查詢結果分析
來源資料
頁籤選單縮合
題名 | 利用植被反射光譜辨識水稻品種=Discriminate Rice Cultivars Using Canopy Reflectance Spectra |
---|---|
作者 | 陳榮坤; 楊純明; Chen, Rong-kuen; Yang, Chwen-ming; |
期刊 | 作物、環境與生物資訊 |
出版日期 | 20041200 |
卷期 | 1:4 2004.12[民93.12] |
頁次 | 頁239-250 |
分類號 | 434.111 |
語文 | chi |
關鍵詞 | 植被光譜特徵; 水稻品種辨識; 逐步判別分析; 主成分轉換; 判別分析; Canopy spectral characteristics; Rice cultivar discrimination; Stepwise discriminant analysis; Principle component transformation; Discriminant analysis; |
中文摘要 | 摘要 本研究旨在量測不同水稻品種,即臺農 67 號(TNG 67)、臺8 號(TK 8)及臺農71 號(TNG 71),在生育期間及期作間之近地 面高解析植被反射光譜(350-2400 nm),以 篩檢合適光譜特徵,建立辨識水稻品種之光 譜遙測模式。田間試驗係於2002 年在臺中 縣霧峰鄉行政院農業委員會農業試驗所農 場進行,計有一、二期稻作。將植被光譜涵 蓋之所有窄波段先經由逐步判別分析 (stepwise discriminant analysis,SDA)篩 檢出若干條合適的光譜特徵窄波段,續由主 成分轉換(principle components transformation,PCT)構成多項主成分,再 由判別分析(discriminant analysis,DA)將 各主成分建立辨識水稻品種之光譜遙測模 式。結果顯示,TNG 67、TK 8 及TNG 71 等三水稻品種的辨識準確度與所選擇特徵 窄波段數之間呈現飽和指數型曲線模型 (exponential rise to max),一、二期稻作 皆然。整體而言,在選擇相同窄波段數的條 件下,一期稻作的辨識準確度高於二期作 者;例如,一、二期稻作在選擇7 條特徵窄 波段時,全體準確度分別達到87%及82%。 當選擇的特徵窄波段數介於7-10 條時,辨 識度緩慢提升,惟當窄波段數目超過10 條 以上時,所增加的辨識能力將十分有限。欲 達到95% 以上的全體準確度(overall accuracy),則特徵窄波段數至少需要達到 15 條。又由檢視的三品種間樣品族群空間 距離分佈結果,發現一期稻作的TK 8 與 TNG 71 之植被反射光譜特徵表現較相近, 而TNG 67 與此二品種的差異較大;二期稻 作則以TK 8 與TNG 67 之植被反射光譜特 徵表現較類似,而TNG 71 則與此二品種的 差異較大。本研究據此提供了栽培於一、二 期稻作之TNG 67、TK 8 與TNG 71 等三品 種利用植被光譜進行品種辨識的方法,並初 步瞭解此三品種間光譜特徵之差異。 |
英文摘要 | ABSTRACT Ground-based remotely sensed high-resolution canopy reflectance spectra (350-2400 nm) were obtained from field experiments to study spectral differences among rice cultivars during the growing periods and between the cropping seasons of 2002. The suitable spectral characteristics were also selected to build the spectral models for cultivar discrimination. In the first step, 3-11 narrow bands were selected progressively from reflectance spectra as the spectral characteristics by the stepwise discriminant analysis. Secondly, through the principal components transformation processes the selected narrow bands were composed to various components, which were used to establish the spectral models by the discriminant analysis. It indicated that the accuracy in discriminating cultivars TNG 67, TK 8, and TNG 71 was related to numbers of selected narrow bands, expressing as an exponential rise to maximum function in both cropping seasons. Generally the accuracy in cultivar discrimination was higher in the first crop than in the second crop under same numbers of the selected narrow bands. For example, when 7 narrow bands were selected, overall accuracy was 87% in first crop and was 82% in second crop. The percent overall accuracy increased slowly when 7 to 10 bands were selected. To reach 95% of overall accuracy, at least 15 bands should be selected. It further showed that the distance distribution among the sampling populations of three cultivars was different between cropping seasons. The distance between TK 8 and TNG 71 was smaller than other pairs in the first crop while the distance between TK 8 and TNG 67 was smaller than others in the second crop. As a result, this study provides information about differences in spectral characteristics among cultivars TNG 67, TK 8 and TNG 71 as well as an appropriate analysis method for discriminating these three cultivars using hyperspectral data of both cropping seasons. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。