A Convolutional Neural Network with Parallel Multi-Scale Spatial Pooling to Detect Temporal Changes in SAR Images

Abstract

In synthetic aperture radar (SAR) image change detection, it is quite challenging to exploit the changing information from the noisy difference image subject to the speckle. In this paper, we propose a multi-scale spatial pooling (MSSP) network to exploit the changed information from the noisy difference image. Being different from the traditional convolutional network with only mono-scale pooling kernels, in the proposed method, multi-scale pooling kernels are equipped in a convolutional network to exploit the spatial context information on changed regions from the difference image. Furthermore, to verify the generalization of the proposed method, we apply our proposed method to the cross-dataset bitemporal SAR image change detection, where the MSSP network (MSSP-Net) is trained on a dataset and then applied to an unknown testing dataset. We compare the proposed method with other state-of-arts and the comparisons are performed on four challenging datasets of bitemporal SAR images. Experimental results demonstrate that our proposed method obtain comparable results with S-PCA-Net on YR-A and YR-B dataset and outperforms other state-of-art methods, especially on the Sendai-A and Sendai-B datasets with more complex scenes. More important, MSSP-Net is more efficient than S-PCA-Net and convolutional neural networks (CNN) with less executing time in both training and testing phases.

Multiple Kernel Graph Cut for SAR Image Change Detection

“…In MKGC, the number of the samples in step 5.1 is defined by experience. It influences the initialization of the parametersσ in (17) and a in (5). As long as the samples are reliable, the pa-rameters computed are reliable, as well as the final results.…”

“…Change detection aims at identifying changes in images of the same scene taken at different times [1]. It is a vital branch of remote sensing image interpretation, and it is attracting a growing interest in civil and military applications, such as environment monitoring, disaster prevention and relief, urban study and so on [2][3][4][5]. Synthetic aperture radar (SAR) is insensitive to atmospheric and sun-illumination conditions, and it is an effective tool for change detection tasks.…”

An Efficient Lightweight Neural Network for Remote Sensing Image Change Detection

“…Several state-of-the-art deep learning-based CD methods were selected for comparison purposes. These methods were introduced in brief, including four pure fully convolutional network (FCN)-based methods (FC-Siam-Diff [26], FC-Siam-Conc [26], FC-EF-Res [35], and CLNet [29]), three attention-based methods (STANet [44], DDCNN [37], and FarSeg [58]), a transformer-based BIT-CD [48], and two light-weight networks (MSPP-Net [49] and Lite-CNN [50]). Specifically, the authors of STANet and BIT-CD are exactly the creators of LEVIR-CD dataset.…”

“…Recently, some lightweight change detection networks have been proposed. Chen et al [49] proposed a lightweight multiscale spatial pooling network to exploit the spatial context information on changed regions for bitemporal SAR image change detection. Wang et al [50] proposed a lightweight network that replaces normal convolutional layers with bottleneck layers and employs dilated convolutional kernels with a few non-zero entries that reduce the running time in convolutional operators.…”

Multispectral Image Change Detection Based on Single-Band Slow Feature Analysis

“…Supervised change detection methods are mainly developed from machine learning methods, which include SVM-based methods [24], random forest-based methods [25], and deep learning-based methods. With the development of deep learning methods, some techniques, such as dictionary learning [17], convolutional neural networks (CNNs) [26], and generative adversarial networks (GANs) [27], have been proven to be effective in detecting changes. It is acknowledged that deep learning methods can automatically extract abstract features of complex images, and it is more robust to noise and other disturbances than other methods.…”