Journal of Geo-information Science >
Quantitatively Evaluating Indexes for Object-based Segmentation of High Spatial Resolution Image
Received date: 2013-01-21
Revised date: 2013-03-11
Online published: 2013-08-08
Traditional classification accuracy assessments in terms of overall accuracy or Kappa coefficient based on isolating pixels statistic, cannot capture the geometrical properties of the segmented image objects, and therefore do not provide an accurate evaluation in object based segmentation or classification. Considering the importance of bordering pixels and geometric shape in object segmentation, it is thus of our interesting to design some measuring indexes introduced the border pixels and geometric structure information to evaluate the object-based resultant image segmentation or classification. This paper improved five indexes originally proposed by Persello and Bruzzone to evaluate the resultant segmentation of high spatial resolution image. Realizing that the original indices cannot well capture the gap among different categories, resulting in difficulties in discriminating the assessment results of different categories, we use normalized techniques based on geometric shape to overcome it. The indices depend on the geometry features of each object of the thematic map including over segmentation, under segmentation, edge location, fragmentation error and shape error. Moreover, we realized a prototype system contained the aforementioned evaluated indexes based on IDL platform to support the object-based image processing and analysis. To validate these indexes, a subset QuickBird image located on Fuzhou was implemented and the results of the Meanshift segmented algorithm demonstrate that the proposed indexes can provide better accuracy evaluation of each land cover class, and can make users more effectively choose the best classification map. Moreover, our experiments also demonstrate that, compared with OA and Kappa coefficient, the proposed indexes have advantages on characterizing the detailed ground materials and are helpful in aiding the optimal parameters selection for the Meanshift segmented algorithm.
TUN Bei, LIN Shan-Shan, ZHOU Gui-Jun . Quantitatively Evaluating Indexes for Object-based Segmentation of High Spatial Resolution Image[J]. Journal of Geo-information Science, 2013 , 15(4) : 567 -573 . DOI: 10.3724/SP.J.1047.2013.00567
[1] 周成虎,骆剑承.高分辨率遥感卫星影像地学计算[M].北京:科学出版社,2009.
[2] Myint S, Lam N, Tylor J M. Wavelets for urban spatial feature discrimination: Comparisons with fractal, spatial autocorrelation, and spatial cooccurrence approaches[J]. Photogrammetric Engineering and Remote Sensing, 2004,70(7):803-812.
[3] 宫鹏,黎夏,徐冰.高分辨率遥感影像解译理论与应用方法中的一些研究问题[J].遥感学报,2006,10(1):1-5.
[4] 闫利,赵展,聂倩,等.利用规则进行高分辨率遥感影像地物提取[J].武汉大学学报·信息科学版,2012,37(6):636-639.
[5] 杜凤兰,田庆久,夏学齐,等.面向对象的地物分类法分析与评价[J].遥感技术与应用,2004,19(1):20-23.
[6] Bruzzone L, Carlin L. A multilevel context-based system for classification of very high spatial resolution images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2006,44(9):2587-2600.
[7] 汪闽,万其明,张大骞,等.光谱、形状特征结合的多精度图像分割算法与应用[J].地球信息科学学报,2010,12(2):261-268.
[8] 李秦,高锡章,张涛,等.最优分割尺度下的多层次遥感地物分类实验分析[J].地球信息科学学报,2011,13(3):409-417.
[9] Foody G M. On the compensation for chance agreement in image classification accuracy assessment[J]. Photogrammetric Engineering and Remote Sensing,1992,58(10):1459-1460.
[10] Persello C, Bruzzone L. A novel protocol for accuracy assessment in classification of very high resolution images[J]. IEEE Transactions on Geoscience and Remote Sensing,2009,48(3):1232-1244.
[11] Huang Q, Dom B. Quantitative methods of evaluating image segmentation[C]. Proc.Conf. on Image Processing (ICIP’95), 1995(3):53-56.
[12] 章毓晋.图像工程(第2版)[M].北京:清华大学出版社,2007.
[13] Comanicis D, Meer P. Mean shift: A robust application toward feature space analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619.
[14] 沈占锋,骆剑承,胡晓东.高分辨率遥感影像多尺度均值漂移分割算法研究[J].武汉大学学报·信息科学版,2010,35(3):313-316.
[15] 薄树奎,韩新超,丁琳.面向对象影像分类中分割参数的选择[J].武汉大学学报·信息科学版,2009,34(5):514-517.
/
| 〈 |
|
〉 |