Advertisement

Data Anonymization for Data Protection on Publicly Recorded Data

  • David MünchEmail author
  • Ann-Kristin Grosselfinger
  • Erik Krempel
  • Marcus Hebel
  • Michael Arens
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11754)

Abstract

Data protection in Germany has a long tradition (https://www.goethe.de/en/kul/med/20446236.html). For a long time, the German Federal Data Protection Act or Bundesdatenschutzgesetz (BDSG) was considered as one of the strictest. Since May 2017 the EU General Data Protection Regulation (GDPR) regulates data protection all over Europe and it strongly influenced by the German law. When recording data in public areas, the recordings may contain personal data, such as license plates or persons. According to the GDPR this processing of personal data has to fulfill certain requirements to be considered lawful. In this paper, we address recording visual data in public while abiding by the applicable laws. Towards this end, a formal data protection concept is developed for a mobile sensor platform. The core part of this data protection concept is the anonymization of personal data, which is implemented with state-of-the-art deep learning based methods achieving almost human-level performance. The methods are evaluated quantitatively and qualitatively on example data recorded with a real mobile sensor platform in an urban environment.

Keywords

Video data anonymization Data protection 

References

  1. 1.
    Agrawal, P., Narayanan, P.: Person de-identification in videos. IEEE Trans. Circuits Syst. Video Technol. 21(3), 299–310 (2011)CrossRefGoogle Scholar
  2. 2.
    Arsenovic, M., Sladojevic, S., Anderla, A., Stefanovic, D.: Deep learning driven plates recognition system. In: 17th International Scientific Conference Industrial Systems (IS 2017) (2017)Google Scholar
  3. 3.
    Bayerisches Landesamt für Datenschutzaufsicht: Bundesdatenschutzgesetz (BDSG); Rechtsgutachten zum möglichen Erprobungseinsatz eines mit Laser- und Kameratechnik ausgestatteten Sensorfahrzeuges im Stadtgebiet von Ettlingen, December 2015Google Scholar
  4. 4.
    Borgmann, B., Schatz, V., Kieritz, H., Scherer-Klöckling, C., Hebel, M., Arens, M.: Data processing and recording using a versatile multi-sensor vehicle. ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci. IV-1, 21–28 (2018)CrossRefGoogle Scholar
  5. 5.
    Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: CVPR (2017)Google Scholar
  6. 6.
    Flores, A., Belongie, S.: Removing pedestrians from google street view images. In: CVPR - Workshops, June 2010Google Scholar
  7. 7.
    Frome, A., et al.: Large-scale privacy protection in Google street view. In: ICCV. IEEE (2009)Google Scholar
  8. 8.
    Grosselfinger, A.K., Münch, D., Arens, M.: An architecture for automatic multi-modal video data anonymization to ensure data protection. SPIE Security + Defence (2019)Google Scholar
  9. 9.
    HÄRTING Rechtsanwälte: RECHTSGUTACHTEN zu Rechtsfragen zum möglichen Erprobungseinsatz eines mit Laser- und Kameratechnik ausgestatteten Sensorfahrzeuges im Stadtgebiet Ettlingen durch das Fraunhofer Institut für Optronik, Systemtechnik und Bildauswertung (IOSB), Abteilung Objekterkennung, June 2013Google Scholar
  10. 10.
    Jørgensen, H.: Automatic license plate recognition using deep learning techniques. Master’s thesis, NTNU (2017)Google Scholar
  11. 11.
    Laroca, R., et al.: A robust real-time automatic license plate recognition based on the YOLO detector. arXiv preprint arXiv:1802.09567 (2018)
  12. 12.
    Li, H., Shen, C.: Reading car license plates using deep convolutional neural networks and LSTMs. arXiv preprint arXiv:1601.05610 (2016)
  13. 13.
    Masood, S.Z., Shu, G., Dehghan, A., Ortiz, E.G.: license plate detection and recognition using deeply learned convolutional neural networks. arXiv preprint arXiv:1703.07330 (2017)
  14. 14.
    McPherson, R., Shokri, R., Shmatikov, V.: Defeating image obfuscation with deep learning. arXiv preprint arXiv:1609.00408 (2016)
  15. 15.
    Nodari, A., Vanetti, M., Gallo, I.: Digital privacy: Replacing pedestrians from Google street view images. In: ICPR, November 2012Google Scholar
  16. 16.
    Padilla-López, J.R., Chaaraoui, A.A., Flórez-Revuelta, F.: Visual privacy protection methods: a survey. Expert Syst. Appl. 42(9), 4177–4195 (2015)CrossRefGoogle Scholar
  17. 17.
    Peter, R., Grosselfinger, A.K., Münch, D., Arens, M.: Automated license plate detection for image anonymization. SPIE Security + Defence (2019)Google Scholar
  18. 18.
    Redmon, J., Farhadi, A.: Yolov3 an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
  19. 19.
    Ribaric, S., Ariyaeeinia, A., Pavesic, N.: De-identification for privacy protection in multimedia content: A survey. Sig. Process. Image Commun. 47, 131–151 (2016)CrossRefGoogle Scholar
  20. 20.
    Uittenbogaard, R., Sebastian, C., Vijverberg, J., Boom, B., Gavrila, D.M., et al.: Privacy protection in street-view panoramas using depth and multi-view imagery. In: CVPR (2019)Google Scholar
  21. 21.
    Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: CVPR (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Fraunhofer IOSBEttlingenGermany

Personalised recommendations