Change Detection from SAR Images Based on Convolutional Neural Networks Guided by Saliency Enhancement

Abstract

Change detection is an important task in identifying land cover change in different periods. In synthetic aperture radar (SAR) images, the inherent speckle noise leads to false changed points, and this affects the performance of change detection. To improve the accuracy of change detection, a novel automatic SAR image change detection algorithm based on saliency detection and convolutional-wavelet neural networks is proposed. The log-ratio operator is adopted to generate the difference image, and the speckle reducing anisotropic diffusion is used to enhance the original multitemporal SAR images and the difference image. To reduce the influence of speckle noise, the salient area that probably belongs to the changed object is obtained from the difference image. The saliency analysis step can remove small noise regions by thresholding the saliency map, and interest regions can be preserved. Then an enhanced difference image is generated by combing the binarized saliency map and two input images. A hierarchical fuzzy c-means model is applied to the enhanced difference image to classify pixels into the changed, unchanged, and intermediate regions. The convolutional-wavelet neural networks are used to generate the final change map. Experimental results on five SAR data sets indicated the proposed approach provided good performance in change detection compared to state-of-the-art relative techniques, and the values of the metrics computed by the proposed method caused significant improvement.

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

“…Images of the same region taken at different times have different levels of speckle. Speckling creates difficulty in distinguishing opposite classes [ 22 ] since it increases the overlap of opposite-class pixels in the histogram of difference images. On the other hand, there is competitive interaction between altered regions and background regions due to a lack of past information, resulting in a fuzzy edge in the changed region that is difficult to discern.…”

Change detection using multispectral satellite images: a systematic review of literature

“…Prior knowledge of the scene will lead to best threshold level selection. The new DI is obtained from the original images by using the thresholding models [24]. The various existing methods using threshold-based CD.…”

“…The input images were taken from the Landsat dataset. Li et al [24] have presented a CNN-based CD from SAR images guided by saliency enhancement. By using SAR image accuracy of CD was improved.…”

“…Need to consider spatial information. Li et al [24] SAR image CD algorithm Enhanced the accuracy of the CD.…”

Synthetic Aperture Radar Image Change Detection Based on Principal Component Analysis and Two-Level Clustering

“…Remote sensing change detection is a method that compares various images or datasets collected from the same geographic area at different times to identify and analyze changes [1,2]. This approach is widely applied across numerous sectors, including environmental monitoring, urban planning, agriculture, and disaster management [3,4]. It plays a crucial role in understanding and responding to changes in our environment and infrastructure, providing valuable insights for decision-making and policy development.…”