Skip to Main content Skip to Navigation
Conference papers

Robust SIFT-Based Hierarchical Video Mosaicing for Endomicroscopy

Abstract : We present a method to perform video mosaicing for endomicroscopy with two major improvements compared to the state of the art. First, instead of using individual images directly, we start by creating sub-mosaics from short video sub-sequences using iconic registration. The sub-mosaics are then considered for registration. Second, groupwise estimation is performed between all sub-mosaics based on SIFT matching to infer globally consistent spatial transformations. Both improvements increase robustness of the reconstruction compared to a baseline mosaicing method.
Complete list of metadatas

Cited literature [2 references]  Display  Hide  Download

https://www.hal.inserm.fr/inserm-01017954
Contributor : Nicolas Linard <>
Submitted on : Thursday, July 3, 2014 - 2:25:39 PM
Last modification on : Friday, July 4, 2014 - 10:30:38 AM
Long-term archiving on: : Tuesday, October 13, 2015 - 3:26:36 PM

File

paper_chang.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inserm-01017954, version 1

Collections

Citation

Danica Chang, Nicolas Linard, Mahé Jessie, Tom Vercauteren, Julien Dauguet. Robust SIFT-Based Hierarchical Video Mosaicing for Endomicroscopy. ISBI - International Symposium on Biomedical Imaging, Apr 2014, Beijing, China. ⟨inserm-01017954⟩

Share

Metrics

Record views

963

Files downloads

276