- 期刊
物件式分類法於高解析度航照影像萃取崩塌地之研究
Object-based Classification for Detecting Landslides Using High Resolution Aerial Images
摘要
傳統的影像分類技術是以像元式（Pixel-Based）的方法為主，但若使用高空間解析度的影像時會產生椒鹽效應（Salt and Pepper Effect）的現象，進而影響分類的精度。基於此，本研究利用物件式（Object-Based）的影像分類方法於Z/I DMC（Digital Mapping Camera）航照影像上萃取出崩塌地區域。首先，本研究比較了Mean-shift和Ward二種不同演算法之影像分割技術，並採取分割結果較佳的Mean-shift演算法將航照影像依同質性分割成不同區塊，接著以每個區塊為最小單元進行分類，最後評估萃取出來之崩塌地的精度。研究結果顯示物件式的影像分類方法可以有效消除在像元式影像分類上所產生的椒鹽效應現象，其崩塌地萃取整體精度從87.05%（像元式分類）提升至99.41%（物件式分類）。
並列摘要
Traditional image classification techniques use per-pixel (pixel-based) approaches to classify images. However, due to ＂salt-and-pepper effect＂, these approaches often result in less satisfactory outcome when applied to high resolution aerial image data. Therefore, the objective of this study was to use object-based classification method to detect landslide areas using aerial images acquired by Z/I DMC (Digital Mapping Camera). Firstly, this study compared two kinds of image segmentation techniques (Mean-shift and Ward approaches), and the algorithm with better segmentation result was adopted to segment image into regions based on homogeneity. Then each region was taken as a unit for image classification, and the accuracy of landslide detection was evaluated. The results show that, compared with pixel-based image classification approach, object-based image classification approach can effectively reduce ＂salt-and-pepper effect＂ and improve the accuracy of landslide extraction from high resolution aerial images. In this study, the overall accuracy for landslide extraction using pixel-based and object-based classification method was 87.05% and 99.41, respectively.
被引用紀錄
延伸閱讀
- 蕭國鑫、尹承遠、劉進金、遊明芳、王晉倫（2003）。SPOT影像與航照資料應用於崩塌地辨識之探討。航測及遙測學刊，8(4)，29-42。https://doi.org/10.6574/JPRS.2003.8(4).3
- 謝依達、陳建璋、黃雅莉、鍾玉龍、陳朝圳、吳守從（2014）。以數位航測資料探討崩塌地變遷與潛感區推估：觀高地區為例。坡地防災學報，13(1)，14-29。https://www.airitilibrary.com/Article/Detail?DocID=a0000474-201406-201809030014-201809030014-14-29
- Yang, C. C. (2019). Deep Learning-Based Land Cover Classification Using Airborne Lidar and Aerial Imagery [master's thesis, National Chiao Tung University]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0030-0306202016332560
- 楊孟學、林明璋、劉進金（2009）。Integrating Geomorphic Indexes and SPOT Multispectral Imagery for Landslides Classification。航測及遙測學刊，14(1)，11-23。https://doi.org/10.6574/JPRS.2009.14(1).2
- Teo, T. A., & Huang, C. H. (2016). Object-Based Land Cover Classification Using Airborne Lidar and Different Spectral Images. Terrestrial, Atmospheric and Oceanic Sciences, 27(4), 491-504. https://doi.org/10.3319/TAO.2016.01.29.01(ISRS)