LAI is retrieved exponentially from 8 planting plants extracted from multispectral images, for the single variable model, the color of maize leaves can be extracted. The effect of LAI inversion by NDVI was better than that of other vegetation indices. The R2 and RMSE of linear model and power model were 0.5250.70110.530300.717, respectively. NDVI could be used to monitor the change of LAI in maize in multi-growth period. In the process of multivariate inversion, the principal component variables are obtained by principal component analysis (PCA) for the 8-implant index, and then the principal component variables are analyzed by multivariate linear regression and BP neural network. The results showed that BP neural network had a better ability to retrieve maize LAI (R2 = 0.608 RMSE = 0.745), which could be used to predict the variation of LAI in maize at multi-growth stage. (5) in the process of extracting plant height, There was a good linear relationship between the plant height of 6884 breeding materials extracted by DSM image and the measured plant height. The R2 was 0.527 and the RMSE was 0.223. Therefore, this method can replace the traditional way of measuring plant height in artificial field, and the information of plant height distribution and variation can be seen more intuitively by generating plant height distribution map.
【學(xué)位授予單位】：東北農(nóng)業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：S513;TP751

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 趙曉慶;楊貴軍;劉建剛;張小燕;徐波;王艷杰;趙春江;蓋鈞鎰;;基于無人機(jī)載高光譜空間尺度優(yōu)化的大豆育種產(chǎn)量估算[J];農(nóng)業(yè)工程學(xué)報;2017年01期

2 劉建剛;趙春江;楊貴軍;于海洋;趙曉慶;徐波;牛慶林;;無人機(jī)遙感解析田間作物表型信息研究進(jìn)展[J];農(nóng)業(yè)工程學(xué)報;2016年24期

3 高林;楊貴軍;于海洋;徐波;趙曉慶;董錦繪;馬亞斌;;基于無人機(jī)高光譜遙感的冬小麥葉面積指數(shù)反演[J];農(nóng)業(yè)工程學(xué)報;2016年22期

4 王振武;孫佳駿;于忠義;卜異亞;;基于支持向量機(jī)的遙感圖像分類研究綜述[J];計算機(jī)科學(xué);2016年09期

5 陶志強(qiáng);Shamim Ara Bagum;馬瑋;周寶元;付金東;崔日鮮;孫雪芳;趙明;;運(yùn)用光譜參數(shù)冠層覆蓋度建立作物長勢及氮營養(yǎng)狀態(tài)模型[J];光譜學(xué)與光譜分析;2016年01期

6 王斐;李強(qiáng);王克雄;向國程;李玉蓮;撒金東;;抽雄早晚對玉米農(nóng)藝性狀和產(chǎn)量的影響研究[J];寧夏農(nóng)林科技;2015年11期

7 滕曉偉;董燕生;沈家曉;孟魯閩;馮海寬;;AquaCrop模型對旱區(qū)冬小麥抗旱灌溉的模擬研究[J];中國農(nóng)業(yè)科學(xué);2015年20期

8 高林;楊貴軍;王寶山;于海洋;徐波;馮海寬;;基于無人機(jī)遙感影像的大豆葉面積指數(shù)反演研究[J];中國生態(tài)農(nóng)業(yè)學(xué)報;2015年07期

9 賈玉秋;李冰;程永政;劉婷;郭燕;武喜紅;王來剛;;基于GF-1與Landsat-8多光譜遙感影像的玉米LAI反演比較[J];農(nóng)業(yè)工程學(xué)報;2015年09期

10 楊貴軍;萬鵬;于海洋;徐波;馮海寬;;無人機(jī)多光譜影像輻射一致性自動校正[J];農(nóng)業(yè)工程學(xué)報;2015年09期

相關(guān)博士學(xué)位論文 前3條

1 賈銀江;無人機(jī)遙感圖像拼接關(guān)鍵技術(shù)研究[D];東北農(nóng)業(yè)大學(xué);2016年

2 王鑫;基于高分辨率遙感影像的植被分類方法研究[D];北京林業(yè)大學(xué);2015年

3 程遠(yuǎn)航;無人機(jī)航空遙感圖像動態(tài)拼接技術(shù)的研究[D];東北大學(xué);2009年

相關(guān)碩士學(xué)位論文 前6條

1 張靜;西北旱區(qū)遙感影像分類方法研究[D];西北農(nóng)林科技大學(xué);2016年

2 胡暢;面向?qū)ο蠓诸惙椒ㄔ谒拇ㄇ鹆陞^(qū)森林分類中的應(yīng)用研究[D];四川農(nóng)業(yè)大學(xué);2015年

3 陳啟浩;面向?qū)ο蟮亩嘣催b感數(shù)據(jù)分類技術(shù)研究與實現(xiàn)[D];中國地質(zhì)大學(xué);2007年

4 彭璐;支持向量機(jī)分類算法研究與應(yīng)用[D];湖南大學(xué);2007年

5 姜麗麗;水分脅迫和正常灌溉條件下玉米株高、產(chǎn)量的QTL分析[D];內(nèi)蒙古農(nóng)業(yè)大學(xué);2006年

6 黃瓊英;支持向量機(jī)多類分類算法的研究及應(yīng)用[D];河北工業(yè)大學(xué);2005年

，

本文編號：2343038