Int. J. of Machine Intelligence and Sensory Signal Processing   »   2014 Vol.1, No.3

 

 

Title: A multi-camera video dataset for research on high-definition surveillance

 

Authors: Athira Nambiar; Matteo Taiana; Dario Figueira; Jacinto C. Nascimento; Alexandre Bernardino

 

Addresses:
Computer and Robot Vision Lab, Institute for Systems and Robotics, Instituto Superior Técnico, VisLab – Torre Norte, 7th floor, Av. Rovisco Pais, 1, 1049-001, Lisbon, Portugal
Computer and Robot Vision Lab, Institute for Systems and Robotics, Instituto Superior Técnico, VisLab – Torre Norte, 7th floor, Av. Rovisco Pais, 1, 1049-001, Lisbon, Portugal
Computer and Robot Vision Lab, Institute for Systems and Robotics, Instituto Superior Técnico, VisLab – Torre Norte, 7th floor, Av. Rovisco Pais, 1, 1049-001, Lisbon, Portugal
Computer and Robot Vision Lab, Institute for Systems and Robotics, Instituto Superior Técnico, VisLab – Torre Norte, 7th floor, Av. Rovisco Pais, 1, 1049-001, Lisbon, Portugal
Computer and Robot Vision Lab, Institute for Systems and Robotics, Instituto Superior Técnico, VisLab – Torre Norte, 7th floor, Av. Rovisco Pais, 1, 1049-001, Lisbon, Portugal

 

Abstract: We present a fully labelled image sequence dataset for benchmarking video surveillance algorithms. The dataset was acquired from 13 indoor cameras distributed over three floors of one building, recording simultaneously for 30 minutes. The dataset was specially designed and labelled to tackle the person detection and re-identification problems. Around 80 persons participated in the data collection, most of them appearing in more than one camera. The dataset is heterogeneous: there are three distinct types of cameras (standard, high and very high resolution), different view types (corridors, doors, open spaces) and different frame rates. This diversity is essential for a proper assessment of the robustness of video analytics algorithms in different imaging conditions. We illustrate the application of pedestrian detection and re-identification algorithms to the given dataset, pointing out important criteria for benchmarking and the impact of high-resolution imagery on the performance of the algorithms.

 

Keywords: video surveillance; pedestrian detection; re-identification; benchmarking; image sequence datasets; camera networks; high definition; signal processing; image sequencing; high resolution; camera resolution; indoor cameras; multiple cameras.

 

DOI: 10.1504/IJMISSP.2014.066428

 

Int. J. of Machine Intelligence and Sensory Signal Processing, 2014 Vol.1, No.3, pp.267 - 286

 

Submission date: 20 Jul 2013
Date of acceptance: 24 Dec 2013
Available online: 19 Dec 2014

 

 

Editors Full text accessPurchase this articleComment on this article