融合视觉、几何与红外数据，提升工业缺陷检测精度
Multi-Sensor Object Anomaly Detection: Unifying Appearance, Geometry, and Internal Properties
- 三模态数据融合：可见光、激光扫描与红外热成像
- 96.1% 物体级检测准确率，显著优于单传感器方法
- 专为工业场景设计，适合质量检测系统开发者
物体异常检测对工业质量检验至关重要，但传统单传感器方法受限于仅能捕捉外观、几何或内部特性中的一种，难以覆盖多样异常类型。为此，我们提出首个高分辨率多传感器异常检测数据集 MulSen-AD，整合了RGB相机、激光扫描仪和锁相红外热成像数据，全面捕获物体外部外观、几何形变与内部缺陷。该数据集涵盖15种工业产品，包含真实世界中的多样化异常。我们还构建了 MulSen-AD Bench 基准测试平台，并提出 MulSen-TripleAD 决策层融合算法，实现三种模态的鲁棒无监督异常检测。实验表明，多传感器融合显著优于单传感器方案，物体级检测达到96.1% AUROC，验证了多源数据融合在全面工业异常检测中的关键作用。
原文摘要 · Abstract (English)
Object anomaly detection is essential for industrial quality inspection, yet traditional single-sensor methods face critical limitations. They fail to capture the wide range of anomaly types, as single sensors are often constrained to either external appearance, geometric structure, or internal properties. To overcome these challenges, we introduce MulSen-AD, the first high-resolution, multi-sensor anomaly detection dataset tailored for industrial applications. MulSen-AD unifies data from RGB cameras, laser scanners, and lock-in infrared thermography, effectively capturing external appearance, geometric deformations, and internal defects. The dataset spans 15 industrial products with diverse, real-world anomalies. We also present MulSen-AD Bench, a benchmark designed to evaluate multi-sensor methods, and propose MulSen-TripleAD, a decision-level fusion algorithm that integrates these three modalities for robust, unsupervised object anomaly detection. Our experiments demonstrate that multi-sensor fusion substantially outperforms single-sensor approaches, achieving 96.1% AUROC in object-level detection accuracy. These results highlight the importance of integrating multi-sensor data for comprehensive industrial anomaly detection.
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。