Skip to Main content Skip to Navigation
Conference papers

Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks

Heng Zhang 1, 2 Elisa Fromont 2 Sébastien Lefèvre 3 Bruno Avignon 1
2 LACODAM - Large Scale Collaborative Data Mining
IRISA-D7 - GESTION DES DONNÉES ET DE LA CONNAISSANCE, Inria Rennes – Bretagne Atlantique
3 OBELIX - Observation de l’environnement par imagerie complexe
IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : Multispectral images (e.g. visible and infrared) may be particularly useful when detecting objects with the same model in different environments (e.g. day/night outdoor scenes). To effectively use the different spectra, the main technical problem resides in the information fusion process. In this paper, we propose a new halfway feature fusion method for neural networks that leverages the complementary/consistency balance existing in multispectral features by adding to the network architecture, a particular module that cyclically fuses and refines each spectral feature. We evaluate the effectiveness of our fusion method on two challenging multispectral datasets for object detection. Our results show that implementing our Cyclic Fuse-and-Refine module in any network improves the performance on both datasets compared to other state-of-the-art multispectral object detection methods.
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02872132
Contributor : Elisa Fromont <>
Submitted on : Wednesday, June 17, 2020 - 3:42:55 PM
Last modification on : Saturday, July 11, 2020 - 3:15:55 AM

File

icip2020.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02872132, version 1

Citation

Heng Zhang, Elisa Fromont, Sébastien Lefèvre, Bruno Avignon. Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks. ICIP 2020 - IEEE International Conference on Image Processing, Oct 2020, Abou Dabi, United Arab Emirates. pp.1-5. ⟨hal-02872132⟩

Share

Metrics

Record views

222

Files downloads

330