POSEidon: Face-from-Depth for Driver Pose Estimation
This work addresses the problem of monitoring driver attention for automotive safety, though it appears incremental as it builds on existing depth-based methods with specific enhancements.
The authors tackled driver head and upper-body pose estimation in challenging conditions by proposing a deep learning framework that uses depth images and a novel Face-from-Depth approach for face reconstruction. Their method outperforms recent state-of-the-art works, achieving real-time performance at over 30 frames per second on public and new datasets.
Fast and accurate upper-body and head pose estimation is a key task for automatic monitoring of driver attention, a challenging context characterized by severe illumination changes, occlusions and extreme poses. In this work, we present a new deep learning framework for head localization and pose estimation on depth images. The core of the proposal is a regression neural network, called POSEidon, which is composed of three independent convolutional nets followed by a fusion layer, specially conceived for understanding the pose by depth. In addition, to recover the intrinsic value of face appearance for understanding head position and orientation, we propose a new Face-from-Depth approach for learning image faces from depth. Results in face reconstruction are qualitatively impressive. We test the proposed framework on two public datasets, namely Biwi Kinect Head Pose and ICT-3DHP, and on Pandora, a new challenging dataset mainly inspired by the automotive setup. Results show that our method overcomes all recent state-of-art works, running in real time at more than 30 frames per second.