Three-dimensional robot localization using cameras in wireless multimedia sensor networks

Sheng Feng

doi:10.1016/j.jnca.2019.102425

Three-dimensional robot localization using cameras in wireless multimedia sensor networks

2019-11-01

15

PRE

AI

DOI：10.1016/j.jnca.2019.102425

原文链接

原文求助

摘要

En 中文

We consider three-dimensional (3D) localization in wireless multimedia sensor networks (WMSNs) and seek optimal localization accuracy in order to ensure real-time data fusion of mobile robots in WMSNs. To this end, we propose a real-time 3D localization algorithm realized by a distributed architecture with various smart devices to overcome network instability and the bottleneck channel at the coordinator. We then employ the recursive least squares (RLS) algorithm to fuse the 2D image coordinates from multiple views synchronously in WMSNs and determine the mobile robot's 3D location in an indoor environment. To minimize wireless data transmission, we also develop a distributed architecture that combines various smart devices by defining the data content transmitted from multiple wireless visual sensors. Moreover, we analyze the factors influencing the network instability of various smart devices, and factors influencing the localization performance of mobile robots in a multiple-view system. Experimental results show the proposed algorithm can achieve reliable, efficient, and real-time 3D localization in indoor WMSNs.

Keyword:

Indoor environment

Wireless multimedia sensor networks (WMSNs)

Recursive least squares localization (RLS)

Real-time data aggregation

Distributed architecture

Three-dimensional robot localization using cameras in wireless multimedia sensor networks

摘要

AI总结

期刊

机构