elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Sensor Fusion-Based Learning for the Improvement of Person Segmentation by Means of a Low-Resolution Thermal Infrared Array Sensor

Deckers, Niklas and Yildirim, Mehmet and Reulke, Ralf (2017) Sensor Fusion-Based Learning for the Improvement of Person Segmentation by Means of a Low-Resolution Thermal Infrared Array Sensor. ACM New York, NY, USA. International Conference on Computer Graphics and Digital Image Processing, 02. - 04. Juli, 2017, Prague. DOI: 10.1145/3110224.3110237 ISBN 978-1-4503-5236-9

[img] PDF - Registered users only
1MB

Official URL: http://dx.doi.org/10.1145/3110224.3110237

Abstract

Low-resolution thermal infrared array sensors can be used to detect human bodies and motion. Segmentation and deriving features from the segmented shape using such devices remains challenging. For improving and testing segmentation results, a sensor fusion approach using a Kinect sensor can be used to automatically receive ground-truth data. After performing a spatial calibration, experiments were performed to receive data for training and testing. A measure of difference to the ground-truth data is defined as error rate. Probability functions can be derived to determine whether a human is present, appearing or disappearing at a specific pixel. Optimization using Gaussian blur results in shapes ready for segmentation. A machine learning approach that uses conditional random fields on the ground-truth data generated by sensor fusion can be trained to reconstruct the ground-truth data. Testing different models showed that a spatial model that consists of a 4-connected neighborhood achieves better results than a temporal-spatial model.

Item URL in elib:https://elib.dlr.de/114179/
Document Type:Conference or Workshop Item (Speech)
Title:Sensor Fusion-Based Learning for the Improvement of Person Segmentation by Means of a Low-Resolution Thermal Infrared Array Sensor
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Deckers, Niklasniklas.deckers (at) hu-berlin.deUNSPECIFIED
Yildirim, MehmetHU-BerlinUNSPECIFIED
Reulke, RalfRalf.Reulke (at) dlr.deUNSPECIFIED
Date:2017
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
DOI :10.1145/3110224.3110237
Publisher:ACM New York, NY, USA
ISBN:978-1-4503-5236-9
Status:Published
Keywords:Image and video acquisition, Camera calibration, Video segmentation
Event Title:International Conference on Computer Graphics and Digital Image Processing
Event Location:Prague
Event Type:international Conference
Event Dates:02. - 04. Juli, 2017
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Erdbeobachtung
DLR - Research theme (Project):R - Vorhaben Optische Sensorik - Theorie, Kalibration, Verifikation
Location: Berlin-Adlershof
Institutes and Institutions:Institute of Optical Sensor Systems
Deposited By: Reulke, Prof. Dr. Ralf
Deposited On:21 Sep 2017 13:19
Last Modified:21 Sep 2017 13:19

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.