Real-time driver behaviour recognition
Abstract
Low inference latency and correct response to the environment change play a key role in the automated driving system, especially in the current level 3 automated driving, where drivers are still expected to take control of the vehicle if there is a request to intervene. Therefore it is of great importance to achieve the fast and reliable recognition of driver’s non-driving-related activities (NDRAs) for designing an intelligent take-over strategy to ensure a safe, smooth and rapid control transition. Most of the existing related methods were not designed for edge computing platforms so their performance in real deployment is untested and not optimised. This chapter proposes a novel lightweight ...
Get Human-Machine Interaction for Automated Vehicles now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
