Real-time people detection and mapping system for a mobile robot using a RGB-D sensor

In this paper, we present a robotic system capable of mapping indoor, cluttered environments and, simultaneously, detecting people and localizing them with respect to the map, in real-time, using solely a Red-Green-Blue and Depth (RGB-D) sensor, the Microsoft Kinect, mounted on top of a mobile robotic platform running Robot Operating System (ROS). The system projects depth measures in a plane for mapping purposes, using a grid-based Simultaneous Localization and Mapping (SLAM) approach, and pre-processes the sensor's point cloud to lower the computational load of people detection, which is performed using a classical technique based on Histogram of Oriented Gradients (HOG) features, and a linear Support Vector Machine (SVM) classifier. Results show the effectiveness of the approach and the potential to use the Kinect in real world scenarios.

• Publication year

  2014

• Venue

  International Conference on Informatics in Control, Automation and Robotics

• Publication date

  2014-09-01

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.5220/0005060604670474
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Victim detection and localisation in an urban disaster site

  2013cited by this paper
• Distributed multi-robot patrol: A scalable and fault-tolerant framework

  2013cited by this paper
• The CHOPIN project: Cooperation between human and rObotic teams in catastrophic incidents

  2013cited by this paper
• Stereo regions-of-interest selection for pedestrian protection: A survey

  2012cited by this paper
• Tracking people within groups with RGB-D data

  2012influential reference
• G2o: A general framework for graph optimization

  2011cited by this paper
• People detection in RGB-D data

  2011cited by this paper
• Distinctive Image Features from Scale-Invariant Keypoints Abstract by Matthijs Dorst Based on the paper by

  2011cited by this paper
• 3D is here: Point Cloud Library (PCL)

  2011cited by this paper
• RGB-D Mapping: Using Depth Cameras for Dense 3D Modeling of Indoor Environments

  2010cited by this paper
• LIDAR and vision‐based pedestrian detection system

  2009cited by this paper
• ROS: an open-source Robot Operating System

  2009cited by this paper
• A Fast Stereo-based System for Detecting and Tracking Pedestrians from a Moving Vehicle

  2009cited by this paper
• Robust Ego-Motion Estimation with ToF Cameras

  2009cited by this paper
• Multiple-Person Tracking for a Mobile Robot Using Stereo

  2009cited by this paper
• FrameSLAM: From Bundle Adjustment to Real-Time Visual Mapping

  2008cited by this paper
• Keypoint Signatures for Fast Learning and Recognition

  2008cited by this paper
• Pose estimation and map building with a Time-Of-Flight-camera for robot navigation

  2008cited by this paper
• Mapping Large Loops with a Single Hand-Held Camera

  2007cited by this paper
• Improved Techniques for Grid Mapping With Rao-Blackwellized Particle Filters

  2007cited by this paper
• Machine Learning for High-Speed Corner Detection

  2006cited by this paper
• Histograms of oriented gradients for human detection

  2005influential reference
• Improving Simultaneous Mapping and Localization in 3D Using Global Constraints

  2005cited by this paper
• Distinctive Image Features from Scale-Invariant Keypoints

  2004cited by this paper
• Learning object detection from a small number of examples: the importance of good features

  2004cited by this paper
• Visual Tracking of Silhouettes for Human-Robot Interaction

  2003cited by this paper
• A Solution to the Simultaneous Localisation and Map Building (SLAM) Problem

  2001cited by this paper
• Bundle Adjustment - A Modern Synthesis

  1999cited by this paper
• TRANSPORTATION RESEARCH. PART C, EMERGING TECHNOLOGIES

  1993cited by this paper
• Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

  1981cited by this paper
• Ieee Transactions on Intelligent Transportation Systems the Benefits of Dense Stereo for Pedestrian Detection

  year unknowncited by this paper
• Transactions on Systems, Man, and Cybernetics, Part B a Bayesian Framework for Active Artificial Perception Final Preprint Version a Bayesian Framework for Active Artificial Perception

  year unknowncited by this paper

• IoT-based human detection for fast earthquake response and rescue

  2024cites this paper
• Design of Autonomous Wireless Sensor Network Using Mobile Robots for Intrusion Detection and Border Surveillance

  2023cites this paper
• ROS-Based Human Detection and Tracking from a Wireless Controlled Mobile Robot Using Kinect

  2019cites this paper
• A Guide for 3D Mapping with Low-Cost Sensors Using ROS

  2019cites this paper
• A Study on the Deployment of a Service Robot in an Elderly Care Center

  2018cites this paper
• Knowledge-Based Framework for Human-Robots Collaborative Context Awareness in USAR Missions

  2016cites this paper
• SocialRobot: An interactive mobile robot for elderly home care

  2015cites this paper