Title :

Meta-parameters Exploration for Unsupervised Event-based Motion Analysis

Author(s) :

Oudjail, Veis [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Martinet, Jean [Auteur]
Université Côte d'Azur [UniCA]
Scalable and Pervasive softwARe and Knowledge Systems [Laboratoire I3S - SPARKS]
Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis [I3S]

Conference title :

15th International Conference on Computer Vision Theory and Applications

City :

Valletta

Country :

France

Start date of the conference :

2020-02-27

Publisher :

SCITEPRESS - Science and Technology Publications

English keyword(s) :

Motion Analysis
Spiking Neural Networks
Event-based sensor
parameter exploration

HAL domain(s) :

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

English abstract : [en]

Being able to estimate motion features is an essential step in dynamic scene analysis. Optical flow typically quantifies the apparent motion of objects. Motion features can benefit from bio-inspired models of mammalian ...
Show more >Being able to estimate motion features is an essential step in dynamic scene analysis. Optical flow typically quantifies the apparent motion of objects. Motion features can benefit from bio-inspired models of mammalian retina, where ganglion cells show preferences to global patterns of direction, especially in the four cardinal translatory directions. We study the meta-parameters of a bio-inspired motion estimation model using event cameras, that are bio-inspired vision sensors that naturally capture the dynamics of a scene. The motion estimation model is made of an elementary Spiking Neural Network, that learns the motion dynamics in a non-supervised way through the Spike-Timing-Dependent Plasticity. After short simulation times, the model can successfully estimate directions without supervision. Some of the advantages of such networks are the non-supervised and continuous learning capabilities, and also their implementability on very low-power hardware. The model is tuned using a synthetic dataset generated for parameter estimation, made of various patterns moving in several directions. The parameter exploration shows that attention should be given to model tuning, and yet the model is generally stable over meta-parameter changes.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL