Flexible Objektdetektion in 3D-Lidar-Scans/Flexible object detection in 3D lidar scans – Development of an object recognition system for creating and updating digital models

Inhaltsverzeichnis

Bibliographische Infos


Cover der Ausgabe: wt Werkstattstechnik online Jahrgang 113 (2023), Heft 03
Open Access Vollzugriff

wt Werkstattstechnik online

Jahrgang 113 (2023), Heft 03


Autor:innen:
Verlag
VDI fachmedien, Düsseldorf
Copyrightjahr
2023
ISSN-Online
1436-4980
ISSN-Print
1436-4980

Kapitelinformationen


Open Access Vollzugriff

Jahrgang 113 (2023), Heft 03

Flexible Objektdetektion in 3D-Lidar-Scans/Flexible object detection in 3D lidar scans – Development of an object recognition system for creating and updating digital models


Autor:innen:
ISSN-Print
1436-4980
ISSN-Online
1436-4980


Kapitelvorschau:

Eine wachsende Zahl von Unternehmen setzt auf Digitalisierung, um ihre Prozesse zu optimieren und angesichts zunehmender Unsicherheiten resilienter zu werden. Die Erzeugung und Pflege der dazu eingesetzten digitalen Modelle ist aber mit hohem Aufwand verbunden. Eine flexible KI-basierte Objekterkennung, die nur geringe Ansprüche an die Datenbasis stellt und dem Anwender außerdem Korrekturmöglichkeiten bietet, kann als Schlüsseltechnologie helfen, die bestehenden Hindernisse zu überwinden und die Transformation zu effizienteren Prozessen zu beschleunigen.

 

More and more companies focus on digitization to optimize their processes and become more resilient in the light of increasing uncertainties. However, generating and updating digital models used for this purpose involves a significant amount of effort. Flexible AI-based object detection places fewer demands on the database while offering additional user correction options. It is the key to overcoming the barriers and accelerating the transformation towards more efficient processes.

