基于Mask R-CNN实例分割及FPFH特征配对的喷涂工件识别方法  

Recognition Method for Spray-Painted Workpieces Based on Mask R-CNN and Fast Point Feature Histogram Feature Pairing

作　　者：葛俊辉 王健[1] 彭以平 李婕瑄 肖昌炎[1] 刘勇[2] Ge Junhui;Wang Jian;Peng Yiping;Li Jiexuan;Xiao Changyan;Liu Yong(College of Electrical and Information Engineering,Hunan University,Changsha 410082,Hunan,China;Zhejiang Tongji Vocational College of Science and Technology,Hangzhou 311231,Zhejiang,China)

机构地区：[1]湖南大学电气与信息工程学院,湖南长沙410082 [2]浙江同济科技职业学院,浙江杭州311231

出　　处：《激光与光电子学进展》2022年第14期178-188,共11页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(62073128)。

摘　　要：工件识别在柔性化机器人自动喷涂生产线中至关重要,它是机器人切换喷涂轨迹的重要依据。然而,实际应用中,由于喷涂工件尺寸和种类的多样性、表面的弱纹理性、多视异构件及相似件等情况的存在,准确且高效识别喷涂工件充满挑战性。为此,提出了一种二维(2D)实例分割与三维特征一致性配对的识别方法,即利用基于小样本训练的Mask R-CNN深度模型对2D工件分割及识别的快速性,再结合fast point feature histogram(FPFH)点云特征对局部细节的强区分性,实现对多视异构件及相似件由粗到精的准确识别。在精识别阶段,提出了一种基于FPFH特征配对的识别方法。该方法以intrinsic shape signature为工件的关键点,以FPFH为矢量特征,通过线性相关度配对FPFH特征,再以拓扑结构及空间变换关系的一致性为约束验证特征的匹配率,以此作为工件识别的评价标准。实验中,采用34种类别1500多个工件进行测试,所提方法的识别率高达99.26%,单工件识别耗时低于1500 ms。Workpiece recognition is critical for switching painting trajectory in a flexible robotic spray-painting production line.However,due to the wide variety of sprayed workpiece sizes and types,as well as the presence of poor surface texture,multiview dissimilar(MVD)components,and comparable parts,it is difficult to effectively and reliably identify sprayed workpieces in the real production line.In this study,a recognition approach is proposed based on two-dimensional(2D)instance segmentation and three-dimensional feature pairing.Specifically,the high efficiency of the Mask R-CNN learning model was used for 2D workpiece segmentation and coarse recognition based on small sample training;this was followed by the integration of the fast point feature histogram(FPFH)feature for fine recognition,with its strong discrimination of local details for accurately recognizing MVD and similar-topology workpieces.During the fine recognition stage,the intrinsic shape signature method was used as the key point of the workpiece and vectored using the FPFH feature.The extracted feature was then coarsely paired and verified with topological structure consistency and spatial transformation to obtain the paring rate,which was used as the evaluation criterion to recognize the workpiece.In the experiment,more than 1500 workpieces of 34 categories are used for testing,and the recognition accuracy can reach99.26%with a running time of less than 1500 ms for a single workpiece.

关 键 词：机器视觉 三维视觉感知 工件识别 Mask R-CNN fast point feature histogram特征配对 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]