SCENE UNDERSTANDING USING A NEUROSYNAPTIC SYSTEM

摘要

Embodiments of the invention provide a method for scene understanding based on a sequence of image frames. The method comprises converting each pixel of each image frame to neural spikes, and extracting features from the sequence of image frames by processing neural spikes corresponding to pixels of the sequence of image frames. The method further comprises encoding the extracted features as neural spikes, and classifying the extracted features.

主权项

1. A method, comprising:
for at least one image frame of a sequence of image frames:
converting, utilizing a first set of neurosynaptic core circuits, each pixel of the image frame to one or more corresponding neural spikes;processing, utilizing a second set of neurosynaptic core circuits, the neural spikes to extract one or more salient features from the image frame;generating a map representing the salient features extracted; anddetecting presence of an object of interest in the image frame based on the map.