Luis Horna Carranza and Tianqi Wei
Thu 23 Mar 2017, 12:45 - 13:45
IF 4.31/4.33

If you have a question about this talk, please contact: Magda Nowak (mnowak)

pastries will be served, this week sponsored by the kind donation of IPAB visiting scholar, Zhengang Nie

 

Speaker: Luis Horna Carranza

Title: Plane labelling trinocular stereo matching with baseline recovery

Abstract:

We present an algorithm which recovers the rigid transformation that describes the displacement of a binocular stereo rig in a scene, and uses this to include a third image to perform dense trinocular stereo matching and reduce some of the ambiguities inherent to binocular stereo. The core idea of the proposed algorithm is the assumption that the binocular baseline is projected to the third view, and thus can be used to constrain the transformation estimation of the stereo rig. Our approach shows improved performance over binocular stereo, and the accuracy of the recovered motion allows to compute optical flow from a single disparity map.

 

Speaker: Tianqi Wei

Title: A chaotic operant learning model inspired by the insect mushroom body

Abstract:

Operant learning is a type of learning in which a behaviour is adjusted according to its consequences. An aspect of the learning is to generate a variety of “spontaneous” motions or behaviours. Chaotic central pattern generators (Chaotic CPG) can be sources of them. Based on it, a model inspired by insects’ mushroom body is proposed and simulated with a maggot-like agent. In the model, mushroom body output neurons work as a chaotic CPG modulating another CPG in a lower level, which controls the agent’s turning. The simulation results show that the model can generate chaotic behaviours or motions and learn which is with reward.