提升红外可见光图像中微小目标检测精度，解决错位与多尺度难题。
COXNet: Cross-Layer Fusion with Adaptive Alignment and Scale Integration for RGBT Tiny Object Detection
- 跨层融合可见光高层特征与红外低层特征，增强语义与空间精度
- 动态对齐模块纠正模态间空间错位，保留多尺度特征
- 基于几何形状相似性优化标签分配，适合复杂场景目标检测
在计算机视觉中，从多模态红绿蓝热成像（RGBT）图像中检测微小目标是一项关键挑战，尤其在监控、搜救和自主导航领域。无人机场景因空间错位、低光照、遮挡和背景杂乱加剧了这一挑战。现有方法难以有效利用可见光与热成像之间的互补信息。本文提出COXNet，一种新型的RGBT微小目标检测框架，通过三项核心创新：i）跨层融合模块，融合高层可见光特征与低层热成像特征，提升语义与空间精度；ii）动态对齐与尺度精炼模块，校正跨模态空间错位并保持多尺度特征；iii）基于地理形状相似性度量的优化标签分配策略，改善定位性能。COXNet在RGBTDronePerson数据集上相比当前最优方法，mAP₅₀提升3.32%，验证了其在复杂环境下的鲁棒性。
原文摘要 · Abstract (English)
Detecting tiny objects in multimodal Red-Green-Blue-Thermal (RGBT) imagery is a critical challenge in computer vision, particularly in surveillance, search and rescue, and autonomous navigation. Drone-based scenarios exacerbate these challenges due to spatial misalignment, low-light conditions, occlusion, and cluttered backgrounds. Current methods struggle to leverage the complementary information between visible and thermal modalities effectively. We propose COXNet, a novel framework for RGBT tiny object detection, addressing these issues through three core innovations: i) the Cross-Layer Fusion Module, fusing high-level visible and low-level thermal features for enhanced semantic and spatial accuracy; ii) the Dynamic Alignment and Scale Refinement module, correcting cross-modal spatial misalignments and preserving multi-scale features; and iii) an optimized label assignment strategy using the GeoShape Similarity Measure for better localization. COXNet achieves a 3.32\% mAP$_{50}$ improvement on the RGBTDronePerson dataset over state-of-the-art methods, demonstrating its effectiveness for robust detection in complex environments.
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。