C
Claudio Cimarelli
Researcher at University of Luxembourg
Publications - 12
Citations - 67
Claudio Cimarelli is an academic researcher from University of Luxembourg. The author has contributed to research in topics: Computer science & Robot. The author has an hindex of 2, co-authored 7 publications receiving 23 citations.
Papers
More filters
Journal ArticleDOI
A Survey of Computer Vision Methods for 2D Object Detection from Unmanned Aerial Vehicles
TL;DR: This survey presents recent advancements in 2D object detection for the case of UAVs, focusing on the differences, strategies, and trade-offs between the generic problem of object detection, and the adaptation of such solutions for operations of the UAV.
Book ChapterDOI
Faster Visual-Based Localization with Mobile-PoseNet
TL;DR: An efficient neural network is introduced to jointly regress the position and orientation of the camera with respect to the navigation environment to solve the problem of 6 Degrees of Freedom (6-DoF) pose estimation from single RGB camera images.
Proceedings ArticleDOI
Real-Time Human Head Imitation for Humanoid Robots
Dario Cazzato,Claudio Cimarelli,Jose Luis Sanchez-Lopez,Miguel A. Olivares-Mendez,Holger Voos +4 more
TL;DR: A system to reproduce on a robot the head movements of a user in the field of view of a consumer camera is presented, using a deep neural network in order to extract head position angles and to command the robot head movements consequently, obtaining a realistic imitation.
Journal ArticleDOI
A Review of Radio Frequency Based Localisation for Aerial and Ground Robots with 5G Future Perspectives
TL;DR: In this paper , the authors review the RF features that can be utilized for localisation and investigate the current methods suitable for Unmanned Vehicles under two general categories: range-based and fingerprinting.
Proceedings ArticleDOI
A case study on the impact of masking moving objects on the camera pose regression with CNNs
TL;DR: This paper contains an attempt to empirically demonstrate the ability of CNNs to ignore dynamic elements, such as pedestrians or cars, through learning, by comparing the pose regression CNN trained and/or tested on the set of masked images and the original one.