Synthetic Vision
We are developing synthetic models of the mammal visual system in hardware. Our model features mechanisms of recognition and catecorization of objects, bottom-up and top-down attention, target selection, saliency.
We design custom hardware that can implement these models and perform in real-time on megapixel-size cameras as well as state-of-the-art neuromorphic image sensors.
Bio-inspired object categorization
We are developing bio-inspired neuromorphic algorithms and neural processing hardware to allow fast categorization of hundreds of objects in real time in multi-megapixel images, videos and custom event-based cameras. Applications are in robotic vision, security, monitoring and assisted living and remote care of elderly and patients.
The algorithm is described in a recent paper. We have used temporal-difference image sensors to recognize objects and people's postures in real time. Our algorithm also works on any regular off-the-shelf camera and imeage sensor array.
The same algorithm is lightweight and can be implemented in embedded platforms, as sensor networks and cellular phones.
Here is a link to our demonstration on a Apple iPhone cellular phone platform of the ultra-low computation object recognition engine:
We have also developed versatile code that can be used by other colleagues. Here is a link to our demonstration program of our bio-inspired object recognition engine Windows PC and MAC OS X.