Deep Head Pose Estimation from Depth Data for In-car Automotive Applications

TL;DR

This paper presents a deep learning-based head pose estimation method using raw depth data, achieving state-of-the-art accuracy and real-time performance for in-car automotive applications.

Contribution

It introduces a CNN that estimates head pose directly from raw depth data without relying on facial features or landmarks, which is novel in the field.

Findings

Achieves state-of-the-art accuracy on Biwi Kinect dataset.

Operates in real-time suitable for automotive use.

Does not depend on facial landmarks or visual features.

Abstract

Recently, deep learning approaches have achieved promising results in various fields of computer vision. In this paper, we tackle the problem of head pose estimation through a Convolutional Neural Network (CNN). Differently from other proposals in the literature, the described system is able to work directly and based only on raw depth data. Moreover, the head pose estimation is solved as a regression problem and does not rely on visual facial features like facial landmarks. We tested our system on a well known public dataset, Biwi Kinect Head Pose, showing that our approach achieves state-of-art results and is able to meet real time performance requirements.