A Light-Weighted Convolutional Neural Network for Bitemporal SAR Image Change Detection

Over past decades, much attentions focus on multitemporal Synthetic Aperture Radar (SAR) image change detection, since a SAR is capable of working in all-time and all-weather without the influence of extremely bad weather and the cloud. In a past decade, most traditional SAR image change detection methods are developed how to extract changed areas from a difference image (DI), which suppose to include the information of changed regions. The DI calculated by the log-ratio (LR) [1] is usually subject to the speckle and it is challenging to extract the accurate and clear information on the changed region. To tackle this issue, sparse learning[2] was recently proposed learning robust features from the noisy DI. Wang et al.[3] analyzed the affects of the SAR image speckle on change detection and proposed a sparse learning-based method for SAR image change detection.

Recently, deep neural networks have been successfully employed to computer vision and remote sensing image analysis due to its ability to exploiting essential and robust structural features on categories of objects. It also has been introduced into the field of change detection. Gong et al[4] proposed a deep neural network for SAR image change detection. Gao et al. [5] proposed a simple convolutional neural network, known as PCA-Net, exploring robust features on the changed regions from the noisy DI. However, the performance of these two unsupervised methods are limited without the correct guidance. To tackle this issue, Wang et al. [6] proposed a supervised PCA-Net to improve the performance by carefully collecting typical training samples, which obtains state-of-arts performance of bitemporal SAR image change detection. However, this two-layer convolutional neural network is low efficient, since the convolutional kernels are trained or generated by a Principle Component Analysis (PCA) decomposition. Recently, Li et al. [7] proposed a convolutional neural network (CNN) for SAR image change detection based on both unsupervised and supervised learning. Zhao et al. [8] proposed a bitemporal PolSAR image change detection by a joint classification and a similarity measurement. Currently, it is still an open problem to extract the changed regions from the noisy DI. Nowadays, a large volume of SAR images are acquired by satellites and it is imperative to develop an efficient model that can produce promising results of SAR image interpretation. Most above networks are too heavy and cost much computational burden. It is strongly required to develop a lightweight convolutional neural network.

Recently, several lite networks are proposed to improve the inference efficiency. Howard et al. and Sandler et al. proposed two lite networks MobileNetV1 [9] and MobileNetV2 [10] for visual category. Recently, Howard et al. proposed to search for MobileNetV3 [11]. Tan et al. [12] proposed an efficient network for visual category. These lite networks have been extensively employed to visual category and the experimental results show that they can achieve comparable performance with heavy networks, but with low latency and network capacity. It can be potentially performed on edge devices with low power. Most recently, Chen et al.[13] proposed a lightweight multiscale spatial pooling network for bitemporal SAR image change detection.

Following the idea of the lightweight neural network, in this letter, we focus on the application of lite networks in SAR image change detection. To achieve this, we propose a lite CNN for SAR image change detection. In the proposed network, bottleneck layers are introduced to reduce the number of output channel. Furthermore, the dilated convolutional layers[14] are introduced to enlarge receptive field with a few of non-zero entries in the kernel, which reduces the number of network parameters. We verify the proposed network by comparing other conventional CNN. Compared with the lightweight network in [13], the proposed network is more robust with the residual and bottleneck structure. Experimental results on four sets of bitemporal SAR image show that our proposed method obtain comparable performance with CNN, while being much more efficient than CNNs.

The rest of paper will be organized as follows. We will introduce our proposed method in Section 2. Then the proposed method will be verified on four datasets in Section 3. Finally, we will draw a conclusion in Section 4.

Given bitemporal SAR images ${\bf I}_{1}$ and ${\bf I}_{2}$, the DI can be generated as follows

where $\ominus$ denote the difference operator. However, most existing difference operator is subject to the speckle. Then we will propose a lightweight convolutional neural network to exploit the changed regions from the noisy DI.

