MR中融合语义特征传播模型的前景对象感知定位算法  

Foreground object perception and location algorithm based on semantic feature propagation model in MR

作　　者：方哲 张金艺[1,2] 姜玉稀 FANG Zhe;ZHANG Jinyi;JIANG Yuxi(Key laboratory of Specialty Fiber Optics and Optical Access Networks,Shanghai University,Shanghai 200444,China;Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication,Shanghai University,Shanghai 200444,China;Shanghai Sansi Institute for System Integration,Shanghai 201100,China)

机构地区：[1]上海大学特种光纤与光接入网重点实验室,上海200444 [2]上海大学特种光纤与先进通信国际合作联合实验室,上海200444 [3]上海三思系统集成研究所,上海201100

出　　处：《上海大学学报（自然科学版）》2023年第1期41-55,共15页Journal of Shanghai University:Natural Science Edition

基　　金："十三五"国家重点研发计划资助项目(2017YFB0403500);高等学校学科创新引智计划(111计划)项目(D20031);上海市教委重点学科资助项目(J50104)。

摘　　要：移动主体获得准确的定位信息是构建稳定的混合现实(mixed reality,MR)系统的关键,然而MR中的前景对象对传统定位算法的精度影响较大.现阶段基于深度学习的定位算法可以通过识别前景对象来提升精度,但深度学习模型耗时过高,导致算法实时性下降.针对该问题,提出了一种MR中融合语义特征传播模型的前景对象感知定位算法.该算法依托语义分割网络与一种快速旋转的二进制独立稳定描述子特征(oriented fast and rotated binary robust independent elementary feature,ORB)提取算法构建了语义特征传播模型,实现高速语义特征提取;融合该模型和几何特征检测方法实现算法中的前景对象感知层,并依赖该感知层剔除MR中前景对象的特征点,构建了背景特征点集,实现高精度、高实时性的定位.实验结果表明:在慕尼黑工业大学(Technical University of Munich,TUM)公共数据集的高动态前景对象场景中,相比动态语义视觉同步定位与建图(dynamic semantic visual simultaneous localization and mapping,DS-SLAM)算法,该算法相对位姿误差降低了60.5%,定位实时性提升了39.5%,可见该算法在MR中具有较高的应用价值.Accurate location information obtained by mobile agents is the key to building a stable mixed reality(MR)system.However,foreground objects in an MR scene have a significant impact on the accuracy of traditional location algorithms.At present,location algorithms based on deep learning show relatively improved accuracy by identifying fore-ground objects,but the time consumption of a deep learning model is too high,resulting in a decline in the real-time performance of the algorithms.To solve this problem,this paper proposes a foreground object-aware location algorithm based on an MR semantic feature propagation model.The algorithm builds a semantic feature propagation model based on a semantic segmentation network and the oriented FAST and rotated BRIEF feature extraction algorithm to realize high-speed semantic feature extraction.The model and a geometric feature detection method are fused to realize the foreground object perception layer in the algorithm,which eliminates the feature points on the foreground objects in MR,and to construct a background feature point set to realize high precision and high real-time location.Experimental results show that the proposed algorithm reduces the relative pose error by 60.5%and improves the real-time location performance by 39.5%compared to the dynamic scenes simultaneous localization and mapping location algorithm in the high-dynamic foreground object scene of the Technical University of Munich public dataset.Therefore,this algorithm has high application value in MR scenes.

关 键 词：混合现实 前景对象 定位 语义特征 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]