Person recognition for service robotics applications

Abstract

The acceptance of service robots comes along with the ability to adapt to user specific preferences. This requires that a robot can determine the identity of the user. As for humans, robust user recognition is based on the identification of the face. However, despite the plethora of published work on face recognition that is robust against real world noise such as illumination, head alignment or facial expressions there is no robust off-the-shelf non-commercial software available to be used in typical robotics applications. Hence, this paper introduces a ready-to-use open-source ROS package providing a face detection and identification system that is comprising novel and state-of-the-art solutions to various aspects of face recognition while utilizing modern RGB-D sensors. This work demonstrates a solution for face recognition in robotic settings that is robust against varying illumination, gaze directions of the head, and facial expressions while operating with online performance. The paper provides a thorough evaluation of the face recognition system based on standard database tests and on real world scenarios regarding these criteria. The work described in this project was partially funded by the European project ACCOMPANY (Acceptable robotics COMPanions for AgeiNg Years). Grant agreement no.: 28762

3D Face Authentication Software Test Automation

“…These tests can be executed using a robotic arm [15]. Robots can be used with image processing algorithms for face recognition [16]. Roboticarm-based 3D reconstruction validation involves verifying the reconstructed 3D objects and executing tests of the algorithmic integrity of the computer vision algorithms that are used for the 3D image reconstruction [17].…”

ROS for Human-Robot Interaction

“…To the best of our knowledge, only two ROS projects have attempted to create a stand-alone toolset for HRI: the people 3 package, originally developed by Pantofaru in 2010-2012 (last code commit in 2015), and the cob_people_perception 4 package [3], developed in 2012-2014 in the frame of the EU project ACCOMPANY (and still maintained).…”

Multi-user identification and efficient user approaching by fusing robot and ambient sensors

“…Compensation measures for varying head pose such as multiple orientation modeling on the training data [27], [33] or face plane estimation [10], [34], [35] also increase the robustness of the identification system. The face recognition module used for this work bases on our earlier work on robust real-time face recognition systems [3].…”

“…The growing group of elderly people requires efficient and accurate care-giving at an affordable level, and robots may offer a solution in future. In recent years, researchers have been extensively working on the tasks of people detection [1], people tracking [2], face recognition [3], robot navigation, and robot controls, however, mainly as isolated tasks instead of combining these systems for real life applications. In this paper, we study these tasks jointly, and we propose a unified system that integrates these components in a home care scenario, as seen in Fig.…”

“…The RGB-D sensor provides both the color image from a color camera and the depth image from a range camera. By fusion of the depth image and color image, the face can be recognized robustly [3]. However, the RGB-D sensor is limited in both the range and the view angle.…”