Hyper-optimization tools comparison for parameter tuning applications

Camille Maurice 1 Jorge Francisco Madrigal Diaz 1 Frederic Lerasle 1
1 LAAS-RAP - Équipe Robotique, Action et Perception
LAAS - Laboratoire d'analyse et d'architecture des systèmes [Toulouse]
Abstract : This paper evaluates and compares different hyper-parameters optimization tools that can be used in any vision applications for tuning their underlying free parameters. We focus in the problem of multiple object tracking, as it is widely studied in the literature and offers several parameters to tune. The selected tools are freely available or easy to implement. In this paper we evaluate the impact of parameter optimization tools over the tracking performances using videos from public datasets. Also, we discuss differences between the tools in term of performances, stability , documentation, etc.
Document type :
Conference papers
AVSS 2017 14th IEEE International Conference on Advanced Video and Signal based Surveillance, Aug 2017, Lecce, Italy. AVSS 2017 6p., 2017, 〈http://www.avss2017.org/〉
Liste complète des métadonnées

Cited literature [14 references]  Display  Hide  Download

https://hal.laas.fr/hal-01584100
Contributor : Jorge Francisco Madrigal Diaz <>
Submitted on : Friday, September 8, 2017 - 12:15:33 PM
Last modification on : Thursday, January 11, 2018 - 6:26:29 AM

File

Hyper-optimization-tools-Mauri...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01584100, version 1

Citation

Camille Maurice, Jorge Francisco Madrigal Diaz, Frederic Lerasle. Hyper-optimization tools comparison for parameter tuning applications. AVSS 2017 14th IEEE International Conference on Advanced Video and Signal based Surveillance, Aug 2017, Lecce, Italy. AVSS 2017 6p., 2017, 〈http://www.avss2017.org/〉. 〈hal-01584100〉

Share

Metrics

Record views

54

Files downloads

27