Personnel and boat detection in unmanned aerial vehicles (UAVs) imagery plays a crucial role in open water search and rescue missions. The diverse perspectives and altitudes of UAV images often result in significant variations in the imagery’s appearance and dimensions of personnel and boats, and the false detections arising from water surface flares are acknowledged as a great challenge as well. The existing deep learning-based detection methods employ convolutional blocks with fixed kernel sizes to extract features from the imagery at a fixed spatial scale, which will lead to missed and false detections and severely affect detection accuracy when there are substantial differences in the appearance and size of the target objects. In this article, a spatial scale adaptive real-time object detection neural network, namely YoloOW, was proposed to tackle the challenge of personnel and boat detection amid the diverse UAV imagery, which comprises a feature extractor, a feature enhancer, and a postprocessor. The OaohRep convolutional block was proposed as a pivotal component in constructing the YoloOW and applied to the feature extractor and the feature enhancer. Compared with general convolution blocks, the OaohRep convolution block can extract image features across a wide range of spatial scales, show better scale adaptability, and achieve faster detection speed due to its unique merged convolution layer design. OaohRepBi-path aggregation network (PAN) was proposed in the feature enhancer, which imitated the architecture of the classic algorithm scale invariant feature transform (SIFT) and was successfully applied to deep learning models, showing better scale adaptability. A novel UAV detection box filter (UDBF) module was proposed in the postprocessor, which can effectively remove false detections caused by water surface flares. Experimental results demonstrate that our YoloOW model achieves 37.18% mean averaged precision (mAP) on the SeaDronesSee dataset, surpassing the baseline by 8.43%. This notable improvement positions our model at the first of the leaderboard. The code will be available at https://github.com/Xjh-UCAS/YoloOW .

Mass remote sensing data management and processing is currently one of the most important topics. In this study, we introduce ScienceEarth, a cluster-based data processing framework. The aim of ScienceEarth is to store, manage, and process large-scale remote sensing data in a cloud-based cluster-computing environment. The platform consists of the following three main parts: ScienceGeoData, ScienceGeoIndex, and ScienceGeoSpark. ScienceGeoData stores and manages remote sensing data. ScienceGeoIndex is an index and query system, a spatial index based on quad-tree and Hilbert curve which is combined for heterogeneous tiled remote sensing data that makes efficient data retrieval in ScienceGeoData. ScienceGeoSpark is an easy-to-use computing framework in which we use Apache Spark as the analytics engine for big remote sensing data processing. The result of tests proves that ScienceEarth can efficiently store, retrieve, and process remote sensing data. The results reveal ScienceEarth has the potential and capabilities of efficient big remote sensing data processing.

Spatiotemporal data fusion provides an efficacious strategy for addressing data gaps within time series datasets. This approach significantly enhances the feasibility of large-scale remote sensing applications by, for example, enabling the creation of seamless data cubes (SDCs). Nevertheless, strict data input requirements and the low computational efficiency of current methods severely limit the practicality of large-scale SDC production. In this study, we propose an efficient spatiotemporal data fusion method, the Fast Variation-based Spatiotemporal Data Fusion (FastVSDF) method. FastVSDF consists of three steps, i.e., unmixing, distributing global residuals, and distributing local residuals. In the unmixing process, FastVSDF introduces the fast abundant variation classification (FAVC) to mitigate sample imbalance and expedite the unsupervised classification. Then, the in-class Gaussian weight function is introduced to accelerate the distribution of local residuals by considering the classification to introduce the information on spectral similarity. Besides, FastVSDF employs the fast-guided filter to combat the “block artifacts” of global residuals efficiently. Results show that FastVSDF demonstrated superior performance over regression model fitting, spatial filtering and residual compensation (Fit-FC), spatial and temporal adaptive reflectance fusion (STARFM), reliable and adaptive spatiotemporal data fusion (RASDF), and flexible spatiotemporal data fusion (FSDAF). More importantly, FastVSDF yields a remarkable improvement in computational efficiency, reducing predicting time by 43–573 times. As a practical application, we generated the Sentinel-2 SDC for the Yangtze River Basin, China. The fusion process for a single period’s Yangtze River Basin dataset was accomplished within 20 min, with an average of 3.85 s for each Sentinel-2 scene. Comprehensively considering the efficiency, accuracy, feasibility, and universality, FastVSDF demonstrates the practical potential for constructing large-scale and long-term SDC. Our code will be publicly available at https://github.com/ChenXuAxel/FastVSDF .

Today, remote sensing (RS) data are already regarded as “big data.” Developments in computer science have made it possible to explore the potential treasure within remote sensing big data, but only limited remote sensing research has made use of big data technology due to gaps in techniques between big data and remote sensing. In this research, we analyzed the full processing flow of remote sensing big data from the perspective of both computer science and remote sensing science and proposed a modular framework. Computation ready data (CRD), a dynamic data type for computation based on analysis ready data (ARD), is proposed to connect the two main modules of the framework, the data module and computation module. Compared with existing research, the proposed framework classifies and abstracts the key technical and research points of the processing of remote sensing big data as replaceable modules and bridges them through an open organization. Subsequently, we built a prototype platform with open-source technologies and carried out three experiments to validate the feasibility and advantages of the framework, namely normalized difference vegetation index (NDVI) production, water body change detection, and land use classification. Results indicate that this framework can greatly reduce experimental costs for remote sensing researchers. While the proposed framework has proven flexible and practical, further research is needed for the technical implementation of certain modules to achieve the original intention of the framework.

Extracting water bodies from synthetic aperture radar (SAR) images plays a crucial role in the management of water resources, flood monitoring, and other applications. Recently, transformer-based models have been extensively utilized in the remote sensing domain. However, due to regular patch-partition and weak inductive bias, transformer-based models face challenges such as edge serration and high data dependency when used for water body extraction from SAR images. To address these challenges, we introduce a new model, the Superpixel-based Transformer (SPT), based on the adaptive characteristic of superpixels and knowledge constraints of the adjacency matrix. (1) To mitigate edge serration, the SPT replaces regular patch partition with superpixel segmentation to fully utilize the internal homogeneity of superpixels. (2) To reduce data dependency, the SPT incorporates a normalized adjacency matrix between superpixels into the Multi-Layer Perceptron (MLP) to impose knowledge constraints. (3) Additionally, to integrate superpixel-level learning from the SPT with pixel-level learning from the CNN, we combine these two deep networks to form SPT-UNet for water body extraction. The results show that our SPT-UNet is competitive compared with other state-of-the-art extraction models, both in terms of quantitative metrics and visual effects.

Visual simultaneous localization and mapping (SLAM) is challenging in dynamic environments as moving objects can impair camera pose tracking and mapping. This paper introduces a method for robust dense bject-level SLAM in dynamic environments that takes a live stream of RGB-D frame data as input, detects moving objects, and segments the scene into different objects while simultaneously tracking and reconstructing their 3D structures. This approach provides a new method of dynamic object detection, which integrates prior knowledge of the object model database constructed, object-oriented 3D tracking against the camera pose, and the association between the instance segmentation results on the current frame data and an object database to find dynamic objects in the current frame. By leveraging the 3D static model for frame-to-model alignment, as well as dynamic object culling, the camera motion estimation reduced the overall drift. According to the camera pose accuracy and instance segmentation results, an object-level semantic map representation was constructed for the world map. The experimental results obtained using the TUM RGB-D dataset, which compares the proposed method to the related state-of-the-art approaches, demonstrating that our method achieves similar performance in static scenes and improved accuracy and robustness in dynamic scenes.