Depth camera driven mobile robot for human localization and following

Nikolaos Skordilis, Nikolaos Vidakis, Georgios Triantafyllidis, Lazaros Nalpantidis

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

Abstract

In this paper the design and the development of a mobile robot able to locate and then follow a human target is described. Both the integration of the required mechatronics
components and the development of appropriate software are covered. The main sensor of the developed mobile robot is an RGB-D camera. This sensor is usually combined with the appropriate middleware that can detect humans in a scene and
also provide the position of the detected human in the 3D space. One of the cues this middleware’s algorithms are using to detect humans is motion, thus resulting in many false detections when applied to data captured by a mobile platform. This work proposes the use of a special-tailored feed forward neural network to further process the initial detections, identifying and rejecting most false positives. Experimental results based on two self-captured data sets show the improved detection rate of
our two-stage human detector, as well as the efficient real-time performance of the proposed system for human localization and following.
Original languageEnglish
Title of host publication2nd AAU Workshop on Robotics
PublisherDepartment of Mech. Eng., AAU
Publication date2014
Publication statusPublished - 2014
Event2nd AAU Workshop on Robotics - Aalborg University, Aalborg, Denmark
Duration: 30 Oct 201330 Oct 2013
Conference number: 2

Conference

Conference2nd AAU Workshop on Robotics
Number2
LocationAalborg University
CountryDenmark
CityAalborg
Period30/10/201330/10/2013

Fingerprint

Middleware
Mobile robots
Cameras
Feedforward neural networks
Sensors
Detectors

Cite this

Skordilis, N., Vidakis, N., Triantafyllidis, G., & Nalpantidis, L. (2014). Depth camera driven mobile robot for human localization and following. In 2nd AAU Workshop on Robotics Department of Mech. Eng., AAU.
Skordilis, Nikolaos ; Vidakis, Nikolaos ; Triantafyllidis, Georgios ; Nalpantidis, Lazaros. / Depth camera driven mobile robot for human localization and following. 2nd AAU Workshop on Robotics. Department of Mech. Eng., AAU, 2014.
@inproceedings{acd6fa2d320d4cc496847507f27784e9,
title = "Depth camera driven mobile robot for human localization and following",
abstract = "In this paper the design and the development of a mobile robot able to locate and then follow a human target is described. Both the integration of the required mechatronicscomponents and the development of appropriate software are covered. The main sensor of the developed mobile robot is an RGB-D camera. This sensor is usually combined with the appropriate middleware that can detect humans in a scene andalso provide the position of the detected human in the 3D space. One of the cues this middleware’s algorithms are using to detect humans is motion, thus resulting in many false detections when applied to data captured by a mobile platform. This work proposes the use of a special-tailored feed forward neural network to further process the initial detections, identifying and rejecting most false positives. Experimental results based on two self-captured data sets show the improved detection rate ofour two-stage human detector, as well as the efficient real-time performance of the proposed system for human localization and following.",
author = "Nikolaos Skordilis and Nikolaos Vidakis and Georgios Triantafyllidis and Lazaros Nalpantidis",
year = "2014",
language = "English",
booktitle = "2nd AAU Workshop on Robotics",
publisher = "Department of Mech. Eng., AAU",

}

Skordilis, N, Vidakis, N, Triantafyllidis, G & Nalpantidis, L 2014, Depth camera driven mobile robot for human localization and following. in 2nd AAU Workshop on Robotics. Department of Mech. Eng., AAU, 2nd AAU Workshop on Robotics, Aalborg, Denmark, 30/10/2013.

Depth camera driven mobile robot for human localization and following. / Skordilis, Nikolaos; Vidakis, Nikolaos; Triantafyllidis, Georgios; Nalpantidis, Lazaros.

2nd AAU Workshop on Robotics. Department of Mech. Eng., AAU, 2014.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Depth camera driven mobile robot for human localization and following

AU - Skordilis, Nikolaos

AU - Vidakis, Nikolaos

AU - Triantafyllidis, Georgios

AU - Nalpantidis, Lazaros

PY - 2014

Y1 - 2014

N2 - In this paper the design and the development of a mobile robot able to locate and then follow a human target is described. Both the integration of the required mechatronicscomponents and the development of appropriate software are covered. The main sensor of the developed mobile robot is an RGB-D camera. This sensor is usually combined with the appropriate middleware that can detect humans in a scene andalso provide the position of the detected human in the 3D space. One of the cues this middleware’s algorithms are using to detect humans is motion, thus resulting in many false detections when applied to data captured by a mobile platform. This work proposes the use of a special-tailored feed forward neural network to further process the initial detections, identifying and rejecting most false positives. Experimental results based on two self-captured data sets show the improved detection rate ofour two-stage human detector, as well as the efficient real-time performance of the proposed system for human localization and following.

AB - In this paper the design and the development of a mobile robot able to locate and then follow a human target is described. Both the integration of the required mechatronicscomponents and the development of appropriate software are covered. The main sensor of the developed mobile robot is an RGB-D camera. This sensor is usually combined with the appropriate middleware that can detect humans in a scene andalso provide the position of the detected human in the 3D space. One of the cues this middleware’s algorithms are using to detect humans is motion, thus resulting in many false detections when applied to data captured by a mobile platform. This work proposes the use of a special-tailored feed forward neural network to further process the initial detections, identifying and rejecting most false positives. Experimental results based on two self-captured data sets show the improved detection rate ofour two-stage human detector, as well as the efficient real-time performance of the proposed system for human localization and following.

M3 - Article in proceeding

BT - 2nd AAU Workshop on Robotics

PB - Department of Mech. Eng., AAU

ER -

Skordilis N, Vidakis N, Triantafyllidis G, Nalpantidis L. Depth camera driven mobile robot for human localization and following. In 2nd AAU Workshop on Robotics. Department of Mech. Eng., AAU. 2014