A Neural Model of the Locust Visual System for Detection of Object Approaches with Real-World Scenes

M.S. Keil, E. Roca-Moreno, and Á. Rodriguez-Vázquez (Spain)


LGMD, neural architecture, collision detection, diffusion


In the central nervous systems of animals like pigeons and locusts, neurons were identified which signal objects ap proaching the animal on a direct collision course. Unrav eling the neural circuitry for collision avoidance, and iden tifying the underlying computational principles, is promis ing for building vision-based neuromorphic architectures, which in the near future could find applications in cars or planes. At the present there is no published model avail able for robust detection of approaching objects under real world conditions. Here we present a computational ar chitecture for signalling impending collisions, based on known anatomical data of the locust lobula giant move ment detector (LGMD) neuron. Our model shows robust performance even in adverse situations, such as with ap proaching low-contrast objects, or with highly textured and moving backgrounds. We furthermore discuss which com ponents need to be added to our model to convert it into a full-fledged real-world-environment collision detector.

Important Links:

Go Back