Multiresolution-Based Rough Fuzzy Possibilistic C-Means Clustering Method for Land Cover Change Detection

Abstract

Object-oriented change detection (OOCD) plays an important role in remote sensing change detection. Generally, most of current OOCD methods adopt the highest predicted probability to determine whether objects have changes. However, it ignores the fact that only parts of an object have changes, which will generate the uncertain classification information. To reduce the classification uncertainty, an improved rough-fuzzy possibilistic c-means clustering algorithm combined with multiresolution scales information (MRFPCM) is proposed. Firstly, stacked bitemporal images are segmented using the multiresolution segmentation approach from coarse to fine scale. Secondly, objects at the coarsest scale are classified into changed, unchanged and uncertain categories by the proposed MRFPCM. Thirdly, all the changed and unchanged objects in previous scales are combined as training samples to classify the uncertain objects into new changed, unchanged and uncertain objects. Finally, segmented objects are classified layer by layer based on the MRFPCM until there are no uncertain objects. The MRFPCM method is validated on three data sets with different land change complexity and compared with five widely used change detection methods. The experimental results demonstrate the effectiveness and stability of the proposed approach.

Performance Comparison of Dimensional Reduction using Principal Component Analysis with Alternating Least Squares in Modified Fuzzy Possibilistic C-Means and Fuzzy Possibilistic C-Means

“…Previous research used FPCM to carry out multi-resolution segmentation of stacked images into objects from coarse to scale. Experimental results demonstrate the effectiveness and stability of the proposed approach [11]. FPCM is also used to investigate data in the real world, namely to break down extensive data sets into meaningful clusters.…”

The Use of Artificial Intelligence and Satellite Remote Sensing in Land Cover Change Detection: Review and Perspectives

“…To reduce this uncertainty, Tong Xiao proposed an improved Rough Fuzzy Possibilistic C-Means Clustering Method (MRFPCM) that combines multi-resolution scale information. MRFPCM classifies the segmented objects layer by layer until there are no uncertain objects left [135].…”

Improving Unsupervised Object-Based Change Detection via Hierarchical Multi-Scale Binary Partition Tree Segmentation: A Case Study in the Yellow River Source Region

“…While single-scale approaches are conceptually simple, they struggle with objects of diverse sizes and shapes. Multi-scale methods hold promise in addressing this limitation, but they encounter their own hurdles-namely, automatic threshold determination and handling complex ground objects with intricate features [11][12][13]. Hierarchical multi-scale methods, despite employing local adaptive scale parameters [14,15], are inherently limited by single-phase imagery and neglect the heterogeneity arising from variations in multi-temporal variations.…”

“…Deep learning has emerged as a potent tool for change detection in high-resolution imagery. Supervised methods, while showcasing great effectiveness, heavily rely on extensive training datasets, limiting their adaptability to diverse scenarios [13,28,29]. Unsupervised approaches utilizing pre-classification schema, on the other hand, encounter challenges in large-scale tasks due to their significant computational demands [30,31].…”