Deep Neural Network-Based Cooperative Visual Tracking Through Multiple Micro Aerial Vehicles

Eric Price, Guilherme Lawless, Roman Ludwig, Igor Martinovic, Heinrich Bulthoff, Michael J. Black, Aamir Ahmad

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Multicamera tracking of humans and animals in outdoor environments is a relevant and challenging problem. Our approach to it involves a team of cooperating microaerial vehicles (MAVs) with on-board cameras only. Deep neural networks (DNNs) often fail at detecting small-scale objects or those that are far away from the camera, which are typical characteristics of a scenario with aerial robots. Thus, the core problem addressed in this letter is how to achieve on-board, online, continuous, and accurate vision-based detections using DNNs for visual person tracking through MAVs. Our solution leverages cooperation among multiple MAVs and active selection of most informative regions of image. We demonstrate the efficiency of our approach through simulations with up to 16 robots and real-robot experiments involving two aerial robots tracking a person, while maintaining an active perception-driven formation. ROS-based source code is provided for the benefit of the community.

Original languageEnglish
Pages (from-to)3193-3200
Number of pages8
JournalIEEE Robotics and Automation Letters
Volume3
Issue number4
DOIs
Publication statusPublished - 2018 Oct 1

Fingerprint

Visual Tracking
Robot
Robots
Neural Networks
Antennas
Person
Camera
Cameras
Reactive Oxygen Species
Leverage
Animals
Scenarios
Deep neural networks
Demonstrate
Experiment
Simulation
Experiments
Vision

Keywords

  • aerial systems: Perception and autonomy
  • multirobot systems
  • Visual tracking

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Human-Computer Interaction
  • Biomedical Engineering
  • Mechanical Engineering
  • Control and Optimization
  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Deep Neural Network-Based Cooperative Visual Tracking Through Multiple Micro Aerial Vehicles. / Price, Eric; Lawless, Guilherme; Ludwig, Roman; Martinovic, Igor; Bulthoff, Heinrich; Black, Michael J.; Ahmad, Aamir.

In: IEEE Robotics and Automation Letters, Vol. 3, No. 4, 01.10.2018, p. 3193-3200.

Research output: Contribution to journalArticle

Price, Eric ; Lawless, Guilherme ; Ludwig, Roman ; Martinovic, Igor ; Bulthoff, Heinrich ; Black, Michael J. ; Ahmad, Aamir. / Deep Neural Network-Based Cooperative Visual Tracking Through Multiple Micro Aerial Vehicles. In: IEEE Robotics and Automation Letters. 2018 ; Vol. 3, No. 4. pp. 3193-3200.
@article{e91437a7b0f64088bc2857d4838e5dba,
title = "Deep Neural Network-Based Cooperative Visual Tracking Through Multiple Micro Aerial Vehicles",
abstract = "Multicamera tracking of humans and animals in outdoor environments is a relevant and challenging problem. Our approach to it involves a team of cooperating microaerial vehicles (MAVs) with on-board cameras only. Deep neural networks (DNNs) often fail at detecting small-scale objects or those that are far away from the camera, which are typical characteristics of a scenario with aerial robots. Thus, the core problem addressed in this letter is how to achieve on-board, online, continuous, and accurate vision-based detections using DNNs for visual person tracking through MAVs. Our solution leverages cooperation among multiple MAVs and active selection of most informative regions of image. We demonstrate the efficiency of our approach through simulations with up to 16 robots and real-robot experiments involving two aerial robots tracking a person, while maintaining an active perception-driven formation. ROS-based source code is provided for the benefit of the community.",
keywords = "aerial systems: Perception and autonomy, multirobot systems, Visual tracking",
author = "Eric Price and Guilherme Lawless and Roman Ludwig and Igor Martinovic and Heinrich Bulthoff and Black, {Michael J.} and Aamir Ahmad",
year = "2018",
month = "10",
day = "1",
doi = "10.1109/LRA.2018.2850224",
language = "English",
volume = "3",
pages = "3193--3200",
journal = "IEEE Robotics and Automation Letters",
issn = "2377-3766",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - Deep Neural Network-Based Cooperative Visual Tracking Through Multiple Micro Aerial Vehicles

AU - Price, Eric

AU - Lawless, Guilherme

AU - Ludwig, Roman

AU - Martinovic, Igor

AU - Bulthoff, Heinrich

AU - Black, Michael J.

AU - Ahmad, Aamir

PY - 2018/10/1

Y1 - 2018/10/1

N2 - Multicamera tracking of humans and animals in outdoor environments is a relevant and challenging problem. Our approach to it involves a team of cooperating microaerial vehicles (MAVs) with on-board cameras only. Deep neural networks (DNNs) often fail at detecting small-scale objects or those that are far away from the camera, which are typical characteristics of a scenario with aerial robots. Thus, the core problem addressed in this letter is how to achieve on-board, online, continuous, and accurate vision-based detections using DNNs for visual person tracking through MAVs. Our solution leverages cooperation among multiple MAVs and active selection of most informative regions of image. We demonstrate the efficiency of our approach through simulations with up to 16 robots and real-robot experiments involving two aerial robots tracking a person, while maintaining an active perception-driven formation. ROS-based source code is provided for the benefit of the community.

AB - Multicamera tracking of humans and animals in outdoor environments is a relevant and challenging problem. Our approach to it involves a team of cooperating microaerial vehicles (MAVs) with on-board cameras only. Deep neural networks (DNNs) often fail at detecting small-scale objects or those that are far away from the camera, which are typical characteristics of a scenario with aerial robots. Thus, the core problem addressed in this letter is how to achieve on-board, online, continuous, and accurate vision-based detections using DNNs for visual person tracking through MAVs. Our solution leverages cooperation among multiple MAVs and active selection of most informative regions of image. We demonstrate the efficiency of our approach through simulations with up to 16 robots and real-robot experiments involving two aerial robots tracking a person, while maintaining an active perception-driven formation. ROS-based source code is provided for the benefit of the community.

KW - aerial systems: Perception and autonomy

KW - multirobot systems

KW - Visual tracking

UR - http://www.scopus.com/inward/record.url?scp=85063307306&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063307306&partnerID=8YFLogxK

U2 - 10.1109/LRA.2018.2850224

DO - 10.1109/LRA.2018.2850224

M3 - Article

VL - 3

SP - 3193

EP - 3200

JO - IEEE Robotics and Automation Letters

JF - IEEE Robotics and Automation Letters

SN - 2377-3766

IS - 4

ER -