The Hodgkin-Huxley neuron model for motion detection in image sequences

Hayat Yedjour (1) , Boudjelal Meftah (2) , Dounia Yedjour (1) , Olivier Lézoray (3)

1 USTO MB - Université des sciences et de la Technologie d'Oran Mohamed Boudiaf [Oran]
2 University of Mascara - Department of Computer Science
3 Equipe Image - Laboratoire GREYC - UMR6072

In this paper, we consider a biologically inspired spiking neural network model for motion detection. The proposed model simulates the neurons' behavior in the cortical area MT to detect different kinds of motion in image sequences. We choose the conductance-based neuron model of the Hodgkin-Huxley to define MT cell responses. Based on the center-surround antagonism of MT receptive fields, we model the area MT by its great proportion of cells with directional selective responses. The network's spiking output corresponds to an MT neuron population's firing rates and enables to extract motion boundaries. We conduct several experiments on real image sequences. The experimental results show the proposed network's ability to segregate multiple moving objects from an image sequence and reproduce the MT cells' responses. We perform a quantitative evaluation on the YouTube Motion Boundaries (YMB) dataset, and we compare the result to stateof-the-art methods for boundary detection in videos: boundary flow estimation (BF) and temporal boundary difference (BD). The proposed network model provides the best results on YMB compared to BF and BD methods.

Mots clés: Visual system; Spiking neural networks; Hodgkin-Huxley model; Motion detection; Receptive field

Domaines: Traitement des images [eess.IV]

Hayat Yedjour, Boudjelal Meftah, Dounia Yedjour, Olivier Lézoray. The Hodgkin-Huxley neuron model for motion detection in image sequences. Neural Computing and Applications, 2022, 34 (2), pp.1123-1133. ⟨10.1007/s00521-021-06446-0⟩. ⟨hal-03331961⟩