An unsupervised multi-scale segmentation method based on automated parameterization

Chao, Wang; Xu, Wei; Pei, Xiaofang; Zhou, Xiaoyan

doi:10.1007/s12517-016-2683-4

Cited by 7 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Espindola et al [19] suggested the use of Global Moran's I Index (MI) to measure inter-segment spectral homogeneity and area-weighted segment variance (WV) to measure intra-segment heterogeneity. Since then, several other variants have been proposed [25,29,30]. In an ideal situation, both MI and WV should be minimized.…”

Section: Introductionmentioning

confidence: 99%

Normalization in Unsupervised Segmentation Parameter Optimization: A Solution Based on Local Regression Trend Analysis

et al. 2018

View full text Add to dashboard Cite

In object-based image analysis (OBIA), the appropriate parametrization of segmentation algorithms is crucial for obtaining satisfactory image classification results. One of the ways this can be done is by unsupervised segmentation parameter optimization (USPO). A popular USPO method does this through the optimization of a "global score" (GS), which minimizes intrasegment heterogeneity and maximizes intersegment heterogeneity. However, the calculated GS values are sensitive to the minimum and maximum ranges of the candidate segmentations. Previous research proposed the use of fixed minimum/maximum threshold values for the intrasegment/intersegment heterogeneity measures to deal with the sensitivity of user-defined ranges, but the performance of this approach has not been investigated in detail. In the context of a remote sensing very-high-resolution urban application, we show the limitations of the fixed threshold approach, both in a theoretical and applied manner, and instead propose a novel solution to identify the range of candidate segmentations using local regression trend analysis. We found that the proposed approach showed significant improvements over the use of fixed minimum/maximum values, is less subjective than user-defined threshold values and, thus, can be of merit for a fully automated procedure and big data applications.

show abstract

Section: Introductionmentioning

confidence: 99%

Normalization in Unsupervised Segmentation Parameter Optimization: A Solution Based on Local Regression Trend Analysis

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Image segmentation is the basis of OBIA, and it extracts the objects with geographical significance in the scene [2]. The quality of segmentation has a direct impact on the accuracy of subsequent image processing, such as classification and change detection [3].…”

Section: Introductionmentioning

confidence: 99%

A Novel Segmentation Method for High Resolution Urban Remote Sensing Image Based on Improved JSEG Algorithm

Gu¹,

Li²

2017

IJSIP

View full text Add to dashboard Cite

show abstract

Morphological characteristics and evolution model of slope units along loess gully cross section

Liu

Yang

et al. 2023

Front. Earth Sci.

View full text Add to dashboard Cite

An unsupervised multi-scale segmentation method based on automated parameterization

Cited by 7 publications

References 22 publications

Normalization in Unsupervised Segmentation Parameter Optimization: A Solution Based on Local Regression Trend Analysis

Normalization in Unsupervised Segmentation Parameter Optimization: A Solution Based on Local Regression Trend Analysis

A Novel Segmentation Method for High Resolution Urban Remote Sensing Image Based on Improved JSEG Algorithm

Morphological characteristics and evolution model of slope units along loess gully cross section

Contact Info

Product

Resources

About