Auflistung Fakultät für Bauingenieurwesen und Geodäsie nach Autor/in "Brédif, M."

Auflistung Fakultät für Bauingenieurwesen und Geodäsie nach Autor/in "Brédif, M."

Sortiert nach: Sortierung: Ergebnisse:

  • Convex image orientation from relative orientations 
    Reich, Martin; Heipke, Christian (Göttingen : Copernicus GmbH, 2016)
    In this paper we propose a novel workflow for the estimation of global image orientations given relative orientations between pairs of overlapping images. Our approach is convex and independent on initial values. First, ...
  • Detecting linear features by spatial point processes 
    Chai, Dengfeng; Schmidt, Alena; Heipke, Christian (Göttingen : Copernicus GmbH, 2016)
    This paper proposes a novel approach for linear feature detection. The contribution is twofold: a novel model for spatial point processes and a new method for linear feature detection. It describes a linear feature as a ...
  • A gaussian process based multi-person interaction model 
    Klinger, Tobias; Rottensteiner, Franz; Heipke, Christian (Göttingen : Copernicus GmbH, 2016)
    Online multi-person tracking in image sequences is commonly guided by recursive filters, whose predictive models define the expected positions of future states. When a predictive model deviates too much from the true motion ...
  • Global rotation estimation using weighted iterative lie algebraic averaging 
    Reich, Martin; Heipke, Christian (Göttingen : Copernicus GmbH, 2015)
    In this paper we present an approach for a weighted rotation averaging to estimate absolute rotations from relative rotations between two images for a set of multiple overlapping images. The solution does not depend on ...
  • Hierarchical higher order crf for the classification of airborne lidar point clouds in urban areas 
    Niemeyer, Joachim; Rottensteiner, Franz; Sörgel, Uwe; Heipke, Christian (Göttingen : Copernicus GmbH, 2016)
    We propose a novel hierarchical approach for the classification of airborne 3D lidar points. Spatial and semantic context is incorporated via a two-layer Conditional Random Field (CRF). The first layer operates on a point ...
  • Invariant descriptor learning using a Siamese convolutional neural network 
    Chen, Lin; Rottensteiner, Franz; Heipke, Christian (Göttingen : Copernicus GmbH, 2016)
    In this paper we describe learning of a descriptor based on the Siamese Convolutional Neural Network (CNN) architecture and evaluate our results on a standard patch comparison dataset. The descriptor learning architecture ...
  • Iterative re-weighted instance transfer for domain adaptation 
    Paul, Andreas; Rottensteiner, Franz; Heipke, Christian (Göttingen : Copernicus GmbH, 2016)
    Domain adaptation techniques in transfer learning try to reduce the amount of training data required for classification by adapting a classifier trained on samples from a source domain to a new data set (target domain) ...
  • Network detection in raster data using marked point processes 
    Schmidt, Alena; Kruse, Christian; Rottensteiner, Franz; Sörgel, Uwe; Heipke, Christian (Göttingen : Copernicus GmbH, 2016)
    We propose a new approach for the automatic detection of network structures in raster data. The model for the network structure is represented by a graph whose nodes and edges correspond to junction-points and to connecting ...
  • Probabilistic multi-person tracking using dynamic bayes networks 
    Klinger, Tobias; Rottensteiner, Franz; Heipke, Christian (Göttingen : Copernicus GmbH, 2015)
    Tracking-by-detection is a widely used practice in recent tracking systems. These usually rely on independent single frame detections that are handled as observations in a recursive estimation framework. If these observations ...

Suche im Repositorium


Durchblättern

Mein Nutzer/innenkonto

Nutzungsstatistiken