中国防汛抗旱2026，Vol.36Issue(5)：22-30,9.DOI:10.16867/j.issn.1673-9264.2026188
提示词驱动下MLLM与YOLO的城市内涝车辆淹没识别性能对比
Performance comparison of MLLM and YOLO for vehicle inundation recognition in urban waterlogging under prompt-driven scenarios
摘要
Abstract
To address the technical selection requirements for vehicle submersion level identification in urban waterlogging scenarios,this study constructs a comparative evaluation framework for multimodal large language models and YOLO series algorithms.Based on a sample of 1 000 vehicle images covering five submersion levels,the recognition performance of Qwen_VL_Max and GPT-4o under zero-shot and few-shot prompting modes is systematically evaluated,with YOLOv8s,YOLOv11s,and YOLO26s serving as supervised learning baseline models for comparative analysis.The results show that:① The YOLO series algorithms generally outperform the multimodal large models,with YOLOv11s demonstrating better balance and stability in level recognition,while YOLO26s exhibits advantages in standard detection metrics.② Few-shot prompting significantly improves the recognition accuracy of Qwen_VL_Max by 22.10 percentage points compared to the zero-shot mode,yet multimodal large models still lack fine-grained discriminative capability for medium-to-high submersion levels.③ The YOLO series algorithms are more suitable for large-scale,high-precision standardized recognition tasks,whereas multimodal large models have certain advantages in small-sample,rapid-deployment scenarios.The findings provide a reference for technology selection in vehicle submersion recognition for smart flood control applications.关键词
城市内涝/车辆淹没/淹没等级识别/多模态大模型/YOLO算法Key words
urban waterlogging/vehicle submergence/submergence level recognition/multimodal large language model/YOLO algorithm分类
信息技术与安全科学引用本文复制引用
李思奇,王涛,刘颖,张会..提示词驱动下MLLM与YOLO的城市内涝车辆淹没识别性能对比[J].中国防汛抗旱,2026,36(5):22-30,9.基金项目
河南省科技攻关项目(252102321017) （252102321017）
河南省杰出青年科学基金项目(242300421041) （242300421041）
河南省高校科技创新团队支持计划(25IRTSTHN008) （25IRTSTHN008）
河南省重点研发专项(241111321100). （241111321100）
