Person detection, tracking and masking for automated annotation of large CCTV datasets
Abstract
In this paper we describe a real-time approach for person detection in video footage, joint with a privacy masking tool, in the framework of forensic applications in CCTV systems. Particularly, this paper summarizes our results in these domains within the European FP7 SAVASA and P-REACT projects. Our main contributions have been focused on real-time performance of detection algorithms using a novel perspective-based approach, and the creation of a methodology for privacy masking content such as the faces of the persons in the images.
BIB_text
author = {Marcos Nieto, Peter Leskovsky, Juan Diego Ortega},
title = {Person detection, tracking and masking for automated annotation of large CCTV datasets},
pages = {519-522},
volume = {8867},
keywds = {
computer vision, real-time, detection and tracking, privacy masking
}
abstract = {
In this paper we describe a real-time approach for person detection in video footage, joint with a privacy masking tool, in the framework of forensic applications in CCTV systems. Particularly, this paper summarizes our results in these domains within the European FP7 SAVASA and P-REACT projects. Our main contributions have been focused on real-time performance of detection algorithms using a novel perspective-based approach, and the creation of a methodology for privacy masking content such as the faces of the persons in the images.
}
isbn = {978-3-319-13101-6},
date = {2014-12-02},
year = {2014},
}
