用AI自动检查工地安全，不用人工盯屏，还能减少误报。
Passive Construction Site Safety Monitoring via Persona-Scaffolded Adversarial Chain-of-Thought VLM Verification
- 分三阶段处理监控视频：先检测装备与危险，再精修分割，最后用多轮对话验证合规性。
- 相比单次提示，误报率降低12%，尤其在易出错的违规类型上效果显著。
- 适合建筑安全监管、智能工地系统开发者，可生成带时间戳证据的个人报告。
美国建筑业仍是致命事故最多的行业，2023年有1,055起致死工伤，多数可预防。现有监控方法成本高、需实时人工干预或仅覆盖有限违规类型。本文提出一种被动式、事后处理的工地安全监测流程，通过视角式体装与固定壁挂摄像头采集视频，采用三阶段架构：（1）微调YOLO11进行主要安全装备与隐患检测；（2）SAM 3实现分割优化与人员去重；（3）基于Qwen3-VL-8B-Instruct的三轮对抗式思维链协议，结合角色设定提示词，完成合规性验证与幻觉控制。核心贡献在于第三阶段的提示设计：采用“方法-角色”框架构建专业角色背景，使非正式三作者评审中12个视频的铁场开发数据集上精度提升12%，尤其在幻觉高发类违规上表现突出。结构化信息隔离确保生成、判别与整合三步观测独立，规则不对称以体现人类观察与自动检测的可靠性差异。系统将违规映射至OSHA标准，基于姿态关键点进行REBA-inspired人因风险评分，并生成含时间戳证据的个人安全报告。评估工具已开源供复现。
原文摘要 · Abstract (English)
Construction remains the deadliest industry sector in the United States, with 1,055 fatal worker injuries recorded in 2023, and the majority preventable. Existing monitoring approaches are expensive, require real-time human operators, or address only a narrow subset of violations. This paper presents a passive, end-of-shift construction safety monitoring pipeline processing video from POV body-worn and fixed wall-mounted cameras through a three-stage architecture: (1) fine-tuned YOLO11 for primary PPE and hazard detection, (2) SAM 3 for segmentation refinement and worker deduplication, and (3) Qwen3-VL-8B-Instruct with a method-prompted, persona-scaffolded three-pass adversarial chain-of-thought protocol for compliance verification and hallucination control. The principal contribution is the Stage 3 prompt design: professional persona backstories following the method-actor framing drive an observed 12% precision improvement over single-pass prompting in an informal three-author review of the 12-video Ironsite development corpus, with the largest gains on hallucination-prone violation categories. Structural message isolation enforces observational independence between a generator, discriminator, and reconciliation pass governed by asymmetric rules encoding priors about human observation versus automated detection reliability. The system maps violations to OSHA standards, performs REBA-inspired ergonomic risk scoring from pose keypoints, and produces per-worker safety reports with timestamped evidence. An evaluation harness is released for future reproduction.
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。