2024-03-29T14:29:47Z
https://zenodo.org/oai2d
oai:zenodo.org:4683073
2021-04-15T12:27:20Z
user-robotunion
user-eu
Lassen, Aske Bach
2021-04-13
<p>Pig intestines used as natural sausage casings are currently cleaned and then sent from Europe to 12 China for manual quality control and grading. This process can be made greener by automation that 13 removes the need for transport. A suitable machine now exists, able to check the casings for leaks 14 and to grade and cut them to standard lengths. The one remaining quality control process is 15 checking for impurities left by the cleaning process. A sophisticated vision system and a deep 16 learning system is needed. 17<br>
After preliminary lighting tests, images of cleaned pig intestines destined for sausage casings were 18 examined manually for impurities. Pixels depicting impurities were labelled and mask impurity 19 images produced as "ground truth". Two deep learning methods were applied in order to predict the 20 areas of impurities in these images: Halcon with SOLOv2 semantic segmentation and Detectron2 21 with Mask-R-CNN instance segmentation. Despite the over-abundance of background pixels, both 22 algorithms learned the segmentation. Detectron2 was more accurate but Halcon found more of the 23 impurities, which was attributed to the difference between the segmentation types: semantic vs 24 instance. Since the aim of this work is to produce clean intestines for use in the food industry, false 25 positives are more acceptable than false negatives, so Halcon was chosen.</p>
https://doi.org/10.5281/zenodo.4683073
oai:zenodo.org:4683073
eng
Zenodo
https://zenodo.org/communities/robotunion
https://zenodo.org/communities/eu
https://doi.org/10.5281/zenodo.4683072
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
Halcon, Detectron2, sausage casings, quality control, detection of impurities
Comparing Halcon and Detectron2 for detecting impurities in pig 1 intestines used as natural sausage casings
info:eu-repo/semantics/report
oai:zenodo.org:4687163
2021-04-15T12:27:20Z
user-robotunion
Lassen, Aske Bach
2021-04-14
<p>In this paper we test 15 point-cloud registration algorithms (including four iterative closest point (ICP) and three coherent point drift (CPD) variants) to find which ones give least registration error and are fastest for our use case: detecting the intersection point between two rods for an industrial robot application. The algorithms are all in common use. The data comprises both real and simulation-adjusted images of approximately perpendicular metal rods taken from different angles.</p>
https://doi.org/10.5281/zenodo.4687163
oai:zenodo.org:4687163
eng
Zenodo
https://zenodo.org/communities/robotunion
https://doi.org/10.5281/zenodo.4687162
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
3D point cloud, registration algorithms, localization, robot action
Comparing algorithms for point cloud registration for accurately locating rod intersections for robot action
info:eu-repo/semantics/report