Scene object recognition for mobile robots through Semantic Knowledge and Probabilistic Graphical Models

作者：

Highlights：

• Semantic Knowledge and PGMs capabilities are combined.

• Common-sense information assists probabilistic inference.

• The system is able to exploit objects’ relations and manage uncertainty.

• Validation is conducted with two datasets, UMA-offices and NYU2.

• The performance of exact and approximate inference methods is studied.

摘要

•Semantic Knowledge and PGMs capabilities are combined.•Common-sense information assists probabilistic inference.•The system is able to exploit objects’ relations and manage uncertainty.•Validation is conducted with two datasets, UMA-offices and NYU2.•The performance of exact and approximate inference methods is studied.

论文关键词：Object recognition,Semantic Knowledge,Probabilistic Graphical Models,Mobile robotics,Expert systems,Autonomous agents

论文评审过程：Received 16 December 2014, Revised 14 July 2015, Accepted 16 July 2015, Available online 22 July 2015, Version of Record 29 August 2015.

论文官网地址：https://doi.org/10.1016/j.eswa.2015.07.033