Learning Pre-attentive Driving Behaviour from Holistic Visual Features

Abstract. The aim of this paper is to learn driving behaviour by associating the actions recorded from a human driver with pre-attentive visual input, implemented using holistic image features (GIST). All images are labelled according to a number of driving

• Type: Conference
• Year: 2010
• Where: ECCV
• Keywords: Activation Maps, Computer Vision, Driver's Actions, ECCV 2010, Pre-attentive Visual Input