构建无人机多模态检测高多样性数据集，提出条件感知融合方法。
Fusion Meets Diverse Conditions: A High-diversity Benchmark and Baseline for UAV-based Multimodal Object Detection with Condition Cues
- 用条件提示动态调整可见光与红外图像的融合权重。
- 在80~300米高度、0°~75°视角下验证模型性能提升。
- 适合做无人机全天候多模态目标检测的研究者参考。
基于无人机的可见光（RGB）与红外（IR）图像目标检测，得益于深度学习进展和高质量数据集，实现了全天候鲁棒检测。然而现有数据集难以全面覆盖真实场景中的复杂成像条件。为此，本文构建了高多样性数据集ATR-UMOD，涵盖80米至300米飞行高度、0°至75°视角变化，以及全年全天候丰富的天气与光照条件。每对RGB-IR图像均标注6个条件属性，提供高层上下文信息。针对多样条件带来的挑战，提出一种提示引导的条件感知动态融合（PCDF）方法，通过文本提示编码成像条件，利用任务特定的软门控变换建模条件与多模态贡献间的关系。进一步设计提示引导的条件解耦模块，使模型在无条件标注时仍可实用。在ATR-UMOD上的实验验证了PCDF的有效性。
原文摘要 · Abstract (English)
Unmanned aerial vehicles (UAV)-based object detection with visible (RGB) and infrared (IR) images facilitates robust around-the-clock detection, driven by advancements in deep learning techniques and the availability of high-quality dataset. However, the existing dataset struggles to fully capture real-world complexity for limited imaging conditions. To this end, we introduce a high-diversity dataset ATR-UMOD covering varying scenarios, spanning altitudes from 80m to 300m, angles from 0° to 75°, and all-day, all-year time variations in rich weather and illumination conditions. Moreover, each RGB-IR image pair is annotated with 6 condition attributes, offering valuable high-level contextual information. To meet the challenge raised by such diverse conditions, we propose a novel prompt-guided condition-aware dynamic fusion (PCDF) to adaptively reassign multimodal contributions by leveraging annotated condition cues. By encoding imaging conditions as text prompts, PCDF effectively models the relationship between conditions and multimodal contributions through a task-specific soft-gating transformation. A prompt-guided condition-decoupling module further ensures the availability in practice without condition annotations. Experiments on ATR-UMOD dataset reveal the effectiveness of PCDF.
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。