Moving object detection for unconstrained low-altitude aerial videos, a pose-independent detector based on artificial flow

Thomas Castelli; Alain Trémeau; Hubert Konik; Eric Dinet

Moving object detection for unconstrained low-altitude aerial videos, a pose-independent detector based on artificial flow

Thomas Castelli Alain Trémeau ¹ Hubert Konik ¹ Eric Dinet ¹

1 LHC - Laboratoire Hubert Curien [Saint Etienne]

Abstract : Automatic detection of moving objects is an important task for aerial surveillance. It has been a popular and well-studied subject for the computer vision community, but is still a challenge. The method we introduce targets surveillance low-altitude mini and micro-UAVs. We take advantage of the inherent image motion on footage captured by such aerial vehicles. Our method confronts Optical Flow vectors and an estimated Flow in order to detect independently moving pixels. This motion-based approach is robust to operational conditions and to the geometric properties of the scene. The efficiency of the method was computed on the VIVID database. The moving areas detected will make the tracking task more robust and efficient.

Type de document :

Communication dans un congrès

9th International Symposium on Image and Signal Processing and Analysis, Sep 2015, Zagreb, Croatia

Domaine :

Informatique [cs] / Vision par ordinateur et reconnaissance de formes [cs.CV]

Liste complète des métadonnées

https://hal-ujm.archives-ouvertes.fr/ujm-01388681
Contributeur : Eric Dinet <>
Soumis le : jeudi 27 octobre 2016 - 13:49:37
Dernière modification le : jeudi 26 juillet 2018 - 01:11:23

Moving object detection for unconstrained low-altitude aerial videos, a pose-independent detector based on artificial flow

Identifiants

Collections

Citation

Exporter

Métriques

24

Contact

Moving object detection for unconstrained low-altitude aerial videos, a pose-independent detector based on artificial flow

Identifiants

Collections

Citation

Exporter

Partager

Métriques

24

Contact