利用四元樹法在SPOT影像上做林型分類之研究

A Study on Quadtree Method to Forest Cover Classification on SPOT Imageries

黃國楨(Kwo-Jern Hwang) ； 焦國模(Kwo-Mu Chiao)

《航測及遙測學刊》 2卷1期 (1997/03) Pp. 13-29

https://doi.org/10.6574/JPRS.1997.2(1).2

摘要

森林資源遙測包括林區調查、災害評估與森林管理等，其中以林型分類在森林資源遙測上為最首要工作。傳統分類林型大致使用監督性統計模式最大概似法則，而在這次研究中，為了要獲得更精確森林資源林型分佈狀況，我們提出一個簡單四元樹方法來辨識林型分佈。實驗中我們使用法國衛星（SPOT）做為材料，配合圖籍與數化地理資訊圖層套疊取樣以選取訓練樣區，再者用我們設計四元樹切割影像方法，切割臺灣大學實驗林衛星影像，直到切割每個子區域各灰值非常均勻為止，最後將均勻各子區域選用數學式相關係數並配合權重數來計算分類林型，實驗結果顯示本研究所提出四元樹方法在林型分類是可行的且優於傳統統計模式最大概似分類法。

關鍵字

四元樹 ； 相關係數 ； 權重數

並列摘要

Forest Remote Sensing consists of forest investigation、disaster estimation, and forest management etc.. One of the main purpose of remote sensing is to recognize the distribution of forest cover type. In this research, we propose a method to estimate the distribution on the remote sensing images with an eye to obtaining important information of forest resources for management purpose. In our work, French Satellite image (SPOT) is adopted as the material, and are integrated forest map and geographic information system as the overlay resampling. We devise the quadtree segmentation method to segment the image of National Taiwan University Forest into uniform areas that satisfy the property of gray level homogeneity. To maximum likelihood classifier in conjunction with associating correlation value and weight loss are utilized to classify the distribution of forest. Experimental results reveal the feasibility of the proposed approach in forest cover classification.

並列關鍵字

Quadtrees ； Correlation ； Weight loss