A unsupervised quality valuation method for multi-scale remote sensing image segmentation based on boundary information
-
摘要: 多尺度分割是高分辨率遥感影像信息提取的关键步骤,但是如何评价分割质量、量化分割错误一直是具有挑战性的课题。本文在边界强度信息的基础上,构建了一种非监督的分割评价方法,用于多尺度遥感影像分割的最优尺度参数选择与局部分割质量评价。分割错误包括过分割与亚分割2种,该文利用归一化边界梯度特征,分别对2类分割错误进行了建模。对过分割错误的估计考虑了斑块边缘的梯度信息,而对亚分割错误的评估运用了斑块内部梯度信息。为了验证所提出的方法,利用2景高分辨率遥感影像,开展了多尺度分割结果的评价实验,所提出方法的分割评价与实际分割效果吻合度较高。结果表明,该文方法可以有效反映斑块的过分割与亚分割错误。Abstract: Multi-scale segmentation is a key step in the information extraction of high-resolution remote sensing images. However, the evaluation of segmentation quality and the quantification of segmentation errors are still challenging. Based on boundary strength information, this study developed an unsupervised segmentation evaluation method of selecting the optimal scale parameter and elevating the local segmentation quality for multi-scale remote sensing image segmentation. Segmentation errors include over-segmentation and under-segmentation. This study modeled the two types of errors using normalized boundary gradient characteristics. The gradient information of patch edges was considered in the estimation of over-segmentation errors, while the intra-patch gradients were employed for the assessment of under-segmentation errors. To validate the proposed method, this study conducted an experiment on the evaluation of multi-scale segmentation results using two scenes of high-resolution remote sensing images. The segmentation evaluation results of the method coincided perfectly with the actual segmentation effects. The results indicate that the method proposed in this study can effectively reflect over- and under-segmentation errors.
-
-
[1] Hossain M, Chen D. Segmentation for object-based image analysis(OBIA):A review of algorithms and challenges from remote sensing perspective[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 150(1):115-134.
[2] Beauchemin M. Semi-supervised map regionalization for categorical data[J]. International Journal of Remote Sensing, 2019, 40(24):9401-9411.
[3] Xiang D, Wang W, Tang T, et al. Adaptive statistical superpixel merging with edge penalty for polsar image segmentation[J]. IEEE Transactions on Geo-scienceand Remote Sensing, 2019, 58(4):2412-2429.
[4] Zhang M, Xue Y, Ge Y, et al. Watershed segmentation algorithm based on luv color space region merging for extracting slope hazard boundaries[J]. ISPRS International Journal of Geo-Information, 2020, 9(4):246.
[5] Su T F, Liu T X, Zhang S W, et al. Machine learning-assisted region merging for remote sensing image segmentation[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 168(1):89-123.
[6] 张大明, 张学勇, 李璐, 等. 一种超像素上Parzen窗密度估计的遥感图像分割方法[J]. 国土资源遥感, 2022, 34(1):53-60.doi:10.6046/gtzyyg.2021089.
[7] Zhang D M, Zhang X Y, Li L, et al. Remote sensing image segmentation based on Parzen window density estimation of super-pixels[J]. Remote Sensing for Land and Resources, 2022, 34(1):53-60.doi:10.6046/gtzyyg.2021089.
[8] Baatz M, Sch?pe A. Multiresolution segmentation:An optimizing approach for high quality multi-scale segmentation[C]. Angewandte Geographich Informationsverarbeitung, 2000,XII,12-23.
[9] 范莹琳, 娄德波, 张长青, 等. 基于面向对象的铁尾矿信息提取技术研究——以迁西地区北京二号遥感影像为例[J]. 自然资源遥感, 2021, 33(4):153-161.doi:10.6046/zrzyyg.2021027.
[10] Fan Y L, Lou D B, Zhang C Q, et al. Information extraction technologies of iron mine tailings based on object-oriented classification:A case study of Beijing-2 remote sensing images of the Qianxi Area,Hebei Province[J]. Remote Sensing for Natural Resources, 2021, 33(4):153-161.doi:10.6046/zrzyyg.2021027.
[11] 王华, 李卫卫, 李志刚, 等. 基于多尺度超像素的高光谱图像分类研究[J]. 自然资源遥感, 2021, 33(3):63-71.doi:10.6046/zrzyyg.2020344.
[12] Wang H, Li W W, Li Z G, et al. Hyperspectral image classification based on multiscale superpixels[J]. Remote Sensing for Natural Resources, 2021, 33(3):63-71.doi:10.6046/zrzyyg.2020344.
[13] Costa H, Foody G M, Boyd D S. Supervised methods of image segmentation accuracy assessment in land cover mapping[J]. Remote Sensing of Environment, 2018, 205(2):338-351.
[14] Witharana C, Civco D L. Optimizing multi-resolution segmentation scale using empirical methods:Exploring the sensitivity of the supervised discrepancy measure euclidean distance 2(ED2)[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 87(1):108-121.
[15] Su T F, Zhang S W. Multi-scale segmentation method based on binary merge tree and class label information[J]. IEEE Access, 2018, 6(1):17801-17816.
[16] Su T F, Zhang S W. Local and global evaluation for remote sensing image segmentation[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 130(1):256-276.
[17] Johnson B, Xie Z. Unsupervised image segmentation evaluation and refinement using a multi-scale approach[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2011, 66(1):473-483.
[18] Yang J, He Y, Weng Q. An automated method to parameterize segmentation scale by enhancing intrasegment homogeneity and intersegment heterogeneity[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(6):1282-1286.
[19] Troya-Galvis A, Gan?arski P, Passat N, et al. Unsupervised quantification of under- and over-segmentation for object-based remote sensing image analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 8(5):1936-1945.
[20] Su T F. Unsupervised evaluation-based region merging for high resolution remote sensing image segmentation[J]. GIScience & Remote Sensing, 2019, 56(6):811-842.
-
计量
- 文章访问数: 644
- PDF下载数: 80
- 施引文献: 0
下载: