天车检修人员防撞检测算法的探索研究  

Exploratory Research on Collision Detection for Overhead Crane Maintenance Personnel

作　　者：吴霜 Wu Shuang(School of Computer Science and Technology,Zhejiang Sci-Tech University,Hangzhou,Zhejiang 310018,China)

机构地区：[1]浙江理工大学计算机科学与技术学院,浙江杭州310018

出　　处：《计算机时代》2025年第4期30-34,共5页Computer Era

摘　　要：针对铝电解车间天车检修场景中存在的金属干扰强、目标小及环境复杂等问题,提出了一种多模态防撞检测系统。融合可见光与红外数据,采用改进型金属干扰抑制算法(MBSA-Pro)和动态特征对齐技术,实现人员精准检测。红外温度掩膜动态过滤高温干扰,将可见光图像信噪比提升至21.4 dB。集成振动与声光预警的智能安全帽构建“感知-决策-执行”闭环体系。工业验证显示,在检测频率30 FPS下,误检率0.6次/小时(总误检次数/总检测次数=0.06%),召回率94.8%,动态距离误差±5%(符合GB 6067.5-2014标准要求),性能优于ISO 13855标准的相关指标。A multimodal anti-collision detection system addresses strong metal interference,small targets,and complex environments in aluminum electrolysis workshop crane maintenance.It integrates visible/infrared data with an improved metal interference suppression algorithm(MBSA-Pro)and dynamic feature alignment for precise personnel detection.Infrared temperature masks filter thermal interference,enhancing visible image SNR to 21.4 dB.Smart helmets with vibration/audio-visual alerts establish a closedloop"perception-decision-execution"system.Industrial validation demonstrates that at a detection frequency of 30 FPS,the system achieves a false detection rate of 0.6 times/hour(0.06%of total detections),a recall rate of 94.8%,a dynamic distance error of±5%(complying with GB 6067.5-2014),outperforming the relevant indicators of ISO 13855.

关 键 词：多模态防撞检测 金属干扰抑制算法 红外温度掩膜 工业验证 

分 类 号：F270[经济管理—企业管理]