ThermalGAN: Multimodal Color-to-Thermal Image Translation for Person Re-Identification in Multispectral Dataset
Abstract
We propose a ThermalGAN framework for cross-modality color-thermal person re-identification (ReID). We use a stack of generative adversarial networks (GAN) to translate a single color probe image to a multimodal thermal probe set. We use thermal histograms and feature descriptors as a thermal signature. We collected a large-scale multispectral ThermalWorld dataset for extensive training of our GAN model. In total the dataset includes 20216 color-thermal image pairs, 516 person ID, and ground truth pixel-level object annotations. We made the dataset freely available ( http://www.zefirus.org/ThermalGAN/ ). We evaluate our framework on the ThermalWorld dataset to show that it delivers robust matching that competes and surpasses the state-of-the-art in cross-modality color-thermal ReID.
Cite
Text
Kniaz et al. "ThermalGAN: Multimodal Color-to-Thermal Image Translation for Person Re-Identification in Multispectral Dataset." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11024-6_46Markdown
[Kniaz et al. "ThermalGAN: Multimodal Color-to-Thermal Image Translation for Person Re-Identification in Multispectral Dataset." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/kniaz2018eccvw-thermalgan/) doi:10.1007/978-3-030-11024-6_46BibTeX
@inproceedings{kniaz2018eccvw-thermalgan,
title = {{ThermalGAN: Multimodal Color-to-Thermal Image Translation for Person Re-Identification in Multispectral Dataset}},
author = {Kniaz, Vladimir V. and Knyaz, Vladimir A. and Hladuvka, Jirí and Kropatsch, Walter G. and Mizginov, Vladimir},
booktitle = {European Conference on Computer Vision Workshops},
year = {2018},
pages = {606-624},
doi = {10.1007/978-3-030-11024-6_46},
url = {https://mlanthology.org/eccvw/2018/kniaz2018eccvw-thermalgan/}
}