增强现实诱导维修进程识别策略  

Recognition strategy for augmented reality induced maintenance process

作　　者：饶楚锋 韩华亭[1] 王崴[1] 瞿珏[1] 李自豪[1] Rao Chufeng;Han Huating;Wang Wei;Qu Jue;Li Zihao(College of Air-Defense&Anti-Missile,Air Force Engineering University,Xi’an 710051,China)

机构地区：[1]空军工程大学防空反导学院,西安710051

出　　处：《计算机应用研究》2018年第3期922-925,929,共5页Application Research of Computers

基　　金：国家自然科学基金资助项目(51405505)

摘　　要：针对传统的增强现实维修系统不能有效对维修状态进行感知和判断的问题进行了研究,提出了一种基于概率神经网络(probabilistic neural network,PNN)的维修进程识别的策略。该策略将关注的焦点由维修对象本身转移到附近的已拆卸零件放置区域,利用曲波变换生成已拆卸零件边缘图像,然后生成Hu不变矩特征值,再将特征值作为PNN的输入进行进程零件的分类识别,从而得到当前的维修进程。实验表明,该策略下识别的准确度明显高于图像匹配方法与曲波不变矩方法,为场景感知提供了新的思路和解决方案。In view of the problem that the traditional augmented reality maintenance system can not effectively perceive and judge the state of maintenance,this paper proposed a method based on PNN for maintenance process identification.The strategy shifted the focus from the maintenance object itself to the nearby removed parts placement area,used the curvelet transform to generate the edge image of the disassembled parts,then generated the Hu invariant moment characteristic value,which was used as the input of PNN neural network to classify and identify the parts of the process,finally got the current maintenance process.Experimental results show that the recognition accuracy of the proposed method is significantly higher than that of the image matching method and curvelet invariant moment method,which provides a new idea and solution for the scene perception.

关 键 词：增强现实 诱导维修 概率神经网络 进程识别 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]