Guided Attentive Feature Fusion for Multispectral Pedestrian Detection - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Guided Attentive Feature Fusion for Multispectral Pedestrian Detection

Abstract

Multispectral image pairs can provide complementary visual information, making pedestrian detection systems more robust and reliable. To benefit from both RGB and thermal IR modalities, we introduce a novel attentive multispectral feature fusion approach. Under the guidance of the inter- and intra-modality attention modules, our deep learning architecture learns to dynamically weigh and fuse the multispectral features. Experiments on two public multispectral object detection datasets demonstrate that the proposed approach significantly improves the detection accuracy at a low computation cost.
Fichier principal
Vignette du fichier
WACV2021_GAFF.pdf (3.89 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03119907 , version 1 (25-01-2021)

Identifiers

  • HAL Id : hal-03119907 , version 1

Cite

Heng Zhang, Elisa Fromont, Sébastien Lefèvre, Bruno Avignon. Guided Attentive Feature Fusion for Multispectral Pedestrian Detection. WACV 2021 - IEEE Winter Conference on Applications of Computer Vision, Jan 2021, Waikoloa /Virtual, United States. pp.1-9. ⟨hal-03119907⟩
154 View
151 Download

Share

Gmail Mastodon Facebook X LinkedIn More