In this paper we present CMRNet, a realtime approach based on a Convolutional Neural Network (CNN) to localize an RGB image of a scene in a map built from LiDAR data. Our network is not trained in the working area, i.e., CMRNet does not learn the map. Instead it learns to match an image to the map. We validate our approach on the KITTI dataset, processing each frame independently without any tracking procedure. CMRNet achieves 0.27m and 1.07 • median localization accuracy on the sequence 00 of the odometry dataset, starting from a rough pose estimate displaced up to 3.5m and 17 • . To the best of our knowledge this is the first CNN-based approach that learns to match images from a monocular camera to a given, preexisting 3D LiDAR-map.

In this paper, we present a novel probabilistic technique, based on the Bayes filter, able to estimate the user location, even with unreliable sensor data coming only from fixed sensors in the monitored environment. Our approach has been extensively tested in a home-like environment, as well as in a real home, and achieves very good results. We present results on two datasets, representative of real life conditions, collected during the testing phase. We detect the patient location with subroom accuracy, an improvement over the state of the art for localization using only environmental sensors. The main drawback is that it is only suitable for applications where a single person is present in the environment, like as with other approaches that do not use any mobile device. For this reason, we introduced the "telehomecare" term, therefore differentiating from generic telemedicine applications, where many people can be in the same environment at the same time.

No abstract

No abstract

No abstract