Images can be affected by weather conditions such as haze, rain, or dust, etc. Also, they can be captured under conditions of bad visibility, such as night-time or underwater. Images obtained under these circumstances usually present faded colors and loss of contrast, among many other problems. Removing the effect of these conditions will be useful not only for aesthetic purposes, but also to improve the performance of computer vision systems that need to operate outdoors under uncontrolled imaging conditions. This minisymposium presents some state-of-the-art algorithms whose purpose is to enhance the visibility of images captured under these scattering conditions.

Variational image dehazing

Javier Vazquez-Corral (Information and Communication Technologies Department, Universitat Pompeu Fabra)

Markov Random Field for combined defogging and stereo reconstruction

Jean-Philippe Tarel (Researcher. COSYS/LEPSiS , IFSTTAR)

Spectral Edge Image Fusion

Graham Finlayson (School of Computing Sciences, University of East Anglia, Norwich Research Park)

On the use of sparse reconstruction for the restoration of areas obscured by thick clouds in satellite image time series

Daniele Cerra (German Aerospace Center (DLR), Remote Sensing Technology Institute, Photogrammetry and Image Analysis, Oberpfaffenhofen)

Organizers:

Javier Vazquez-Corral (Information and Communication Technologies Department, Universitat Pompeu Fabra)

Keywords:

computer vision, image dehazing, image enhancement, visibility enhancement