多传感器数据融合室内定位方法  

Indoor Positioning Method Based on Multi-sensor Data Fusion

作　　者：段金杰 江督 詹志明[1] DUAN Jinjie;JIANG Du;ZHAN Zhiming(School of Artificial Intelligence,Jianghan University,Wuhan 430056,Hubei,China)

机构地区：[1]江汉大学人工智能学院,湖北武汉430056

出　　处：《江汉大学学报（自然科学版）》2023年第3期47-54,共8页Journal of Jianghan University：Natural Science Edition

基　　金：江汉大学研究生科研创新基金资助项目。

摘　　要：研究了基于超宽带技术(ultra wide band,UWB)定位和视觉定位的多传感器融合室内定位方法,设计了UWB定位单元软硬件平台,调用修改了基于MMTracking的视觉定位方法,实现了两种室内定位技术,构建了基于贝叶斯估计的双传感器数据融合模型。实验结果表明,该方法具有较好的定位效果,提高了室内定位的测量精度和稳定性。This paper studied the multi-sensor fusion indoor positioning method based on UWB and visual positioning.The software and hardware platform of the UWB positioning unit was designed,the visual positioning method based on MMTracking was called and modified,two indoor positioning technologies were realized,and a two-sensor data fusion model based on Bayesian estimation was constructed.The experimental results showed that this method had a good positioning effect and improved the measurement accuracy and stability of indoor positioning.

关 键 词：超宽带技术 视觉定位 贝叶斯估计 融合算法 

分 类 号：TP212.9[自动化与计算机技术—检测技术与自动化装置]