Training set size, scale, and features in Geographic Object-Based Image Analysis of very high resolution unmanned aerial vehicle imagery
Training set size, scale, and features in Geographic Object-Based Image Analysis of very high resolution unmanned aerial vehicle imagery
复制标题
超高分辨率无人机图像的基于地理对象的图像分析中的训练集大小、规模和特征
DOI：
10.1016/j.isprsjprs.2014.12.026
复制
发表时间：
2015-04
影响因子：
12.7
通讯作者：
Ma Xiaoxue
中科院分区：
文献类型：
--
作者：
Ma Lei;Cheng Liang;Li Manchun;Liu Yongxue;Ma Xiaoxue
近年来，无人机（UAV）由于其更大的可用性和传感器的小型化而越来越多地用于自然资源应用。此外，基于地理对象的图像分析（GEOBIA）作为遥感对地观测数据的一种新范式也受到了越来越多的关注。然而，GEOBIA产生了一些新的问题相比，基于像素的方法。在这项研究中，我们开发了一种基于对象的分类的半自动优化策略，该策略涉及基于区域的准确性评估，该评估分析了规模和训练集大小之间的关系。我们发现，当分割尺度参数（SSP）固定时，总体准确度（OA）随着训练集比率（用于训练的分割对象的比例）的增加而增加。随着训练集比例的增大，OA的增长速度变慢，基于像素的图像分析也得到了类似的规律。当训练集比率固定时，随着SSP的增加，OA降低。因此，在使用小训练集比率的分类期间，SSP不应太大。相比之下，如果使用高SSP执行分类，则需要较大的训练集比率。此外，我们建议，最佳的SSP为每个类有一个高度的正相关性，通过人工判读得到的平均面积，这可以概括为一个线性相关方程。我们希望这些结果将适用于无人机图像分类，以确定每个类的最佳SSP。
Unmanned Aerial Vehicle (UAV) has been used increasingly for natural resource applications in recent years due to their greater availability and the miniaturization of sensors. In addition, Geographic Object-Based Image Analysis (GEOBIA) has received more attention as a novel paradigm for remote sensing earth observation data. However, GEOBIA generates some new problems compared with pixel-based methods. In this study, we developed a strategy for the semi-automatic optimization of object-based classification, which involves an area-based accuracy assessment that analyzes the relationship between scale and the training set size. We found that the Overall Accuracy (OA) increased as the training set ratio (proportion of the segmented objects used for training) increased when the Segmentation Scale Parameter (SSP) was fixed. The OA increased more slowly as the training set ratio became larger and a similar rule was obtained according to the pixel-based image analysis. The OA decreased as the SSP increased when the training set ratio was fixed. Consequently, the SSP should not be too large during classification using a small training set ratio. By contrast, a large training set ratio is required if classification is performed using a high SSP. In addition, we suggest that the optimal SSP for each class has a high positive correlation with the mean area obtained by manual interpretation, which can be summarized by a linear correlation equation. We expect that these results will be applicable to UAV imagery classification to determine the optimal SSP for each class.
登录
查看更多内容
DOI：
10.1016/j.isprsjprs.2013.02.001
发表时间：
2013-05-01
影响因子：
12.7
作者：
Kim, Jinsoo;Lee, Seongkyu;Choi, Chuluong
通讯作者：
Choi, Chuluong
DOI：
10.1109/jstars.2013.2253089
发表时间：
2013-04
影响因子：
5.5
作者：
Jan Stefanski;B. Mack;B. Waske
通讯作者：
Jan Stefanski;B. Mack;B. Waske
影响因子：
3.4
作者：
H. Costa;H. Carrão;F. Bação;M. Caetano
通讯作者：
H. Costa;H. Carrão;F. Bação;M. Caetano
DOI：
10.1016/j.isprsjprs.2013.11.006
发表时间：
2014-01-01
影响因子：
12.7
作者：
Witharana, Chandi;Civco, Daniel L.
通讯作者：
Civco, Daniel L.
影响因子：
13.5
作者：
Chan, Jonathan Cheung-Wai;Paelinckx, Desire
通讯作者：
Paelinckx, Desire