Fully Convolutional Siamese Networks for Change Detection

Abstract : This paper presents three fully convolutional neural network architectures which perform change detection using a pair of coregistered images. Most notably, we propose two Siamese extensions of fully convolutional networks which use heuris-tics about the current problem to achieve the best results in our tests on two open change detection datasets, using both RGB and multispectral images. We show that our system is able to learn from scratch using annotated change detection images. Our architectures achieve better performance than previously proposed methods, while being at least 500 times faster than related systems. This work is a step towards efficient processing of data from large scale Earth observation systems such as Copernicus or Landsat.
Complete list of metadatas

Cited literature [19 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01824557
Contributor : Alexandre Boulch <>
Submitted on : Wednesday, June 27, 2018 - 12:46:03 PM
Last modification on : Wednesday, July 3, 2019 - 3:02:02 PM
Long-term archiving on : Thursday, September 27, 2018 - 3:47:26 AM

File

2018_icip_change.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01824557, version 1

Citation

Rodrigo Daudt, Bertrand Le Saux, Alexandre Boulch. Fully Convolutional Siamese Networks for Change Detection. IEEE International Conference on Image Processing, Oct 2018, Athens, Greece. ⟨hal-01824557⟩

Share

Metrics

Record views

170

Files downloads

936