Guest Editorial: Special issue on intelligence technology for remote sensing image

Abstract

With the development of artificial intelligence, remote sensing scene interpretation task has attracted extensive attention, which mainly includes scene classification, target detection, hyperspectral classification, and multi-modal analysis. The remote sensing scene interpretation has effectively promoted the development of the Earth observation field. It was the intention for this Special Issue to serve as a platform for the publication of the most recent research concepts from remote sensing image.

To recognise remote sensing scenes, several methods have been proposed to represent the scene image. The first paper (Zhang et al.) proposes a lightweight privacy-preserving recognition framework which diffuses the error between the encryption block and the original block to adjacent blocks which makes the transmission of high-resolution images more secure and efficient. The second paper (Ning et al.) introduces a knowledge distillation network for aerial scene recognition, which produces consistent predictions by distilling the predictive distribution between different scales. With the development of scene recognition task, its branch scene retrieval task also emerges. In this regard, the third paper (Yuan et al.) shows how to efficiently optimise the average accuracy to improve remote sensing image retrieval. This approach enables a more flexible optimisation strategy by involving positive post-samples, which provides a new way to improve the retrieval performance.

To detect targets, a series of advanced methods have been developed to improve detection accuracy and efficiency. The fourth paper (Zhang et al.) proposes an intelligent anchor learning strategy for arbitrary orientation target detection. The fifth paper (Ma et al.) focuses on infrared image detection of small and weak targets and proposes an efficient deep learning method. The sixth paper (Zhou et al.) proposes a convolutional transformer method based on spectral-spatial sequence features for hyperspectral image change detection. With the maturity of target detection techniques, researchers have begun to focus on more complex challenges, namely anomaly detection. In this subfield, the seventh paper (Wang et al.) provides a new solution for semi-supervised hyperspectral anomaly detection. It maps the raw spectrum into the fractional Fourier domain, thereby enhancing the distinguishability between background and anomaly. Meanwhile, the eighth paper (Zhao et al.) utilises a memory-enhanced self-encoder to improve the separation of anomaly samples from background in hyperspectral images. These studies demonstrate the rapid development in the target detection field, such as change detection and anomaly detection.

To classify hyperspectral images, the ninth paper (Liao et al.) shows how to integrate the features of convolutional neural networks and transformers to enhance the performance of hyperspectral image classification. This approach fully utilises the respective advantages of convolutional networks and transformers to provide a comprehensive solution for feature extraction of hyperspectral images. Furthermore, the tenth paper (Xie et al.) employs a transformer network that fuses semantic, spatial, and spectral features to show how the combination of multiple information types can improve the accuracy and robustness of classification. Meanwhile, the eleventh paper (Ran et al.) combines deep transformer modelling with small-sample learning to tackle the challenges in hyperspectral image classification, especially when the number of samples is limited. This approach effectively improves the generalisation ability of the classification model by making full use of the information in a small number of samples.

The multi-modal analysis provides increased capabilities for observing the Earth's surface and handling the challenging issues. The twelfth paper (Hong et al.) utilises multispectral remote sensing data and geographically weighted regression experiments to reveal the importance of green infrastructure layout for mitigating the urban heat island effect. The thirteenth paper (Zhang et al.) introduces a multi-task framework for precipitation prediction. It combines radar echo images and other auxiliary tasks, which improved the accuracy and efficiency of precipitation forecasting. Finally, the fourteenth paper (Zhang et al.) improves robot self-localisation and environment perception in dynamic environments by fusing visual and audio data. This fusion approach demonstrates excellent stability and reconstruction performance in a multi-robot collaborative scenario. These studies demonstrate the potential of multi-source data analytics in improving areas, such as environmental monitoring, prediction, and robot navigation.

We appreciate all the authors for their submissions and all the reviewers for their valuable reviews and comments. We hope that this Special Issue will inspire new outcomes for the research community in remote sensing scene interpretation.

National Natural Science Foundation of China, Grant/Award Number: 62271484.