Research papers · Posted 2019.04.03 · Preprint
A Visual Neural Network for Robust Collision Perception in Vehicle Driving Scenarios
A Visual Neural Network for Robust Collision Perception in Vehicle Driving Scenarios
Overview
Inspired by locust LGMD neurons, the model adapts inhibition strength and excitation timing to background complexity. Synthetic stimuli, natural panoramic motion, and vehicle-crash videos evaluate visual collision-cue extraction.
Author-supplied source information
Author-supplied information on arXiv.
12 pages, 7 figures, conference, springer format
Version: v1