场景图引导的生成式AI框架用于工业危险场景的合成与评估
Scene Graph-Guided Generative AI Framework for Synthesizing and Evaluating Industrial Hazard Scenarios
AI总结：
针对工业危险场景数据集获取困难的问题，提出场景图引导的生成式AI框架，基于OSHA事故报告提取危险推理生成场景图，引导扩散模型合成逼真危险图像，并通过VQA框架验证其优于现有指标。
摘要：
训练视觉模型准确检测工作场所危险需要可能导致事故的不安全状况的真实图像。然而，获取此类数据集十分困难，因为捕获事故触发场景几乎不可能。为克服这一限制，本研究提出一种新颖的场景图引导生成式AI框架，基于历史职业安全与健康管理局（OSHA）事故报告合成危险场景的逼真图像。使用GPT-4o分析OSHA叙述以提取结构化危险推理，将其转换为对象级场景图，捕获理解风险所需的空间和上下文关系。这些图引导文本到图像扩散模型生成构图准确的危险场景。为评估生成数据的真实性和语义保真度，引入视觉问答（VQA）框架。在四种最先进的生成模型上，所提出的VQA图得分基于熵验证优于CLIP和BLIP指标，证实其更高的判别敏感性。
英文摘要：
Training vision models to detect workplace hazards accurately requires realistic images of unsafe conditions that could lead to accidents. However, acquiring such datasets is difficult because capturing accident-triggering scenarios as they occur is nearly impossible. To overcome this limitation, this study presents a novel scene graph-guided generative AI framework that synthesizes photorealistic images of hazardous scenarios grounded in historical Occupational Safety and Health Administration (OSHA) accident reports. OSHA narratives are analyzed using GPT-4o to extract structured hazard reasoning, which is converted into object-level scene graphs capturing spatial and contextual relationships essential for understanding risk. These graphs guide a text-to-image diffusion model to generate compositionally accurate hazard scenes. To evaluate the realism and semantic fidelity of the generated data, a visual question answering (VQA) framework is introduced. Across four state-of-the-art generative models, the proposed VQA Graph Score outperforms CLIP and BLIP metrics based on entropy-based validation, confirming its higher discriminative sensitivity.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
