Double-Variance Measures: A Potential Approach to Parameter Optimization of Remote Sensing Image Segmentation

Abstract

The unsupervised segmentation evaluation (USE) method has been commonly used for remote-sensing segmentation parameter (SP) determinations to produce good segmentation results, due to its objectiveness and high efficiency. Existing studies have used different criteria to measure homogeneity and heterogeneity and have used certain combination strategies to form overall evaluations. However, different criteria have unique statistical characteristics. The differentiated statistical characteristics maintained in homogeneity and heterogeneity calculations may result in inherent instability in the USE results, leading to unsuitable SP selections. Moreover, few studies have focused on the simultaneous determination of a single optimal SP and multiple optimal SPs. In this paper, double-variance (DV) measures were proposed for recognizing more suitable SPs. Then, two combination strategies, F-measure and local peak (LP), were applied to test the potential of using double-variance measures to determine a single SP and multiple SPs, respectively. The multiresolution segmentation (MRS) algorithm and Gaofen-1 data were used to test the proposed method. The comparative results indicated that the DV is a more promising internal homogeneity and external heterogeneity metric for segmentation evaluation and optimal SP determination compared to conventional methods. The F-measure-based DV method could produce better overall goodness of segmentation for differently sized natural geo-objects, compared with the competing methods. The LP-based DV method could obtain multiple optimal scales that produced better segments for the identification of small, natural geo-objects to large, semantic geo-objects, compared to the competitive methods.

Agglutination Multivariate Optimal Spanning SOLOv3 Algorithm: Novel Augment-Based Approach for Early-Stage Brain Tumor Image Segmentation

“…Previous studies show segmentation is the most critical and essential factor for tumor analysis [40][41][42][43][44][45][46][47][48][49][50]. The analysis depends on the performance of the segmentation technique which was used for the work.…”

Local Scale-Guided Hierarchical Region Merging and Further Over- and Under-Segmentation Processing for Hybrid Remote Sensing Image Segmentation

“…To further improve the segmentation quality, the over-and under-segmented regions need to be identified and then further processed. Most methods only evaluate the over-and under-segmentation in a global manner [17,[50][51][52][53]. In other words, these methods can indicate segmentation quality but not be helpful for further improving the segmentation results.…”