Global tracker: an online evaluation framework to improve tracking quality

Julien Badie 1 François Bremond 1
1 STARS - Spatio-Temporal Activity Recognition Systems
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : Evaluating the quality of tracking outputs is an important task in video analysis. This paper presents a new framework for estimating both detection and tracking quality during runtime. If anomalies are detected in the tracking output results, they are categorized as natural phenomena or real errors using contextual information. As this framework should be generic and work on any kind of system (single camera, camera network), a re-acquisition step using a constrained clustering algorithm is also performed in order to keep track of the object even if it leaves the scene and comes back or appears on another camera. The framework is evaluated on two datasets using different kinds of tracking algorithms.
Liste complète des métadonnées

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/hal-01062766
Contributor : Julien Badie <>
Submitted on : Wednesday, September 10, 2014 - 3:01:45 PM
Last modification on : Tuesday, July 24, 2018 - 3:48:02 PM
Document(s) archivé(s) le : Friday, April 14, 2017 - 11:51:42 AM

File

Global_tracker_an_online_evalu...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01062766, version 1

Collections

Citation

Julien Badie, François Bremond. Global tracker: an online evaluation framework to improve tracking quality. AVSS - 11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, Aug 2014, Seoul, South Korea. 2014. 〈hal-01062766〉

Share

Metrics

Record views

174

Files downloads

189