arXiv cs.AI· Jiang Wu, Sichao Wu, Yinsong Ma, Guangyuan Yu, Haoyuan Xu, Lifang Zheng, Jingliang Duan·· 2 小时前AI 评分35
MonitorVLM:面向矿山作业安全违规检测的视觉语言框架
MonitorVLM:A Vision Language Framework for Safety Violation Detection in Mining Operations
AI 导读
研究团队提出 MonitorVLM 视觉语言框架,可直接从监控视频流中检测矿山作业安全违规。框架包含覆盖 40 条高频矿山规程的 9,000 条 VQA 样本数据集,以及条款过滤(CF)模块和行为放大(BM)模块,后者使精确率提升 3.45%、召回率提升 8.62%。
正文 · 原文
Abstract:Industrial accidents, particularly in high-risk domains such as surface and underground mining, are frequently caused by unsafe worker behaviors. Traditional manual inspection remains labor-intensive, error-prone, and insufficient for large-scale, dynamic environments, highlighting the urgent need for intelligent and automated safety monitoring. In this paper, we present MonitorVLM, a novel vision--language framework designed to detect safety violations directly from surveillance video streams. MonitorVLM introduces three key innovations: (1) a domain-specific violation dataset comprising 9,000 vision--question--answer (VQA) samples across 40 high-frequency mining regulations, enriched with augmentation and auxiliary detection cues; (2) a clause filter (CF) module that dynamically selects the Top-$K$ most relevant clauses, reducing inference latency by 13.56% while maintaining accuracy; and (3) a behavior magnifier (BM) module that enhances worker regions to improve fine-grained action recognition, yielding additional gains of 3.45% in precision and 8.62% in recall. Experimental results demonstrate that MonitorVLM significantly outperforms baseline vision--language models, achieving improvements of 22.01% in precision, 34.22\% in recall, and 28.37% in F1 score over the 72B unfine-tuned baseline. A lightweight web-based interface further integrates MonitorVLM into practical workflows, enabling automatic violation reporting with video timestamping. This study highlights the potential of multimodal large models to enhance occupational safety monitoring in mining and beyond.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2510.03666 [cs.CV] |
| (or arXiv:2510.03666v3 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2510.03666 arXiv-issued DOI via DataCite |
Submission history
From: Jiang Wu [view email]
[v1]
Sat, 4 Oct 2025 04:46:21 UTC (2,483 KB)
[v2]
Wed, 11 Mar 2026 12:33:18 UTC (2,489 KB)
[v3]
Wed, 18 Nov 2026 01:33:40 UTC (7,324 KB)
来源:arXiv cs.AI · arxiv.org