Recently, supervised deep learning has achieved a great success in remote sensing image (RSI) semantic segmentation. However, supervised learning for semantic segmentation requires a large number of labeled samples, which is difficult to obtain in the field of remote sensing. A new learning paradigm, self-supervised learning (SSL), can be used to solve such problems by pretraining a general model with a large number of unlabeled images and then fine-tuning it on a downstream task with very few labeled samples. Contrastive learning is a typical method of SSL that can learn general invariant features. However, most existing contrastive learning methods are designed for classification tasks to obtain an image-level representation, which may be suboptimal for semantic segmentation tasks requiring pixel-level discrimination. Therefore, we propose a global style and local matching contrastive learning network (GLCNet) for RSI semantic segmentation. Specifically, first, the global style contrastive learning module is used to better learn an image-level representation, as we consider that style features can better represent the overall image features. Next, the local features matching the contrastive learning module is designed to learn the representations of local regions, which is beneficial for semantic segmentation. We evaluate four RSI semantic segmentation datasets, and the experimental results show that our method mostly outperforms the state-of-the-art self-supervised methods and the ImageNet pretraining method. Specifically, with 1% annotation from the original dataset, our approach improves Kappa by 6% on the International Society for Photogrammetry and Remote Sensing (ISPRS) Potsdam dataset relative to the existing baseline. Moreover, our method outperforms supervised learning methods when there are some differences between the datasets of upstream tasks and downstream tasks. Our study promotes the development of SSL in the field of RSI semantic segmentation. Since SSL could directly learn the essential characteristics of data from unlabeled data, which is easy to obtain in the remote sensing field, this may be of great significance for tasks such as global mapping. The source code is available at https://github.com/GeoX-Lab/G-RSIM .

Are we on the right way for remote sensing image understanding (RSIU) by training models in a supervised data-dependent and task-dependent manner, instead of original human vision in a label-free and task-independent way? We argue that a more desirable RSIU model should be trained with intrinsic structure from data rather than extrinsic human labels to realize generalizability across a wide range of RSIU tasks. According to this hypothesis, we proposed T he O riginal V ision model (TOV) in the remote sensing field. Trained by massive unlabeled optical data along a human-like self-supervised learning (SSL) path that is from general knowledge to specialized knowledge, TOV model can be easily adapted to various RSIU tasks, including scene classification, object detection, and semantic segmentation, and outperforms dominant ImageNet supervised pre-trained method as well as two recently proposed SSL pre-trained methods on the majority of 12 publicly available benchmarks. Moreover, we analyze the influences of two key factors on the performance of building TOV model for RSIU, including the influence of using different data sampling methods and the selection of learning paths during self-supervised optimization. We believe that a general model which is trained in a label-free and task-independent way may be the next paradigm for RSIU and hope the insights distilled from this study can help to foster the development of an original vision model for RSIU.

A low Earth orbiter (LEO)-based navigation signal augmentation system is considered as a complementary of current global navigation satellite systems (GNSS), which can accelerate precise positioning convergence, strengthen the signal power, and improve signal quality. Wuhan University is dedicated to LEO-based navigation signal augmentation research and launched one scientific experimental satellite named Luojia-1A. The satellite is capable of broadcasting dual-frequency band ranging signals over China. The initial performance of the Luojia-1A satellite navigation augmentation system is assessed in this study. The ground tests indicate that the phase noise of the oscillator is sufficiently low to support the intended applications. The field ranging tests achieve 2.6 m and 0.013 m ranging precision for the pseudorange and carrier phase measurements, respectively. The in-orbit test shows that the internal precision of the ephemeris is approximate 0.1 m and the clock stability is 3 × 10⁻¹⁰. The pseudorange and carrier phase measurement noise evaluated from the geometry-free combination is about 3.3 m and 1.8 cm. Overall, the Luojia-1A navigation augmentation system is capable of providing useable LEO navigation augmentation signals with the empirical user equivalent ranging error (UERE) no worse than 3.6 m, which can be integrated with existing GNSS to improve the real-time navigation performance.

Through the use of video technology, satellites can detect dynamic targets and analyze their motion characteristics. Target tracking can extract dynamic information about key ground targets for target monitoring and trajectory prediction by satellite video. Tracking algorithms are affected by target motion characteristics, such as velocity and direction, as well as background characteristics, such as illumination changes, occlusion, and background similarities with the target. However, these problems are seldom studied with satellite video cameras. Current algorithms are unsuitable for satellite video because of the poor texture and color features of the target in satellite video. Therefore, in this article, we enhance target tracking for satellite video technology using two aspects: 1) sample training strategy and 2) sample characterization. We establish a filter training mechanism for the target and background to improve the discrimination ability of the tracking algorithm. We then build a target feature model using a Gabor filter to enhance the contrast between the target and background. Moreover, we propose a tracking state evaluation index to avoid tracking drift. Tracking experiments using nine sets of Jilin-1 satellite videos show that the proposed approach can accurately locate a target under weak feature attributes. Therefore, this article contributes to more robust tracking using satellite video technology.

The LJ1-01 satellite is the first dedicated nighttime light remote sensing satellite in the world and offers a higher spatial resolution than the Defense Meteorological Satellite Program’s Operational Linescan System (DMSP/OLS) and the Visible Infrared Imaging Radiometer Suite (VIIRS) sensor on the Suomi National Polar-orbiting Partnership (NPP) satellites of the United States. This study compared the LJ1-01 nighttime light data with NPP/VIIRS data in the context of modeling socio-economic parameters. In the eastern and central regions of China, 10 parameters from the four aspects of gross regional product (annual average population, electricity consumption, and area of land in use) were selected to build linear regression models. The results showed that the LJ1-01 nighttime light data offered better potential for modeling socio-economic parameters than the equivalent NPP/VIIRS data; the former can be an effective tool for establishing models for socio-economic parameters. There were significant positive correlations between the two types of nighttime light data and the 10 socio-economic parameters; that for the gross regional product was the highest.