基于移动机器人和单目视觉的姿态测量方法  

Pose measurement based on moving robot based and monocular vision

作　　者：龙涛[1] LONG Tao(Research Department,Hubei Polytechnic Institute,Xiaogan 432000,China)

机构地区：[1]湖北职业技术学院科研处,湖北孝感432000

出　　处：《光学技术》2021年第2期203-208,共6页Optical Technique

基　　金：湖北省教育厅科学技术研究项目(B2019403)。

摘　　要：在单目视觉的姿态测量工作中,传统卷积神经网络在模糊场景及复杂场景下存在准确度大幅降低的问题,为此提出了一种基于胶囊网络与贝叶斯网络相结合的深度学习模型,在此基础上提出了基于移动机器人与单目视觉的姿态测量方法。采用新型胶囊网络对单目视觉目标的重要关节点进行空间定位;设计了简单的贝叶斯网络学习算法,通过贝叶斯网络推理出关节点的空间姿态;在复杂的人体姿态测量数据集上完成了验证实验,结果表明实现了较好的测量准确度,在复杂场景下依然保持了较好的准确度,在室内与室外环境下的F1-measure值分别达到0.9和0.78。In the task of pose measurement based on monocular vision,traditional convolutional neural networks suffer from the problem that the measurement accuracy reduces dramatically in both fuzzy background and complicated background,a deep learning model based on capsule network and Bayesian network is proposed,further a pose measurement method is proposed based on moving robot and monocular vision.First of all,the new Capsules Network is adopted to locating the important joint points of monocular vision objectives;then,a simple learning algorithm for Bayesian networks is designed,and the attitudes of joint points are inferred by Bayesian networks.Finally,validation experiments are carried on complicated human pose measurement datasets,the experimental results show that the proposed method realizes a good measurement accuracy,it remains a high-level accuracy in complicated background too,the result F1-measure values equal 0.9 and 0.78 for indoors and outdoors scenarios respectively.

关 键 词：姿态测量 智能机器人 单目视觉 光学图像 深度学习 关节点定位 

分 类 号：TP394.1[自动化与计算机技术—计算机应用技术] TH691.9[自动化与计算机技术—计算机科学与技术]