S
Stefano Ghidoni
Researcher at University of Padua
Publications - 93
Citations - 1835
Stefano Ghidoni is an academic researcher from University of Padua. The author has contributed to research in topics: Convolutional neural network & Support vector machine. The author has an hindex of 18, co-authored 86 publications receiving 1330 citations. Previous affiliations of Stefano Ghidoni include Volkswagen & Institute of Robotics and Intelligent Systems.
Papers
More filters
Journal ArticleDOI
Handcrafted vs. non-handcrafted features for computer vision classification
TL;DR: A generic computer vision system designed for exploiting trained deep Convolutional Neural Networks as a generic feature extractor and mixing these features with more traditional hand-crafted features is presented, demonstrating the generalizability of the proposed approach.
Journal ArticleDOI
A New Approach to Urban Pedestrian Detection for Automatic Braking
TL;DR: This paper presents an application of a pedestrian-detection system aimed at localizing potentially dangerous situations under specific urban scenarios and the drastic reduction of false alarms, making this system robust enough to control nonreversible safety systems.
Proceedings ArticleDOI
Performance evaluation of the 1st and 2nd generation Kinect for multimedia applications
S. Zennaro,Matteo Munaro,Simone Milani,Pietro Zanuttigh,Andrea Bernardi,Stefano Ghidoni,Emanuele Menegatti +6 more
TL;DR: A comparison of the data provided by the first and second generation Kinect is presented in order to explain the achievements that have been obtained with the switch of technology.
Journal ArticleDOI
Different approaches for extracting information from the co-occurrence matrix.
TL;DR: Novel sets of texture descriptors extracted from the co-occurrence matrix are investigated, which improve the performance of standard methods and compare and combine different strategies for extending these descriptors.
Journal ArticleDOI
Ensemble of convolutional neural networks for bioimage classification
TL;DR: This work presents a system based on an ensemble of Convolutional Neural Networks and descriptors for bioimage classification that has been validated on different datasets of color images and obtains state-of-the-art performance across four different bioimage and medical datasets.