綠化生態模型的評估：以遙測影像的水稻田影像判釋：自組織映射圖與邏輯式迴歸之研究

The Eco-friendly Evaluation Model: The Paddy Rice Image Classification through SOM and Logistic Regression by Remote Sensing Data

張士勳(Shih-Hsun Chang) ； 萬絢(Shiuan Wan) ； 周彥芝(Yan-Zhi Chou)

《水保技術》 7卷4期 (2012/10) Pp. 212-220

https://doi.org/10.30040/JSWCT.201210.0002

摘要

水稻田在都市環境上對水土保持之影響主要有三：區域性水田綠化環境、水田調洪功能與二氧化碳的吸收淨化空氣。在台灣水稻為台灣賴以維生的糧食作物，為了讓政府取得糧食政策制訂、產量推估與農民休耕或災後補助之依據來源，通常都會進行水稻種植面積的調查。而以往對於水稻田的判斷都是以實地探勘方式進行耕地坵塊圖（Rice Pattern）數化與編修。這些過程通常需要大量人力，因此透過遙測影像與合適的分類器足以改善現場探勘之困境。本研究以60筆訓練樣本即120筆測試樣本為例，利用自組織映射圖（Self-Organizing Map, SOM）和邏輯式迴歸（Logistic Regression）建構判釋規則。並引入有效紋理資訊和植生指標作為輔助資訊，對水稻田判釋上提供一套有效資訊萃取的策略。其貢獻有四點：（1）避免不必要的雜訊引入（2）萃取眾多水稻田描述因子中之主要有效因子（3）建立水稻田發生的判釋規則（4）提升判釋水稻田發生的正確性。

關鍵字

自組織映射圖 ； 邏輯式迴歸 ； 判釋規則 ； 紋理資訊 ； 植生指標

並列摘要

Paddy rice is the major crop of food in Taiwan. There are three main contributions on Taiwan: regional eco-friendly of environments, adjustment of floods and refresh the air pollution. The estimation of area is important since this information are related to the national food policy, yearly crop yields calculation and post-disaster reimburse. In the past, it is performed through field exploration and rice pattern revising, which is a large amount of human power and time-consuming works. A more economic manner to estimate paddy rice area is desired. Accordingly, this study aims to design a paddy rice classifier in which the area of paddy rice in a remote sensing image can be calculated. In this study, 60 samples of data (pixels in image) are selected and used for classification training process, and 120 samples for validation. Self-Organizing Map method is used for clustering and Logistic Regression method is used to construct the classification rules. It is noted that in the present study texture information and vegetation index are included as ancillary features. This is quite beneficial in constructing a more effective informational retrieval strategy for paddy rice classification. In the study the main contributions are summarized as follows, (1) avoid uncertainties, (2) retrieve the primary factors (3) establish a series of classification rules for paddy rice, (4) increase the accuracy of classification.

並列關鍵字

Image Classification ； Texture Information ； Self-Organizing Map ； Logistic Regression