Sandra Aigner, M.Sc.

Sandra Aigner wurde 1989 in Landshut geboren. Im November 2015 erhielt sie ihren Master (M.Sc.) im Studiengang Geodäsie und Geoinformation der Technischen Universität München (TUM). Der Titel ihrer Masterarbeit lautet "Messreihenauswertung mit künstlichen neuronalen Netzen". Seit März 2016 ist sie als wissenschaftliche Mitarbeiterin und Doktorandin am Lehrstuhl für Methodik der Fernerkundung Teil der Computer Vision Research Group. Ihr Promotionsprojekt umfasst die Modellierung von Verkehrsinfrastruktur mit Hilfe von Methoden des maschinellen Lernens (deep learning). Der Fokus liegt dabei auf der Generierung von Videos zur Vorhersage des Verkehrsgeschehens.

Research

Interests:

  • Computer Vision
  • Machine Learning
  • Artificial Intelligence
  • Autonomous Driving Systems
  • Video Frame Generation

Projects:

Prediction of Image Sequences from Driver Assistance Systems by implicit modelling of Activity Patterns

Safe autonomous driving systems rely on autonomous vehicles that are able to drive anticipatory. This project aims at simulating the human anticipation of future scenarios by predicting traffic events from generated video frames. We build up on state of the art methods in Computer Vision and Machine Learning to generate prospective frames of a video based on the latest observed video sequence. Features learned by the model are further used for modeling and analyzing traffic scenes and activity patterns of traffic participants.

Teaching

Courses:

  • Photogrammetry and Remote Sensing IV (Tutorial, Bachelor Geodesy and Geoinformation, SS2016)

Supervised Student Projects:

  • Geodetic Seminar: "Synthetic Training Data: Playing for Data" (Gummel, 2017)
  • Geodetic Seminar: "Geodata for Autonomous Driving" (Härpfer, 2016)

  • Specialization Project Photogrammetry and Remote Sensing: "Enhancement of Video Prediction Results" (König, wip)
  • Specialization Project Photogrammetry and Remote Sensing: "Prediction of Moving Foreground Objects" (Wu, wip)

Supervised Theses:

  • Bachelor Thesis: "Google Earth Engine: Global Analyses based on Remote Sensing Data" (Kolsch, 2018)
  • Bachelor Thesis: "Comparative Analysis of a State of the Art Object Detector" (Greza, 2017)

  • Master Thesis: "Prediction of Video Frames using Depth Information" (Sachße, wip)

Curriculum Vitae

  • since 2016: Research Associate and PhD Student at TUM
  • 2015: M.Sc. in Geodesy and Geoinformation at TUM
  • 2012: B.Sc. in Geodesy and Geoinformation at TUM
  • 2008: A-Levels from Hans-Leinberger-Gymnasium, Landshut

Awards/Grants

  • WiCV Travel Grant (CVPR 2016, WiCV Workshop)

Publications

  • Aigner, Sandra; Körner, Marco: FutureGAN: Anticipating the Future Frames of Video Sequences using Spatio-Temporal 3d Convolutions in Progressively Growing GANs. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences (ISPRS) (tbp), 2019 more…
  • König, Peter; Aigner, Sandra; Körner, Marco: Enhancing Traffic Scene Predictions with Generative Adversarial Networks. Proceedings of the IEEE Intelligent Transportation Systems Conference (ITSC), 2019 more…