Sparse analysis for mesoscale convective systems tracking

Abstract : In this paper, we study the tracking of de-formable shapes in sequences of images. Our target application is the tracking of clouds in satellite image. We propose to use a recent state-of-the-art method for off-the-grid sparse analysis to describe clouds in image as mixtures of 2D atoms. Then, we introduce an algorithm to handle the tracking with its specificities: apparition or disappearance of objects, merging, and splitting. This method provides similar numerical outputs as the recent state-of-the-art alternatives, while being more flexible, and providing additional information on, e.g., cloud surface brightness.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [33 references]  Display  Hide  Download
Contributor : Jean-Baptiste Courbot <>
Submitted on : Thursday, February 7, 2019 - 10:59:57 AM
Last modification on : Wednesday, May 15, 2019 - 3:39:44 AM
Long-term archiving on : Wednesday, May 8, 2019 - 1:56:01 PM


Files produced by the author(s)


  • HAL Id : hal-02010436, version 1


Jean-Baptiste Courbot, Vincent Duval, Bernard Legras. Sparse analysis for mesoscale convective systems tracking. 2019. ⟨hal-02010436⟩



Record views


Files downloads