Analyzing the Spatial Distribution Pattern of Image Classification Error.
スポンサーリンク
概要
- 論文の詳細を見る
The quality of image classification results is not always uniform over entire image. Thus, this paper proposes the concept of ISDd (Index of Spatial Distribution by distance) and ISDs (ISD by scatteredness) to evaluate the unevenness of result quality, and spatial distribution of satellite image classification errors. The ISDd is indexed mean distance of misclassified pixels and the ISDs is statistical indicator of scatteredness of misclassified pixels. Using both the ISDd and the ISDs, the basis of decision on adoption/rejection of classification results is offered at sub-image level by evaluation of the local aggregation of misclassified pixels. In this study, we assumed rejection criteria as a window's overall accuracy is under 0.5, and we have extracted the rejection area following this assumption. As a result, users can understand the spatial distribution of misclassified pixels, and can have the basis of the judgement on suitability and reliability of classification results.
- 社団法人 日本写真測量学会の論文
社団法人 日本写真測量学会 | 論文
- Landform monitoring of Tottori Sand Dune using aerial photographs.
- One Projector-One Camera System on Short Range Photogrammetry
- タイトル無し
- A Study on Environmental Evaluation Method Using the Satellite Image-Radiation quantity adjustment of multi-temporal data-.:-Radiation quantity adjustment of multi-temporal data-
- タイトル無し