PRIMORIS      Contacts      FAQs      INSTICC Portal


The role of the tutorials is to provide a platform for a more intensive scientific exchange amongst researchers interested in a particular topic and as a meeting point for the community. Tutorials complement the depth-oriented technical sessions by providing participants with broad overviews of emerging fields. A tutorial can be scheduled for 1.5 or 3 hours.

Robust Motion Detection for Human-Robot Interaction
Lecturer(s): Dr. Ester Martinez-Martin, Jaume-I University, Spain
Estimated Session Time: 3 hours

Dr. Ester Martinez-Martin
Jaume-I University

Robust Motion Detection for Human-Robot Interaction

The paradigm shift of Robotics moving toward autonomous robots meeting human needs in real world settings requires to develop robot interaction skills. So, a synergy of different disciplines is essential to achieve that goal. In particular, Human-Robot Interaction (HRI), the study of how humans interact with robots in daily environments, aims to endow robots with the necessary interactive abilities. So, the first stage is efficient people detection and tracking. In this sense, vision plays a main role due to the information it can provide. Despite the wide research on this topic, robot applications require a trade-off between efficiency and runtime. For that reason, it is necessary to design visual systems to efficiently detect and track people in real scenarios, but without culminating in a time-consumption process. In this context, motion plays a main role because it provides a stimulus for detecting moving elements (e.g. people) in the observed scene. Moreover, motion allows to obtain other characteristics such as, for instance, object shape, speed or trajectory, which are meaningful for detection and recognition. Nevertheless, the motion observable in a visual input could be due to different factors: (partial or total) occlusions, movement of the imaged objects (targets and/or vacillating background elements), movement of the observer, variable illumination or motion of the light sources, or a combination of (some of) them. Therefore, image analysis for motion detection will be contingent upon the considered factors. Therefore, the purpose of this tutorial is to make the attendee aware of the problems to be overcome for robust human detection and tracking as well as the existing methods. It will be partially based on our recent book E. Martínez-Martín & A.P. del Pobil, Robust Motion Detection in Real-Life Scenarios, Springer, 2012. ISBN: 978–1–4471–4215–7

Motion Detection Human-Robot Interaction

Aims and Learning Objectives
In this tutorial we propose to analyse the motion detection problem whose solution offers the opportunity of performing a visual perception in real-time and an accurate people/object distinction ( i.e., people move in a different way than robots do), in order to achieve a solution for a good environment adaptation of the system as it properly copes with most of the vision problems when dynamic, non-structured environments are considered. For that, the way sensors obtain images of the world, in terms of resolution distribution and pixel neighbourhood will be studied, so that a proper spatial analysis of motion could be carried out. Then, background maintenance for robust target motion detection will be analysed. On this matter, two different situations will be considered: (1) a fixed camera observes a constant background where interest objects are moving; and, (2) a still camera observes interest objects moving in a dynamic background. The reason for this distinction lies in developing, from the first analysis, an attentional mechanism which removes the constraint of observing a scene free of foreground elements during several seconds when a reliable initial background model is obtained, since that situation cannot be guaranteed when a robotic system works in a dynamic, unknown environment. Furthermore, to achieve a robust background maintenance system, other canonical problems are addressed to successfully deal with (gradual and global) changes in illumination, distinction between foreground and background elements in terms of motion and motionless, non-uniform vacillating backgrounds, etc. Efficient people detection and tracking can be a preliminary step to increase efficiency by selecting relevant parts of an image to be processed by other systems such as: gesture detection and recognition; face detection, recognition and tracking; understanding human activity, etc. Also, motion detection can play a fundamental role in safety and attentional mechanisms, possible by adding a panoramic camera for detecting saliency to guide the saccadic movements in an ocular- motor robot system towards the person target. Both these issues will be studied. The tutorial will discuss recent advances with respect to state-of-the-art computer vision approaches to people detection by using motion as a primary cue. An extensive set of experiments and applications using different testbeds of real environments with real and/or virtual targets will be analysed.

Target Audience
This tutorial is primarily addressed to engineering and computer science graduate students interested in this topic, who usually find it difficult to get introduced in the basic vision methods based on motion cues that are relevant to human-robot interaction research. As secondary audience, practitioners in HRI, who are interested in applying this technology.

Detailed Outline
  • 1. Introduction
    • a. Problem Statement
    • b. Analysis of the canonical problems for visual human detection and tracking
  • 2. Review of existing methods
  • 3. Motion detection in static backgrounds
  • 4. Motion detection in general, real scenarios
  • 5. People tracking
  • 6. HRI principles combined with computer vision methods
  • 7. Safety and attentional mechanism
    • 8. Practical considerations for real applications
    • a. Human Action Recognition
    • b. Others

3 hours

Biography of Dr. Ester Martinez-Martin
Ester Martínez-Martín is Assistant Professor at Jaume-I University (Spain) and member of the Robotic Intelligence Laboratory. She holds a B.Sc. in Computer Science (Engineering in Computer Science, 2004) and a Ph.D. in Engineering (Robotics, 2011), both from the Jaume-I University. Her education is completed with postgraduate certificates in different topics such as computer design, programming languages and web design. She has been involved in robotics research, being part of several national and international projects (e.g. Eyeshots (Heterogeneous 3D Perception across Visual Fragments), and GRASP (Emergence of cognitive grasping through emulation, introspection and surprise)). Her research background has been extended by attending several relevant international conferences and schools, as well as being in University of Genoa and in SungKyunKwan University for research stays. So, she is author and co-author of several scientific publications – including one book Robust motion detection in real-life scenarios (Springer), "Computer Vision Methods for Robot Tasks: Motion Detection, Depth Estimation and Tracking" (AICom), "A Panoramic vision system for human-robot interaction" (HRI 2010), "Safety for human-robot interaction in dynamic environments" (ISAM 2009) – and editor of one book: "Swarm Robotics" (In-Tech). She has been the Organization Chair of the 12th International UJI Robotics School on Perceptual Robotics for Humanoids (2012), and has collaborated in some conference committees and outreach activities. Recently, she has been invited to give a talk on this topic in Portugal.