Airports are important transportation hubs, but their locations searched on open databases are not reliable. Manual verification of these locations is time-consuming and labor-intensive, so that a rapid and automated validation of their spatial location is necessary. In this study, three datasets of global airports were collected and fused into one dataset through coordinate and name matching. The fused dataset contained 46,290 airport (with runway) records. Then, we downloaded the remote sensing images of these airports from Google Earth. To determine whether there were airports in these images, we proposed a process framework. In this framework, we used a multi-scale runway detector based on YOLO-v3 to initially detect the airport runway, then used a re-classifier based on ResNet-101 to improve the accuracy of the initial detection results, and gave a comprehensive result score. The accuracy of this process framework and the airport recall rate on the test dataset reached 95.4% and 95.6%, respectively. The framework was applied to airport locations around the world. When the threshold of the result score was set to 0.65, 29259 airport records passed the verification. In addition, we manually verified the application results. The accuracy of the process framework reached 91%, while its speed was 15 times faster than that of the manual verification. The results showed that the entire process framework can quickly and reliably help verify the spatial locations of airports worldwide and provide processing ideas for the validation of the spatial locations of other remote sensing objects.

As an important transportation facility, airports substantially affect the economic lives of people. However, the full extraction of airports located in a vast area is concerning. The size of an airport in a previous wide area detection framework is relatively large and has a strong saliency in remote sensing images, whereas the contradiction between a complex geographical background and a small airport size has yet to be resolved. In this study, we propose a set of automatic detection frameworks to realize efficient detection for various airports in nine Indian states/union territories under the condition that only runway samples are labeled. A preliminary extraction of runway features is performed with a high F1 and recall rate, and teacher nodes judge and guide the results. Next, the output is connected to classification and segmentation for outlier elimination and pixel extraction to locate the runways. For the study area, the proposed framework airport retention rate (RR) is 92.7%, with the false alarm reduction rate(FARR) reduced by a maximum of 95.3%. A total of 192 airports are discovered, and the effective airport growth rate(GR) is 47.4%. Compared to previous work, RR, GR, FARR, and run efficiency increased by 2.2%, 16.0%, 4.5%, and 432.5%, respectively, with more small- and medium-sized airports detected. Furthermore, the framework is tested in Japan, and 155 airports are detected. Thus, the proposed framework effectively improves detection capability for small- and medium-sized airports in large-scale areas and updates the airport database.

Although deep neural networks have made significant progress in tasks related to remote sensing image scene classification, most of these tasks assume that the training and test data are independently and identically distributed. However, when remote sensing scene classification models are deployed in the real world, the model will inevitably encounter situations where the distribution of the test set differs from that of the training set, leading to unpredictable errors during the inference and testing phase. For instance, in the context of large-scale remote sensing scene classification applications, it is difficult to obtain all the feature classes in the training phase. Consequently, during the inference and testing phases, the model will categorize images of unidentified unknown classes into known classes. Therefore, the deployment of out-of-distribution (OOD) detection within the realm of remote sensing scene classification is crucial for ensuring the reliability and safety of model application in real-world scenarios. Despite significant advancements in OOD detection methods in recent years, there remains a lack of a unified benchmark for evaluating various OOD methods specifically in remote sensing scene classification tasks. We designed different benchmarks on three classical remote sensing datasets to simulate scenes with different distributional shift. Ten different types of OOD detection methods were employed, and their performance was evaluated and compared using quantitative metrics. Numerous experiments were conducted to evaluate the overall performance of these state-of-the-art OOD detection methods under different test benchmarks. The comparative results show that the virtual-logit matching methods without additional training outperform the other types of methods on our benchmarks, suggesting that additional training methods are unnecessary for remote sensing image scene classification applications. Furthermore, we provide insights into OOD detection models and performance enhancement in real world. To the best of our knowledge, this study is the first evaluation and analysis of methods for detecting out-of-distribution data in remote sensing. We hope that this research will serve as a fundamental resource for future studies on out-of-distribution detection in remote sensing.

Runway heading is a crucial runway attribute that closely affects aircraft' takeoff and landing safely while having a large number of missing in existing runway thematic databases, limiting the evaluation and analysis globally. This article proposes an automated runway heading extraction method, considering various runway surface materials and spatial structure differences encountered in wide-area detection, promoting a quick and reliable broad investigation. First, multiscale detection is performed based on the mask regional convolutional neural network runway detection model to locate airport runways, using the mask nonmaximum suppression mechanism algorithm to distinguish runways with highly overlapping candidate results. Second, abnormality judgment and mask selection according to semantic constraints were applied to the identified runway area to reserve high-confidence masks to accurately extract the runway heading. We tested our framework results on 1483 runways in the United States with complex runway materials and structures combination. The runway detection recall was 99.12%, and 98.9% of the runway heading errors were limited to 2°, showing that the overall frame for extracting the true runway heading is reliable. In addition, we complement the true headings of 892 runways in OurAirports, promoting research on the completion, verification, and updating of runway semantics in related databases.

In remote sensing building detection tasks, data acquisition remains a critical bottleneck that limits both model performance and large-scale deployment. Due to the high cost of manual annotation, limited geographic coverage, and constraints of image acquisition conditions, obtaining large-scale, high-quality labeled datasets remains a significant challenge. To address this issue, this study proposes an automatic semantic labeling framework for remote sensing imagery. The framework leverages geospatial vector data provided by OpenStreetMap, precisely aligns it with high-resolution satellite imagery from Bing Maps through projection transformation, and incorporates a quality-aware sample filtering strategy to automatically generate accurate annotations for building detection. The resulting dataset comprises 36,647 samples, covering buildings in both urban and suburban areas across multiple cities. To evaluate its effectiveness, we selected three publicly available datasets—WHU, INRIA, and DZU—and conducted three types of experiments using the following four representative object detection models: SSD, Faster R-CNN, DETR, and YOLOv11s. The experiments include benchmark performance evaluation, input perturbation robustness testing, and cross-dataset generalization analysis. Results show that our dataset achieved a mAP at 0.5 intersection over union of up to 93.2%, with a precision of 89.4% and a recall of 90.6%, outperforming the open-source benchmarks across all four models. Furthermore, when simulating real-world noise in satellite image acquisition—such as motion blur and brightness variation—our dataset maintained a mean average precision of 90.4% under the most severe perturbation, indicating strong robustness. In addition, it demonstrated superior cross-dataset stability compared to the benchmarks. Finally, comparative experiments conducted on public test areas further validated the effectiveness and reliability of the proposed annotation framework.

Global land cover heterogeneity is usually directly reflected in the background of remote sensing objects. This substantially affects the generalization ability of object detection models and is a challenge for remote sensing object detection in large-scale areas. In this study, we analyze the heterogeneity of land cover in different climate areas, and propose a remote sensing object image synthesis method based on multi-stage blending strategy (MBS) to achieve a high-quality blending of the labeled runway foreground image and the typical surface image of the area to be detected. Three geometric augmentation algorithms are applied to expand the size of the sample data. Finally, two representative object detection models, YOLOv5 and Faster R-CNN, are used to evaluate the effectiveness of the synthetic data. Experiments in North Africa and Central Asia demonstrate that the MBS method effectively improves the performance of airport runway detection in large-scale heterogeneous areas. Additionally, our method performs better than Copy-Paste and Poisson blending.