Concrete aggregate benchmark: Fid-Bau Portal

Fachinformationsdienst BAUdigital

Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik

Concrete aggregate benchmark

Coenen, Maximilian Alexander

The Concrete Aggregate Dataset consists of high resolution images acquired from 40 different concrete cylinders, cut lengthwise as to display the particle distribution in the concrete, with a ground sampling distance of 0.03mm. In order to train and evaluate approaches for the semantic segmentation of the concrete aggregate images, currently 17 of the 40 images have been annotated by manually associating one of the classes aggregate or suspension to each pixel. We encourage to use the remaining unlabelled images for semi-supervised segmentation approaches, in which unlabelled data is leveraged in addition to labelled training data in order to improve the segmentation performance.

Zugriff

Seitennavigation

Dokumentinformationen

Ähnliche Titel

Exportieren, teilen und zitieren

Concrete aggregate benchmark

Coenen, Maximilian Alexander

The Concrete Aggregate Dataset consists of high resolution images acquired from 40 different concrete cylinders, cut lengthwise as to display the particle distribution in the concrete, with a ground sampling distance of 0.03mm. In order to train and evaluate approaches for the semantic segmentation of the concrete aggregate images, currently 17 of the 40 images have been annotated by manually associating one of the classes aggregate or suspension to each pixel. We encourage to use the remaining unlabelled images for semi-supervised segmentation approaches, in which unlabelled data is leveraged in addition to labelled training data in order to improve the segmentation performance.

Concrete aggregate benchmark

Coenen, Maximilian Alexander

The Concrete Aggregate Dataset consists of high resolution images acquired from 40 different concrete cylinders, cut lengthwise as to display the particle distribution in the concrete, with a ground sampling distance of 0.03mm. In order to train and evaluate approaches for the semantic segmentation of the concrete aggregate images, currently 17 of the 40 images have been annotated by manually associating one of the classes aggregate or suspension to each pixel. We encourage to use the remaining unlabelled images for semi-supervised segmentation approaches, in which unlabelled data is leveraged in addition to labelled training data in order to improve the segmentation performance.

Zugriff

Seitennavigation

Dokumentinformationen

Ähnliche Titel

Exportieren, teilen und zitieren

Dokumentinformationen

Titel:

Concrete aggregate benchmark

Beteiligte:

Coenen, Maximilian Alexander (Autor:in)

Erscheinungsdatum:

2022

Format / Umfang:

1 Online-Ressource (204,9 MByte)

Anmerkungen:

3 Dateien im png-, zip-Format
Zuerst veröffentlicht: 15.04.2021
Gesehen am 25.07.2024

DOI:

https://doi.org/10.25835/0027789

Medientyp:

Forschungsdaten

Format:

Elektronische Ressource

Sprache:

Englisch

Lizenzbestimmungen:

https://creativecommons.org/licenses/by-nc/3.0/deed.de

Ähnliche Titel

Concrete Aggregate Benchmark

Coenen, Max | DataCite | 2021

Concrete aggregate

Kelley, J.W. | Engineering Index Backfile | 1929

AGGREGATE FOR CONCRETE, MANUFACTURING METHOD OF AGGREGATE FOR CONCRETE AND CONCRETE

YAMAMOTO KAZUNARI | Europäisches Patentamt | 2017

Freier Zugriff

Lightweight aggregate concrete

XIE NING / ZHENG KAI / GUO MIANHUI et al. | Europäisches Patentamt | 2021

Freier Zugriff

Proportioning concrete aggregate

Snow, F.C. | Engineering Index Backfile | 1914