论文/arXiv 2610.06596·23 天前

面向自动驾驶系统的恶劣环境条件下 SWIR 成像检测性能分析

研究在 RASMD 上系统比较 RGB 与 SWIR 目标检测，提出传感器优势挖掘，验证 SWIR 在少数困难场景的互补价值。

AI 整理

• 数据与采集
• 端侧部署
• 评测与安全

原文链接：Analysis of SWIR Imaging Detection Performance Under Adverse Environmental Conditions for Autonomous Driving Systems（arXiv 2610.06596 · 发布日期：2026-10-05）

Analysis of SWIR Imaging Detection Performance Under Adverse Environmental Conditions for Autonomous Driving Systems

研究在 RASMD 上系统比较 RGB 与 SWIR 目标检测，提出传感器优势挖掘，验证 SWIR 在少数困难场景的互补价值。

核心要点

• 动机是 SWIR 成像被视为自动驾驶的有前景模态，但相对 RGB 的实际收益仍缺乏充分刻画。
• 方法上比较成对 RGB 与 SWIR 检测，并提出结合多模型一致性与人工检查的传感器优势挖掘框架。
• 实验覆盖 RASMD 数据集四种天气和两种实时检测架构；多数场景 RGB 相当或更优，RF-DETR 更稳健。
• 分析发现 SWIR 在挡风玻璃眩光、水滴、低对比目标和远距离车辆检测中更可靠；代码和权重已公开。

验证范围与局限：验证范围为 RASMD 数据集上的成对 RGB/SWIR 目标检测，覆盖四种天气和两种实时检测架构。

英文摘要 (Abstract)

Short-wave infrared (SWIR) imaging has emerged as a promising modality for autonomous driving, yet its practical benefits over RGB remain poorly characterized across diverse conditions. This paper presents a systematic comparative study of paired RGB and SWIR object detection on the RASMD dataset, covering four weather conditions and two real-time detection architectures, with various fine-tunings evaluated against a unified ground truth. Overall, RGB demonstrates comparable or superior performance in most scenarios, while RF-DETR exhibits greater robustness across varying conditions. Beyond aggregate metrics, we propose a sensor-dominance mining framework that combines multi-model agreement with targeted manual inspection to identify scenarios where one sensing modality provides more reliable detections using largely unannotated paired data. This analysis reveals that SWIR offers clear advantages in four safety-critical situations, including windshield glare, water droplets on the windshield, low-contrast object visibility, and long-range vehicle detection. The findings suggest that SWIR should be viewed as a complementary modality that enhances perception in rare but challenging conditions. The datasets will be available upon request, and all code and trained model weights are publicly released at https://github.com/comsee-research/swir-adverse-env-analysis.

作者：Rohan Mehra, Alexandre Riffard, Yannis Loumouamou, Mathieu Labussière

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.06596：Analysis of SWIR Imaging Detection Performance Under Adverse Environmental Conditions for Autonomous Driving Systems访问 2026-10-21