From Depth Data to Head Pose Estimation: a Siamese approach
This work addresses head pose estimation for applications like driver attention monitoring, representing an incremental improvement over existing methods.
The paper tackles head pose estimation by using a Siamese convolutional neural network with a novel loss function to directly regress poses from depth data, achieving improved accuracy over state-of-the-art methods and real-time performance on public datasets.
The correct estimation of the head pose is a problem of the great importance for many applications. For instance, it is an enabling technology in automotive for driver attention monitoring. In this paper, we tackle the pose estimation problem through a deep learning network working in regression manner. Traditional methods usually rely on visual facial features, such as facial landmarks or nose tip position. In contrast, we exploit a Convolutional Neural Network (CNN) to perform head pose estimation directly from depth data. We exploit a Siamese architecture and we propose a novel loss function to improve the learning of the regression network layer. The system has been tested on two public datasets, Biwi Kinect Head Pose and ICT-3DHP database. The reported results demonstrate the improvement in accuracy with respect to current state-of-the-art approaches and the real time capabilities of the overall framework.