Change Analysis in Urban Areas Based on Statistical Features and Temporal Clustering Using TerraSAR-X Time-Series Images

Abstract

The existing unsupervised multitemporal change detection approaches for synthetic aperture radar (SAR) images based on the pixel level usually suffer from the serious influence of speckle noise, and the classification accuracy of temporal change patterns is liable to be affected by the generation method of similarity matrices and the pre-specified cluster number. To address these issues, a novel time-series change detection method with high efficiency is proposed in this paper. Firstly, spatial feature extraction using local statistical information on patches is conducted to reduce the noise and for subsequent temporal grouping. Secondly, a density-based clustering method is adopted to categorize the pixel series in the temporal dimension, in view of its efficiency and robustness. Change detection and classification results are then obtained by a fast differential strategy in the final step. The experimental results and analysis of synthetic and realistic time-series SAR images acquired by TerraSAR-X in urban areas demonstrate the effectiveness of the proposed method, which outperforms other approaches in terms of both qualitative results and quantitative indices of macro F1-scores and micro F1-scores. Furthermore, we make the case that more temporal change information for buildings can be obtained, which includes when the first and last detected change occurred and the frequency of changes.

A Survey of Change Detection Methods Based on Remote Sensing Images for Multi-Source and Multi-Objective Scenarios

“…However, instead of optimizing the initial centers, many scholars pursue the self-adaption capability. For example, the density-based algorithms [109], which are independent of the initial setting by density adaptation (i.e., Density-Based Spatial Clustering of Applications with Noise (DBSCAN) [110]); the hierarchical clustering algorithms [111,112], which merge clusters with the same criteria level-by-level. Furthermore, in addition to the feature itself, other dimensions also have the possibility for clustering.…”

Unsupervised Multitemporal Building Change Detection Framework Based on Cosegmentation Using Time-Series SAR

“…Change detection is a process of automatically analyzing and identifying the variation of Earth's surface objects based on multitemporal remote sensing images acquired in the same region at different times [1,2]. As a significant application of remote sensing image, change detection analysis provides an effective technological significance for land use and land cover monitoring [3,4], urban planning and management [5,6], natural disaster assessment and monitoring [7][8][9], etc.…”

“…However, in multi-temporal change detection, DL methods are infrequent due to the large difficulty of acquiring high-quality labels. For example, Su et al [10] and Yuan et al [2] used traditional methods to classify change behavior into four types: step change, impulse change, cycle change, and complex change. These labeling tasks are difficult for a human.…”

“…The second approach compares each pair of adjacent images, and the first approach, which we mainly focus on, compares pixels at all times in the same position. Yuan et al [2] applied the density-based temporal clustering method to extract change classification. Su et al [10] presented a likelihood ratio test based method of change detection and classification for SAR time series.…”

K-Matrix: A Novel Change-Pattern Mining Method for SAR Image Time Series

“…Direct conversion of SAR image time series into time series is another effective analysis method [27]. That is to say that each time series is constructed by extracting the feature of pixel at the same spatial position over all SAR images.…”