Head Detection with Depth Images in the Wild

TL;DR

This paper presents a novel deep learning-based method for head detection using depth images, addressing challenges like illumination variability and scale, and demonstrating superior performance over existing methods in unconstrained environments.

Contribution

The paper introduces a new deep learning approach for head detection in depth images, utilizing two public datasets for training and testing, and achieving improved accuracy over state-of-the-art methods.

Findings

Outperforms existing depth image head detection methods

Effective in unconstrained, real-world environments

Utilizes depth information to handle scale and illumination issues

Abstract

Head detection and localization is a demanding task and a key element for many computer vision applications, like video surveillance, Human Computer Interaction and face analysis. The stunning amount of work done for detecting faces on RGB images, together with the availability of huge face datasets, allowed to setup very effective systems on that domain. However, due to illumination issues, infrared or depth cameras may be required in real applications. In this paper, we introduce a novel method for head detection on depth images that exploits the classification ability of deep learning approaches. In addition to reduce the dependency on the external illumination, depth images implicitly embed useful information to deal with the scale of the target objects. Two public datasets have been exploited: the first one, called Pandora, is used to train a deep binary classifier with face and non-face images. The second one, collected by Cornell University, is used to perform a cross-dataset test during daily activities in unconstrained environments. Experimental results show that the proposed method overcomes the performance of state-of-art methods working on depth images.