ABSTRACT

With the rapid development of remote sensing technologies, the frequency of observations of the same location is increasing, and many satellites and sensors produced a large amount of time series images. These images make long-term change detection and dynamic characteristic estimation of ground features possible. However, conventional remote sensing image change detection methods mostly rely on manual visual interpretation and supervised or unsupervised computer-aided classification. Traditional methods always face many bottlenecks when processing big and fast-growing datasets, such as low computational efficiency, low level of automation, and different identification standards and accuracies caused by different operators. With the rapid accumulation of remote sensing data, it has become an important but more challenging task to conduct change detection in a more precise, automated and standardized way. The development of geointelligent computing technologies provides a means of solving these problems and improve the accuracy and efficiency of remote sensing image change detection. In this paper, we presented a novel deep learning model called nest network(NestNet) based on a convolutional neural network to improve the accuracy of the automatic change detection task by using remotely sensed time series images. NestNet extracts the respective features of bi-temporal images using an encoding parallel module and subsequently employs absolute different operations to process the features of two images. Compared with change detection method based on U-Shaped network plus plus (UNet++), the parallel module improves the efficiency of NestNet. Finally, a decoding module is used to generate a predicted change image. This paper compares NestNet to traditional methods and state-of-the-art deep learning models on two datasets. The experimental results demonstrate that the accuracy of NestNet is better than that of state-of-the-art methods. It can be concluded that the NestNet model is a potential approach for change detection using high resolution remote sensing images.

摘要

随着遥感技术的飞速发展，同一地点的观测频率在增加，许多卫星和传感器产生了大量的时间序列图像。这些图像使长期变化检测和地面特征的动态特征估计成为可能。然而，常规的遥感图像变化检测方法主要依靠人工视觉解释以及有监督或无监督的计算机辅助分类。传统方法在处理庞大且快速增长的数据集时始终面临许多瓶颈，例如计算效率低，自动化程度低以及由不同运算符引起的不同识别标准和准确性。随着遥感数据的迅速积累，以更精确，自动化和标准化的方式进行变更检测已经成为一项重要但更具挑战性的任务。地理智能计算技术的发展提供了解决这些问题的方法，并提高了遥感图像变化检测的准确性和效率。在本文中，我们提出了一种基于卷积神经网络的称为嵌套网络（NestNet）的新型深度学习模型，以通过使用遥感时间序列图像提高自动变化检测任务的准确性。NestNet使用编码并行模块提取双时相图像的各个特征，然后采用绝对不同的操作来处理两个图像的特征。与基于U形网络plus plus（UNet ++）的更改检测方法相比，并行模块提高了NestNet的效率。最后，解码模块用于生成预测的变化图像。本文将NestNet与传统方法和两个数据集上的最新深度学习模型进行了比较。实验结果表明，NestNet的准确性优于最新方法。可以得出结论，NestNet模型是使用高分辨率遥感影像进行变化检测的潜在方法。