Skip to Main content Skip to Navigation
Conference papers

Recherche multimodale d'images aériennes multi-date à l'aide d'un réseau siamois

Abstract : Abstract This paper introduces a multi-modal network that learns to match aerial images of french urban and rural territories taken about 15 years apart. This means it should be invariant against a big range of changes as the (natural) landscape evolves over time. It leverages the original images and semantically segmented and labeled regions. The core of the method is a siamese network that learns to extract features from corresponding image pairs across time, and non matching pairs. These descriptors are discri-minative enough, such that a simple kNN classifier on top, suffices as a final geo-matching criteria. We demonstrate that our siamese descriptor outperforms other image descriptors for cross-time image retrieval.
Complete list of metadatas

Cited literature [43 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02906569
Contributor : Margarita Khokhlova <>
Submitted on : Wednesday, July 29, 2020 - 3:10:04 PM
Last modification on : Thursday, August 6, 2020 - 3:39:36 AM

File

rfiap2020_21_cameraready.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02906569, version 1

Citation

Margarita Khokhlova, Valérie Gouet-Brunet, Nathalie Abadie, Liming Chen. Recherche multimodale d'images aériennes multi-date à l'aide d'un réseau siamois. Conférence française en Reconnaissance des Formes, Image, Apprentissage et Perception (RFIAP 2020), https://cap-rfiap2020.sciencesconf.org/, Jun 2020, Vannes, France. ⟨hal-02906569⟩

Share

Metrics

Record views

64

Files downloads

40