Bio-inspired clustering of moving objects

Nowadays several researches have implemented various techniques to solve the problem of clustering data. In this paper we present a visual bio-inspired approach to clustering based on the Conepvim [1] Model for visual perception of moving objects in the primary visual cortex (VI) of the human brain. This model uses the Gabor-like filters to detect motion, estimates the global speed, direction and trajectory. We have extended this model with a bio-inspired algorithm: the Self-Organization Maps (SOM) to define how many objects in motion there are in the sequence. Our approach is totally bio-inspired and it has been evaluated on natural sequences of images