Remote Sensing Image Change Detection Based on Information Transmission and Attention Mechanism

Abstract

Change detection is one of the core issues of earth observation and has been extensively studied in recent decades. This paper presents a novel deep neural network architecture based on information transmission and attention mechanism. Existing methods rely on a simple mechanism for independently encoding bi-temporal images to obtain their representation vectors. In view of the fact that these methods do not make full use of the rich information between bi-temporal images, we introduce the information transmission module in the design of DNN structure for doing the transmission and interaction of information. In addition, we introduce the attention mechanism behind the information transmission module to give the corresponding attention weight to each temporal image feature so as to enhance the change information of the image, which noticeably improves final prediction. The proposed network is validated on real remote sensing image data sets. Both visual and quantitative analyses of the experimental results demonstrate competitiveness of the proposed method.INDEX TERMS Remote sensing image, change detection, deep neural network, information transmission, attention mechanism.

Deep Learning for Change Detection in Remote Sensing Images: Comprehensive Review and Meta-Analysis

“…To explore the underlying information of the combined features, discrimination learning is then performed at the last step. Liu et al [25] have demonstrated the complementarity of CNNs and bidirectional long short-term memory network (BiLSTM) by combining them into one unified architecture. While, the former is useful in extracting the rich spectral-spatial features from bi-temporal images, the latter is powerful in analyzing the temporal dependence of bi-temporal images and transferring the features of images.…”

“…A positive label thus means that the area of that pixel has changed, while a null label represents an unchanged area (See Figs. 1 and 2) [25]. Actually, change detection represents a powerful tool for video surveillance, mapping urban areas, and other forms of multi-temporal analysis.…”

Change Detection Based on Artificial Intelligence: State-of-the-Art and Challenges

“…Specifically, the most commonly used types of multispectral images for AI-based change detection methods are derived from the Landsat series of satellites and the Sentinel series of satellites [66,67], due to their low acquisition cost and high time and space coverage. In addition, other satellites, such as Quickbird [68][69][70][71][72][73][74], SPOT series [75][76][77][78], Gaofen series [14,79,80], Worldview series [81][82][83][84][85], provide high and very high spatial resolution images, and various aircrafts provide very high spatial resolution aerial images [20,[86][87][88][89][90][91][92][93][94], allowing the change detection results to retain more details of the changes. HSIs have hundreds or even thousands of continuous and narrow bands, which can provide abundant spectral and spatial information.…”

“…The multi-model integrated framework is a hybrid structure, which is similar to the double stream structure, but it contains more types of AI models and can also be trained in multiple stages. Change detection is a spatiotemporal analysis and can be achieved by acquiring the spatial-spectral features through an AI-based feature extractor as a spectral-spatial module, and then modeling temporal dependency through an AI-based classifier as a temporal module [14,38,53,74]. Moreover, this hybrid structure is skillfully used for unsupervised change detection [100] and object-level change detection [87].…”

“…A long short-term memory (LSTM) network, a special RNN that alleviates the problem of gradient disappearance and gradient explosion during long sequence training, has been employed as a temporal module (see Section 4.3) in change detection tasks [14,38,53,64,74]. In [51], the authors used an improved LSTM network to acquire and record the change information of multi-temporal RS data.…”