Skip to Main content Skip to Navigation
Conference papers

Suivi d'individus dans des cartes de profondeurs par champ de Markov, dans un contexte de détection de chute

Abstract : This paper proposes a method for the detection, separation, and tracking of objects in depth maps. The method is based on an application of spatio-temporal Markov Random Fields (ST-MRF) which uses the results of 3 preprocessing steps of the depth map: a segmentation step, a motion estimation step, and finally, an objects map updating step. The method has been tested on synthetic and real depth map sequences, and yielded results which show its ability to discriminate objects with crossing image trajectories.
Complete list of metadata

Cited literature [9 references]  Display  Hide  Download

https://www.hal.inserm.fr/inserm-01319945
Contributor : Jean-Louis Dillenseger Connect in order to contact the contributor
Submitted on : Monday, May 23, 2016 - 11:39:32 AM
Last modification on : Wednesday, April 14, 2021 - 6:44:05 PM

File

cr_cormier207.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inserm-01319945, version 1

Citation

Geoffroy Cormier, Jean-Marc Laferté, Guy Carrault, Jean-Louis Dillenseger, Vincent Gauthier. Suivi d'individus dans des cartes de profondeurs par champ de Markov, dans un contexte de détection de chute. Gretsi 2015, Sep 2015, Lyon, France. ⟨inserm-01319945⟩

Share

Metrics

Record views

229

Files downloads

171