LAUSR

Accurate location information is very important for human beings and agents. However, GPS has very limited positioning accuracy or even can not work in challenging environments such as indoor and urban canyons, and other solutions suffer from different shortcomings. It is very meaningful to use the scene image captured by the high-definition camera on the smart phone to locate indoor through the neural network, but the existing image-based positioning methods do not take into account the interrelationship of diffenrent instances of the same feature space. In this paper we present a novel network architecture, which embeds Scene Enhancement module and Relational Network (RN) into the end-to-end positioning system. The system was tested in three typical scenarios, and the test results show that its performance outerperforms existing image-based schemes in most cases.