Change Detection in Synthetic Aperture Radar Images Based on a Generalized Gamma Deep Belief Networks

Abstract

Change detection from synthetic aperture radar (SAR) images is of great significance for natural environmental protection and human societal activity, which can be regarded as the process of assigning a class label (changed or unchanged) to each of the image pixels. This paper presents a novel classification technique to address the SAR change-detection task that employs a generalized Gamma deep belief network (gΓ-DBN) to learn features from difference images. We aim to develop a robust change detection method that can adapt to different types of scenarios for bitemporal co-registered Yellow River SAR image data set. This data set characterized by different looks, which means that the two images are affected by different levels of speckle. Widely used probability distributions offer limited accuracy for describing the opposite class pixels of difference images, making change detection entail greater difficulties. To address the issue, first, a gΓ-DBN can be constructed to extract the hierarchical features from raw data and fit the distribution of the difference images by means of a generalized Gamma distribution. Next, we propose learning the stacked spatial and temporal information extracted from various difference images by the gΓ-DBN. Consequently, a joint high-level representation can be effectively learned for the final change map. The visual and quantitative analysis results obtained on the Yellow River SAR image data set demonstrate the effectiveness and robustness of the proposed method.

Comparative Analyses of Unsupervised PCA K-Means Change Detection Algorithm from the Viewpoint of Follow-Up Plan

“…In addition, PCAKM has a higher KC than MRFFCM and GaborTLC for two out of three data. Gamma deep belief network (g -DBN) is proposed by Jia and Zhao [ 12 ] for comparison with PCAKM, convolutional-wavelet neural network (CWNN), deep belief network (DBN), and joint deep belief network (JDBN). According to their experimental results, PCAKM shows better performance than CWNN and DBN for one of the benchmark datasets in terms of KC.…”

“…Considering its features such as being fast, not requiring learning data, and having a simple algorithm, we selected PCAKM as a benchmark method. It shows promising results for both unsupervised [ 13 , 18 , 20 ] and supervised methods [ 12 , 21 ].…”

“…These images typically form the function for actions such as those listed above. Speckle noise [ 10 , 11 , 12 ], fuzzy edge of changed regions [ 12 ], and limited datasets [ 12 ] are the main challenges for the change detection of SAR images.…”

A Semi-Supervised Deep Learning Framework for Change Detection in Open-Pit Mines Using SAR Imagery

“…Wang [27] proposed a deformable residual convolutional neural network (DRNet), which address the limitations of fixed sampling locations in traditional CNNs and the need for stronger multi-scale representation. Jia [28] presented a generalized Gamma deep belief network to address SAR change detection. By extracting hierarchical features and fitting the distribution of difference images, the model learns joint high-level representations for accurate change mapping.…”