DrIFT数据集提升无人机视觉检测在域偏移下的可靠性。
DrIFT: Autonomous Drone Dataset with Integrated Real and Synthetic Data, Flexible Views, and Transformed Domains
- 融合真实与合成数据，覆盖14种不同视角和环境域
- 提出新不确定性度量MCDO-map，降低后处理复杂度且性能更优
- 适合研究域适应与鲁棒视觉检测的学者使用
可靠的视觉无人机检测对无人机安全融入空域至关重要。然而，环境变化、视角差异和背景变动导致的域偏移会显著影响检测精度。为此，我们提出DrIFT数据集，专为域偏移下的视觉无人机检测设计。该数据集包含14个不同域，涵盖视角、真实-合成数据、季节及恶劣天气的差异。其独特之处在于提供背景分割图，支持按背景评估性能。我们提出的不确定性度量MCDO-map具有更低的后处理复杂度，优于传统方法。将其用于不确定性感知的无监督域适应方法，在多个任务中表现超越现有最先进技术。数据集已开源：https://github.com/CARG-uOttawa/DrIFT.git。
原文摘要 · Abstract (English)
Dependable visual drone detection is crucial for the secure integration of drones into the airspace. However, drone detection accuracy is significantly affected by domain shifts due to environmental changes, varied points of view, and background shifts. To address these challenges, we present the DrIFT dataset, specifically developed for visual drone detection under domain shifts. DrIFT includes fourteen distinct domains, each characterized by shifts in point of view, synthetic-to-real data, season, and adverse weather. DrIFT uniquely emphasizes background shift by providing background segmentation maps to enable background-wise metrics and evaluation. Our new uncertainty estimation metric, MCDO-map, features lower postprocessing complexity, surpassing traditional methods. We use the MCDO-map in our uncertainty-aware unsupervised domain adaptation method, demonstrating superior performance to SOTA unsupervised domain adaptation techniques. The dataset is available at: https://github.com/CARG-uOttawa/DrIFT.git.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。