Modeling visual perception of motion by connectionist networks offers various areas of research for the development of real-time models of dynamic perception-action. In this paper we present the bases of a bio-inspired connectionist approach that is part of our development of neural networks applied to autonomous robotics. Our model of visual perception of motion is based on a causal adaptation of spatiotemporal Gabor lters. We use our causal spatiotemporal lters within a modular and strongly localized architecture that performs a shunting inhibition mechanism. This model has been evaluated on arti cial as well as natural image sequences. || La modélisation de la perception visuelle du mouvement par des réseaux connexionnists offre différents aires de recherche pour le développement en temps réel de modèles pour la dynamique perception action. Dans cet article nous présentons les fundaments d