构建合成数据集，提升基础设施裂缝检测模型在真实场景的泛化能力
CERBERUS: Crack Evaluation & Recognition Benchmark for Engineering Reliability & Urban Stability
- 用Unity生成逼真3D巡检场景和裂缝图像
- 合成+真实数据混合训练使YOLO模型在实拍图上精度提升
- 适合做智能基建巡检的算法研究者使用
CERBERUS是一个用于训练和评估人工智能模型检测基础设施裂缝等缺陷的合成基准。它包含一个裂缝图像生成器和在Unity中构建的真实感3D巡检场景，涵盖两种设置：简单的飞越墙检场景和包含光照与几何挑战的复杂地下通道场景。我们使用主流目标检测模型YOLO，测试了不同组合的合成与真实裂缝数据。结果表明，混合使用合成与真实数据可显著提升模型在真实图像上的表现。CERBERUS提供了一种灵活、可复现的缺陷检测系统评测方式，支持未来自动化基础设施巡检研究。项目已开源，地址为https://github.com/justinreinman/Cerberus-Defect-Generator。
原文摘要 · Abstract (English)
CERBERUS is a synthetic benchmark designed to help train and evaluate AI models for detecting cracks and other defects in infrastructure. It includes a crack image generator and realistic 3D inspection scenarios built in Unity. The benchmark features two types of setups: a simple Fly-By wall inspection and a more complex Underpass scene with lighting and geometry challenges. We tested a popular object detection model (YOLO) using different combinations of synthetic and real crack data. Results show that combining synthetic and real data improves performance on real-world images. CERBERUS provides a flexible, repeatable way to test defect detection systems and supports future research in automated infrastructure inspection. CERBERUS is publicly available at https://github.com/justinreinman/Cerberus-Defect-Generator.
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。