@article{ref1,
title="Deep CNN, body pose, and body-object interaction features for drivers' activity monitoring",
journal="IEEE transactions on intelligent transportation systems",
year="2022",
author="Behera, Ardhendu and Wharton, Zachary and Keidel, Alexander and Debnath, Bappaditya",
volume="23",
number="3",
pages="2874-2881",
abstract="Automatic recognition and prediction of in-vehicle human activities has a significant impact on the next generation of driver assistance and intelligent autonomous vehicles. In this article, we present a novel single image driver action recognition algorithm inspired by human perception that often focuses selectively on parts of the images to acquire information at specific places which are distinct to a given task. Unlike existing approaches, we argue that human activity is a combination of pose and semantic contextual cues. In detail, we model this by considering the configuration of body joints, their interaction with objects being represented as a pairwise relation to capture the structural information. Our body-pose and body-object interaction representation is built to be semantically rich and meaningful, which is highly discriminative even though it is coupled with a basic linear SVM classifier. We also propose a Multi-stream Deep Fusion Network (MDFN) for combining high-level semantics with CNN features. Our experimental results demonstrate that the proposed approach significantly improves the drivers' action recognition accuracy on two exacting datasets.<p /> <p>Language: en</p>",
language="en",
issn="1524-9050",
doi="10.1109/TITS.2020.3027240",
url="http://dx.doi.org/10.1109/TITS.2020.3027240"
}