Two- and Three-Dimensional Benchmarks for Particle Detection from an Industrial Rotary Kiln Combustion Chamber Based on Light-Field-Camera Recording

Markus Vogelbacher (), Miao Zhang, Krasimir Aleksandrov, Hans-Joachim Gehrmann and Jörg Matthes
Additional contact information
Markus Vogelbacher: Institute for Automation and Applied Informatics, Karlsruhe Institute of Technology (KIT), Hermann-von-Helmholtz-Platz 1, 76344 Eggenstein-Leopoldshafen, Germany
Miao Zhang: Institute for Automation and Applied Informatics, Karlsruhe Institute of Technology (KIT), Hermann-von-Helmholtz-Platz 1, 76344 Eggenstein-Leopoldshafen, Germany
Krasimir Aleksandrov: Institute for Technical Chemistry, Karlsruhe Institute of Technology (KIT), Hermann-von-Helmholtz-Platz 1, 76344 Eggenstein-Leopoldshafen, Germany
Hans-Joachim Gehrmann: Institute for Technical Chemistry, Karlsruhe Institute of Technology (KIT), Hermann-von-Helmholtz-Platz 1, 76344 Eggenstein-Leopoldshafen, Germany
Jörg Matthes: Institute for Automation and Applied Informatics, Karlsruhe Institute of Technology (KIT), Hermann-von-Helmholtz-Platz 1, 76344 Eggenstein-Leopoldshafen, Germany

Data, 2022, vol. 7, issue 12, 1-16

Abstract: This paper describes a benchmark dataset for the detection of fuel particles in 2D and 3D image data in a rotary kiln combustion chamber. The specific challenges of detecting the small particles under demanding environmental conditions allows for the performance of existing and new particle detection techniques to be evaluated. The data set includes a classification of burning and non-burning particles, which can be in the air but also on the rotary kiln wall. The light-field camera used for data generation offers the potential to develop and objectively evaluate new advanced particle detection methods due to the additional 3D information. Besides explanations of the data set and the contained ground truth, an evaluation procedure of the particle detection based on the ground truth and results for an own particle detection procedure for the data set are presented.

Keywords: benchmark; 3D point cloud; particle detection; light-field camera; refuse-derived fuels (search for similar items in EconPapers)
JEL-codes: C8 C80 C81 C82 C83 (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2306-5729/7/12/179/pdf (application/pdf)
https://www.mdpi.com/2306-5729/7/12/179/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jdataj:v:7:y:2022:i:12:p:179-:d:1002020

Access Statistics for this article

Data is currently edited by Ms. Cecilia Yang

More articles in Data from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().