R
Riccardo Gherardi
Researcher at Toshiba
Publications - 38
Citations - 1072
Riccardo Gherardi is an academic researcher from Toshiba. The author has contributed to research in topics: Change detection & Point cloud. The author has an hindex of 13, co-authored 38 publications receiving 845 citations. Previous affiliations of Riccardo Gherardi include University of Verona & Amazon.com.
Papers
More filters
Journal ArticleDOI
Street-view change detection with deconvolutional networks
TL;DR: This work proposes a system for performing structural change detection in street-view videos captured by a vehicle-mounted monocular camera over time, and introduces a new urban change detection dataset which is an order of magnitude larger than existing datasets and contains challenging changes due to seasonal and lighting variations.
Proceedings ArticleDOI
Structure-and-motion pipeline on a hierarchical cluster tree
TL;DR: This papers introduces a novel hierarchical scheme for computing Structure and Motion that has a lower computational complexity, it is independent from the initial pair of views, and copes better with drift problems.
Proceedings ArticleDOI
Improving the efficiency of hierarchical structure-and-motion
TL;DR: A completely automated Structure and Motionpipeline capable of working with uncalibrated images with varying internal parameters and no ancillary information is presented.
Proceedings ArticleDOI
Street-View Change Detection with Deconvolutional Networks
TL;DR: In this article, the authors proposed a method for performing structural change detection in street-view videos captured by a vehicle-mounted monocular camera over time, motivated by the need for more frequent and efficient updates in the large-scale maps used in autonomous vehicle navigation.
Journal ArticleDOI
Hierarchical structure-and-motion recovery from uncalibrated images
TL;DR: A new pipeline, dubbed Samantha, is presented, that departs from the prevailing sequential paradigm and embraces instead a hierarchical approach, which has several advantages, like a provably lower computational complexity, which is necessary to achieve true scalability, and better error containment, leading to more stability and less drift.