No abstract

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.

No abstract

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.

Abstract-In this work, we propose a system for private sound which is based on the Weighted Pressure Matching method (WPMM). The aim is to design the input signals to an array of loudspeakers which allow for the synthesis of a target field defined with large amplitude variations between the so-called dark points and the listener's position. The system enables listeners to control the trade-off between directivity performance and the accuracy of reproduction of the target field at the listening position when the input energy to the array is limited. This is achieved by calculating the WPMM weight in the dark zone based on a performance constraint on the characteristics of the sound field in the listening zone. The system is validated for a number of pre-defined use-case scenarios. The results of the experiments in an anechoic environment with a circular array prototype show that listeners can control the performance trade-off in a wide frequency range. In the second part of the paper, algorithms are presented for the fast update of the input signals when the user selects a new value of the performance constraint.