Beyond Clear Skies: Synthetic Seasonal and Weather Variations for Real-World Drone Detection
2026-08-17 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created a big set of fake (synthetic) drone images showing different weather like rain, snow, and fog, plus seasonal changes in cities. This helps train drone detectors to work well even in bad weather, which is usually hard to do because real bad weather photos are tough to get. Their new dataset, SDV-W, lets researchers compare how drone detectors perform in clear versus bad weather using the same scenes. Tests show their dataset helps improve detection accuracy and reduces mistakes when drones are harder to see. They plan to share this dataset publicly to support better drone detection in various weather conditions.
drone detectionsynthetic dataadverse weatherseasonal variationurban environmentYOLO modelsdomain shiftdata annotationrealistic renderingdataset
Authors
Tamara R. Lenhard, Andreas Weinmann, Tobias Koch
Abstract
Reliable drone detection under real-world deployment conditions requires training data that spans the full operational design domain, including adverse weather and seasonal appearance variation. However, acquiring and annotating such data at scale remains highly resource-intensive, as adverse-weather conditions are inherently difficult to control, reproduce, and sample systematically. Existing datasets therefore typically provide only limited coverage of such conditions. Conversely, synthetic data offers a scalable alternative: environmental variation becomes controllable, while modern game-engine-based pipelines provide realistic rendering and automatic annotations. Leveraging this potential, we introduce SynDroneVision-Weather (SDV-W), an systematic extension of SynDroneVision (SDV) targeting adverse-weather and seasonal domain shifts in urban drone detection. SDV-W comprises 55,187 annotated high-resolution images from three urban environments, rendered across three seasonal configurations and diverse weather conditions, including rain, snow, and fog at multiple severity levels. By preserving SDV's scene and trajectory configuration, SDV-W enables matched clean-adverse comparisons and quantification of condition-specific detector degradation. Across representative YOLO models and real-world datasets, we show that SDV-W improves detector reliability under adverse appearance shifts, reduces missed detections and false alarms, and is most effective as a complement to general-purpose synthetic drone-detection data. SDV-W will be publicly released upon paper acceptance.