Auflistung Fakultät für Elektrotechnik und Informatik nach Autor/in "6260f976-afcd-49a0-9298-4e4db15b95a4"

Auflistung Fakultät für Elektrotechnik und Informatik nach Autor/in "6260f976-afcd-49a0-9298-4e4db15b95a4"

Sortiert nach: Sortierung: Ergebnisse:

  • Banz, Christian; Pirsch, Peter; Blume, Holger (Katlenburg-Lindau : Copernicus Publications, 2012)
    The stereo matching method semi-global matching (SGM) relies on consistency constraints during the cost aggregation which are enforced by so-called penalty terms. This paper proposes new and evaluates four penalty functions ...
  • Yang, Michael Ying; Foerstner, Wolfgang; Chai, Dengfeng (Katlenburg-Lindau : Copernicus Publications, 2012)
    The classification of building facade images is a challenging problem that receives a great deal of attention in the photogrammetry community. Image classification is critically dependent on the features. In this paper, ...
  • Liao, W.; Rosenhahn, B.; Ying Yang, M. (Katlenburg-Lindau : Copernicus Publications, 2015)
    Complex activity modeling and identification of anomaly is one of the most interesting and desired capabilities for automated video behavior analysis. A number of different approaches have been proposed in the past to ...
  • Ying Yang, M.; Feng, S.; Ackermann, H.; Rosenhahn, B. (Katlenburg-Lindau : Copernicus Publications, 2015)
    In this paper, we propose a new framework for segmenting feature-based moving objects under affine subspace model. Since the feature trajectories in practice are high-dimensional and contain a lot of noise, we firstly apply ...
  • Liao, Wengtong; Chen, Xiang; Yang, Jingfeng; Roth, Stefan; Goesele, Michael; Ying Yang, Michael; Rosenhahn, Bodo (Katlenburg-Lindau : Copernicus Publications, 2020)
    State-of-the-art object detection approaches such as Fast/Faster R-CNN, SSD, or YOLO have difficulties detecting dense, small targets with arbitrary orientation in large aerial images. The main reason is that using ...
  • Gritzner, D.; Ostermann, J. (Katlenburg-Lindau : Copernicus Publications, 2020)
    Modern machine learning, especially deep learning, which is used in a variety of applications, requires a lot of labelled data for model training. Having an insufficient amount of training examples leads to models which ...

Suche im Repositorium


Durchblättern

Mein Nutzer/innenkonto

Nutzungsstatistiken