Literaturverzeichnis


  1. [1] PricewaterhouseCoopers GmbH: PwC Digital Factory Transformation Survey 2022. Stand: 2022. Internet: www.pwc.de/de/content/0f96ea9c-992c-4ba7–8c4d-b4637cf81d9f/pwc-digital-factory-transformation-survey-2022.pdf. Zugriff am 01.03.2023 Google Scholar öffnen doi.org/10.37544/1436-4980-2023-03-6
  2. [2] Chen, Y.; Tang, J.; Jiang, C. et al.: The accuracy comparison of three simultaneous localization and mapping (SLAM)-based indoor mapping technologies. Sensors 18 (2018) 10, pp. 3228 Google Scholar öffnen doi.org/10.37544/1436-4980-2023-03-6
  3. [3] Borrmann, A.; König, M.; Koch, C. et al.: Building Information Modeling – Technology Foundations and Industry Practice. Cham: Springer International Publishing 2018 Google Scholar öffnen doi.org/10.37544/1436-4980-2023-03-6
  4. [4] Undet: How to improve modeling speed using point clouds in Revit by 2x times?. Stand: 2022. Internet: www.undet.com/how-to-improve-modeling-speed-using-point-clouds-in-revit-by-2x-times/. Zugriff am 01.03.2023 Google Scholar öffnen doi.org/10.37544/1436-4980-2023-03-6
  5. [5] BI-Medien: Reales BIM-konform erfassen – Marktüberblick 3D-Laserscanner. Stand 2022. Internet: bi-medien.de/fachzeitschriften/baumagazin/hochbau/marktueberblick-3-d-laserscanner-reales-bim-konform-erfassen-b12232. Zugriff am 01.03.2023 Google Scholar öffnen doi.org/10.37544/1436-4980-2023-03-6
  6. [6] Fayez, T.-K.; Landes, T.; Gussenmeyer, P.: Hough-transform and extended ransac algorithms for automatic detection of 3d building roof planes from lidar data. ISPRS Workshop on Laser Scanning 2007 and SilviLaser 2007, Espoo/Finnland, 2007, pp. 407–412 Google Scholar öffnen doi.org/10.37544/1436-4980-2023-03-6
  7. [7] Son, H.; Kim, C.; Turkan, Y.: Scan-to-BIM-An Overview of the Current State of the Art and a Look Ahead. Proceedings of the International Symposium on Automation and Robotics in Construction 32 (2015), #1 Google Scholar öffnen doi.org/10.37544/1436-4980-2023-03-6
  8. [8] Zeiser, R.; Ullmann, F.; Neuhäuser, T. et al.: System concept for semi-automated generation of layouts for simulation models based on point clouds. Simulation in Produktion und Logistik 2021 (2021), pp. 443 Google Scholar öffnen doi.org/10.37544/1436-4980-2023-03-6
  9. [9] Qi, C. R.; Su, H.; Mo, K et al.: Pointnet: Deep learning on point sets for 3d classification and segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition, CVPR 2017, New York/USA, 2017, pp. 652–660 Google Scholar öffnen doi.org/10.37544/1436-4980-2023-03-6
  10. [10] Qi, C. R.; Yi, L.; Su, H et al.: Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Proceedings of the 31st International Conference on Neural Information Processing Systems NIPS‘17, 2017, pp. 5105–5114 Google Scholar öffnen doi.org/10.37544/1436-4980-2023-03-6
  11. [11] Lang, A. H.; Vora, S.; Caesar, H. et al.: Pointpillars: Fast encoders for object detection from point clouds. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 12697–12705 Google Scholar öffnen doi.org/10.37544/1436-4980-2023-03-6
  12. [12] Petschnigg, C.; Pilz, J.: Uncertainty aware deep point based neural network for 3D object classification. Data Science–Analytics and Applications: Proceedings of the 3rd International Data Science Conference, iDSC2020, 2021, pp. 66–73 Google Scholar öffnen doi.org/10.37544/1436-4980-2023-03-6
  13. [13] Zhao, N.; Chua, T. S.; Lee, G. H.: Few-shot 3d point cloud semantic segmentation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 8873–8882 Google Scholar öffnen doi.org/10.37544/1436-4980-2023-03-6
  14. [14] Viu, J. G.: Object recognition on panoramic images. Bachelorarbeit, Universität Zaragoza, 2019 Google Scholar öffnen doi.org/10.37544/1436-4980-2023-03-6
  15. [15] Ultralytics: yolov5. Stand 2023. Internet: github.com/ultralytics/yolov5. Zugriff am 01.03.2023 Google Scholar öffnen doi.org/10.37544/1436-4980-2023-03-6
  16. [16] Redmon, J.; Divvala, S.; Girshick, R. et al.: You only look once: Unified, real-time object detection. Proceedings of the IEEE conference on computer vision and pattern recognition 2016, pp. 779–788 Google Scholar öffnen doi.org/10.37544/1436-4980-2023-03-6
  17. [17] Köhler, M.; Eisenbach, M.; Gross, H. M.: Few-Shot Object Detection: A Survey. ACM Computing SurveysVolume 54 (2022) 11s, # 242, pp 1–37, doi.org/10.1145/3519022 Google Scholar öffnen doi.org/10.37544/1436-4980-2023-03-6
  18. [18] Qiao, L.; Zhao, Y.; Li, Z. et al.: Defrcn: Decoupled faster r-cnn for few-shot object detection. Proceedings of the IEEE/CVF International Conference on Computer Vision 2021, pp. 8681–8690 Google Scholar öffnen doi.org/10.37544/1436-4980-2023-03-6
  19. [19] Schnabel, R.; Wahl, R.; Klein, R.: Efficient RANSAC for point-cloud shape detection. Computer graphics forum, 2007, pp. 214–226, doi.org/10.1111/j.1467–8659.2007.01016.x Google Scholar öffnen doi.org/10.37544/1436-4980-2023-03-6

Zitation


Download RIS Download BibTex