相对于自然图像和多光谱图像,高光谱图像包含丰富的空间-光谱信息,不仅能够保留目标的空间信息,还能够获取高度可辨别的光谱信息。因此,如变化检测、目标追踪等高光谱图像处理技术在对地观测任务中得到了广泛应用,如自然灾害监测、农业调查、环境管理和国土安全等重要领域。然而,在高光谱图像变化检测的过程中仍然存在许多问题与挑战。如高光谱图像的高维复杂性、光谱差异性以及存在光谱混合等问题,影响变化检测效果。得益于深度学习理论的深入研究,高光谱图像变化检测技术研究得到了极大的发展,现有基于深度学习的变化检测方法可以大致分为两类,一类为基于时序依赖和空谱信息提取的方法,利用图像间的时序依赖性和关联性,获取更具辨别性的特征,增强变化检测性能；另一类为基于端元提取和解混的方法,通过端元提取与解混方法解决高光谱图像光谱混合的问题,提高变化检测精度。此外,面对来自无人机、卫星等不同传感器获取的高光谱图像数据,现有的方法基于图论学习异构图像的结构关系,并基于图像变换将其转换至公共域从而进行变化检测处理。本文从高光谱图像变化检测领域的新设计、新方法和应用场景出发,通过综合国内外前沿文献来梳理该领域的主要发展,重点论述高光谱图像变化检测领域的发展现状、前沿动态、热点问题及趋势。

Compared with natural images and multispectral images, hyperspectral images contain rich spatial-spectral information. They can not only retain the spatial information of the target, but also obtain highly distinguishable spectral information and provide more detailed target feature information. Therefore, hyperspectral images have become one of the most commonly used data types for earth observation and are widely used in important fields that actually affect human livelihoods, such as natural disaster monitoring, urban landscape mapping, agricultural surveys, environmental management, and homeland security. Change detection refers to the timely observation of land cover changes by analyzing images of the same geographical area and different phases. It is one of the important research directions in remote sensing image processing. With the increasing popularity and application of remote sensing technology, various remote sensing image processing technologies such as target detection and change detection have played an indispensable role in Earth observation tasks, such as natural disaster monitoring, agricultural surveys, environmental management, and homeland security. important areas. However, there are still many problems and challenges in the process of change detection in hyperspectral images. On the one hand, hyperspectral images have a large number of spectral bands, which leads to too high dimensions of data, easily causing dimensionality disaster; moreover, processing high-dimensional data requires a high degree of computing resources. Therefore, in real application scenarios, hyperspectral image change detection is difficult to achieve. Data processing and method design are often easily limited by device storage performance, computing performance, etc. On the other hand, hyperspectral images acquired at different time points may have differences in spectral response due to factors such as illumination and atmospheric conditions, and may have inconsistencies in resolution, spatial location, etc., thereby increasing the complexity of change detection. Spectral mixing is also one of the important challenges facing hyperspectral change detection. Pixels in hyperspectral data may contain a variety of ground object information, seriously interfering with the accuracy of change detection. In addition, with the rapid development of hyperspectral remote sensing technology, equipment such as drones and satellites continue to collect a large number of hyperspectral images for use in important fields such as disaster monitoring, mineral exploration, and homeland security. However, there are differences in the shooting angle, height and resolution of the sensors configured on different devices, and the acquired hyperspectral images also have differences in data structures. The existing isomorphism-based hyperspectral change detection methods cannot be directly applied to heterogeneous Hyperspectral image change detection task. Therefore, the problem of change detection in heterogeneous hyperspectral images from different types of sensors also brings new challenges to hyperspectral image change detection. Therefore, it is crucial to alleviate the highly complex data characteristics of hyperspectral images and design practical and effective processing solutions to improve the change detection effect. Among existing hyperspectral image change detection methods, traditional methods usually use manually designed methods for feature extraction, which may not be able to effectively extract discriminative features, and it is difficult to select appropriate thresholds to accurately detect land cover changes. Thanks to in-depth research on deep learning theory, research on hyperspectral image change detection technology has been greatly developed. Existing change detection methods based on deep learning can be roughly divided into two categories. One is based on temporal dependence and spatial spectrum information. The extraction method uses the temporal dependence and correlation between images to obtain more discriminative features and enhance the change detection performance; the other type is the method based on endmember extraction and unmixing, which is solved by the endmember extraction and unmixing method. Hyperspectral image spectral mixing problem to improve change detection accuracy. In addition, in the face of heterogeneous hyperspectral image data acquired from different sensors such as drones and satellites, existing methods learn the structural relationships of heterogeneous images based on graph theory, and convert them into the public domain based on image transformation to make changes. Detection and processing. Since there are certain temporal dependencies and correlations between multiple input images in the change detection task, how to effectively utilize the temporal dependencies and correlations between images and combine the existing deep learning module design to improve the hyperspectral image change detection effect is also a current issue. one of the research hotspots. This article starts from the new designs, new methods and application scenarios in the field of hyperspectral image change detection, and sorts out the main developments in this field by synthesizing domestic and foreign cutting-edge literature. First, it introduces the key pre-processing technologies for hyperspectral image change detection. Secondly, for the problem of isomorphic hyperspectral image change detection, traditional methods and deep learning-based methods for hyperspectral image change detection are introduced respectively, and each type of method is systematically introduced and compared according to the different implementation methods; for heterogeneous hyperspectral image change detection, Spectral image change detection problem, this paper introduces and summarizes the existing heterogeneous hyperspectral image change detection methods. Next, the current status of application of hyperspectral image change detection methods in real industrial practice is discussed. Finally, the current research and development status at home and abroad is compared and the development trend of hyperspectral image change detection is prospected.