The whole framework of the proposed network can illustrated in Fig.1(a). It is shown that the network consists of five groups of bottleneck layers [15] with an 1$\times$1 kernels, illustrated by variety of colorful bars, among which the former three ones work as the encoder, and the latter two ones as the decoder. The tensors of all layers are listed in Table 1.

In the forward process, the network takes a patch of DI as the input. Firstly, the input data go through a normal convolutional layer and a max-pooling (MP) layer, respectively and then the outputs are concatenated. Next, the contact activations go through the decoder with three groups bottleneck layers. The essential structure of a bottleneck of encoder can be illustrated in Fig.1(b). It is shown that a bottleneck layer is constructed by a small residual block, including a maxpooling path and a convolutional path. More specifically, the convolutional path consists of two 1$\times$1 convolutions and one main convolution. The main convolution will vary with the various function of the bottleneck. It can be a normal convolution, a dilated convolution [14] or an asymmetrical convolution[16]. The tensors inside the encoding bottleneck are listed in Table 2.

The first group consist a down-sampling bottleneck and four normal convolutional bottleneck layers. In the normal bottleneck layers, the main convolution component is default set as the main normal convolutional layer. Especially, in the down-sampling bottleneck, the main convolutional component is set as a normal convolution kernel with 3$\times$3 and the 1$\times$1 convolution component is replaced by a 2$\times$2 one. In the next two groups, to exploit the spatial context, we insert the bottleneck layers with asymmetrical and dilated convolution layers with various kernel sizes among the normal bottleneck, where the kernel sizes are set 2, 4, 8 and 16, respectively, as shown the digits below the green bars. In these bottleneck layers, the main convolutional layers are replaced by the dilated convolutional layers, where the kernels are sparse and most entries are zeros. Furthermore, the bottleneck layers with asymmetric convolution layers are also insert between the dilated and normal convolutional layer, illustrated by the blue bars. After encoding, the sizes of feature maps decrease as the one fourth as the original image.

In the decoding part, the context information collected by the encoder will be propagated to the pixel level. To achieve this, inspired by the idea of U-Net [17], we schedule a upsampling layer and two bottleneck layers. The essential structure of bottleneck for decoder can be illustrated in Fig.1(c). Similar to the bottleneck for the encoder, the bottleneck for the decoder contains a pooling path and a convolution path. The former includes a maxpooling layer and a 1$\times$1 convolution, while the latter includes two 1$\times$1 convolutional layers and a 3$\times$3 convolutional layer. Especially, when the bottleneck layer is used for upsampling, the 3$\times$3 convolution component, illustrated by the yellow bar, will be replaced by a 3$\times$3 transpose convolution [18]. Then the bottleneck will do the 2x upsampling. Trough two groups of decoding bottleneck layers, the feature map will be recover the same size as the input image. The tensors inside the decoding bottleneck are listed in Table 3. Finally, we put a 2$\times$2 convolutional layer to get the probability map of two categories.

In this paper, we develop a lightweight convolutional neural network for bitemporal SAR image change detection. The proposed network consists of groups of bottlenecks layers which exploit the image feature. To verify the benefits of our proposed method, we compare it with several traditional neural networks and the comparisons are performed on fours sets of bitemporal SAR images. The experimental results show that our proposed method Lite CNN performs better than other two methods on cross-dataset change detection, especially when the scene is complex. Furthermore, Lite CNN is a lightweight network, which is more computationally efficient than CNN and S-PCA-Net. In the future, we will further optimize Lite CNN and make it more efficient on the edge device.

This work was supported by the State Key Program of National Natural Science of China (No. 61836009), the National Natural Science Foundation of China (No. 61701361, 61806154), the Major Research Plan of National Natural Science Foundation of China (No. 91838303), the Open Fund of Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University (Grant No. IPIU2019006), the Natural Science Basic Research Plan in Shaanxi Province of China (No.2018JM6083) and the Open Fund of State Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University (No. 17E02).