微小随机变化焊缝的视觉特征提取  

Tiny visual feature extraction of random changing weld

作　　者：陈海永[1] 杜晓琳[1] 董砚[1] 

机构地区：[1]河北工业大学控制科学与工程学院,天津300130

出　　处：《焊接学报》2016年第5期97-101,133,共5页Transactions of The China Welding Institution

基　　金：河北省高等学校科学技术研究资助项目(YQ2013036);国家自然科学基金资助项目(61203275);河北省自然科学基金资助项目(F2014202071);河北省首批青年拔尖人才支持计划;天津市科技特派员资助项目(15JCTPJC55500)

摘　　要：针对焊接过程中薄钢板搭接微小焊缝随机变化的特点,提出一种基于图像能量分布的视觉特征检测和提取方法,采用伪彩色图像增强算法得到能量分布,有效地抑制了焊接过程中飞溅、烟雾等能量弱的瞬时噪声.接着提出一种差分搜索算法实现了结构光条纹骨架的准确提取,并获得了图像特征点.然后,利用随机抽样一致算法对图像特征历史数据进行概率分析,进而精确地拟合出焊缝特征的局部模型,实现了焊缝特征点的准确预测.结果表明,提出的方法是有效的,焊缝视觉特征提取的效果令人满意.To random variation characteristics of the welding process of thin steel lap weld,Proposing a methods based on the energy distribution of the visual featuresdetection and extraction,Using pseudo-color enhancement algorithms to get energy distribution,Effectively suppressed splash,smoke,noise and other transient weak energy during welding. Then proposing a differential search algorithm to achieve the accurate extraction of structured light stripe skeleton,gaining the image feature points.Then using a random sample consensus algorithm to analysis probabilistic of image feature historical data,Thus achiving accurately fitted local model of weld features,fulfiling accurate prediction of feature points. Experimental results show that the proposed method is effective and weld visual feature extraction satisfactory.

关 键 词：焊缝 视觉检测 能量分布 特征提取 随机抽样 

分 类 号：TG441.3[金属学及工艺—焊接]