Exploring Flood Filling Networks for Instance Segmentation of XXL-Volumetric and Bulk Material CT Data
- PDF / 3,042,246 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 41 Downloads / 170 Views
Exploring Flood Filling Networks for Instance Segmentation of XXL-Volumetric and Bulk Material CT Data Roland Gruber1 · Stefan Gerth1 Thomas Wittenberg2
· Joelle Claußen1
· Norbert Wörlein1
· Norman Uhlmann1
·
Received: 18 June 2020 / Accepted: 9 November 2020 © The Author(s) 2020
Abstract XXL-Computed Tomography (XXL-CT) is able to produce large scale volume datasets of scanned objects such as crash tested cars, sea and aircraft containers or cultural heritage objects. The acquired image data consists of volumes of up to and above 10,0003 voxels which can relate up to many terabytes in file size and can contain multiple 10,000 of different entities of depicted objects. In order to extract specific information about these entities from the scanned objects in such vast datasets, segmentation or delineation of these parts is necessary. Due to unknown and varying properties (shapes, densities, materials, compositions) of these objects, as well as interfering acquisition artefacts, classical (automatic) segmentation is usually not feasible. Contrarily, a complete manual delineation is error-prone and time-consuming, and can only be performed by trained and experienced personnel. Hence, an interactive and partial segmentation of so-called “chunks” into tightly coupled assemblies or sub-assemblies may help the assessment, exploration and understanding of such large scale volume data. In order to assist users with such an (possibly interactive) instance segmentation for the data exploration process, we propose to utilize delineation algorithms with an approach derived from flood filling networks. We present primary results of a flood filling network implementation adapted to non-destructive testing applications based on large scale CT from various test objects, as well as real data of an airplane and describe the adaptions to this domain. Furthermore, we address and discuss segmentation challenges due to acquisition artefacts such as scattered radiation or beam hardening resulting in reduced data quality, which can severely impair the interactive segmentation results. Keywords Instance segmentation · Flood filling networks · XXL-CT · Big data
1 Introduction
B
Roland Gruber roland.gruber@iis.fraunhofer.de Stefan Gerth stefan.gerth@iis.fraunhofer.de Joelle Claußen joelle.claussen@iis.fraunhofer.de Norbert Wörlein norbert.woerlein@iis.fraunhofer.de Norman Uhlmann norman.uhlmann@iis.fraunhofer.de Thomas Wittenberg thomas.wittenberg@fau.de
1
Fraunhofer IIS Development Center X-ray Technology (EZRT), Flugplatzstraße 75, 90768 Fürth, Germany
2
Chair of Computer Science 9 (Computer Graphics), Department of Computer Science, Friedrich-Alexander-Universität Erlangen-Nürnberg, Cauerstraße 11, 91058 Erlangen, Germany
Volumetric datasets produced by computed tomography (CT) may yield huge amounts of image information of the scanned specimen which are used in the field of non-destructive testing (NDT). The acquired image data consist of volumes of up to and above 10,0003 voxels which can relate up to terabytes in file siz
Data Loading...