A
Andrea Cavallaro
Researcher at Queen Mary University of London
Publications - 366
Citations - 10738
Andrea Cavallaro is an academic researcher from Queen Mary University of London. The author has contributed to research in topics: Video tracking & Object detection. The author has an hindex of 46, co-authored 345 publications receiving 8945 citations. Previous affiliations of Andrea Cavallaro include Tel Aviv University & Dalhousie University.
Papers
More filters
Proceedings ArticleDOI
Single camera calibration for trajectory-based behavior analysis
Nadeem Anjum,Andrea Cavallaro +1 more
TL;DR: This paper improves the results of trajectory-based scene analysis by using single camera calibration for perspective rectification and unsupervised fuzzy clustering is applied on the transformed trajectories to group similar behaviors and to isolate outliers.
Distributed video acquisition and annotation for sport-event summarization
Christophe De Vleeschouwer,Fan Chen,Damien Delannay,C. Parisot,Christophe Chaudy,Eric Martrou,Andrea Cavallaro +6 more
TL;DR: This document presents the video data set that has been recently collected within the FP7 APIDIS project, and consists in a set of 7 calibrated IP cameras, each one collecting 2 Mpixels frames at a rate higher than 20 frames/sec.
Proceedings ArticleDOI
Multiscale observation of multiple moving targets using Micro Aerial Vehicles
TL;DR: A centralized algorithm for multi-scale observation of multiple moving targets using a team of Micro Aerial Vehicles using a quad-tree data structure to model the movement decisions of MAVs as well as the variable qualities of observations.
Proceedings ArticleDOI
Segmentation-driven perceptual quality metrics
Andrea Cavallaro,S. Winkler +1 more
TL;DR: A full-reference and a no-reference perceptual video quality metric that incorporate both low-level and high-level aspects of vision that take into account the cognitive behavior of an observer when watching a video by means of semantic segmentation is presented.
Proceedings ArticleDOI
Scene Privacy Protection
TL;DR: The proposed method, private FGSM, achieves a desirable trade-off between the drop in classification accuracy and the distortion on the private classes of the Places365-Standard dataset using ResNet50.