Foveal-pit inspired filtering of DVS spike response
This work addresses visual processing for neuromorphic vision systems, but it appears incremental as it combines existing models (DoG filters and spiking neural networks) on DVS data.
The paper tackled the problem of processing Dynamic Vision Sensor (DVS) recordings by applying foveal-pit inspired Difference of Gaussian filters to extract features, which were then classified using a spiking convolutional neural network, resulting in a method for visual pattern recognition.
In this paper, we present results of processing Dynamic Vision Sensor (DVS) recordings of visual patterns with a retinal model based on foveal-pit inspired Difference of Gaussian (DoG) filters. A DVS sensor was stimulated with varying number of vertical white and black bars of different spatial frequencies moving horizontally at a constant velocity. The output spikes generated by the DVS sensor were applied as input to a set of DoG filters inspired by the receptive field structure of the primate visual pathway. In particular, these filters mimic the receptive fields of the midget and parasol ganglion cells (spiking neurons of the retina) that sub-serve the photo-receptors of the foveal-pit. The features extracted with the foveal-pit model are used for further classification using a spiking convolutional neural network trained with a backpropagation variant adapted for spiking neural networks.