MIPT, Moscow, Russia
In ECCV 2018, 1st Multimodal Learning and Applications Workshop
Examples of annotated images in ThermalWorld VOC dataset.
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 . 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.
Examples of person images from ThermalWorld ReID dataset.
The ReID split includes 15118 aligned color and thermal image pairs of 516 IDs. Pairs of color and thermal images were captured by sixteen FLIR ONE PRO cameras. All cameras were located in a shopping mall area. Cameras #2, 9, 13 are located in underground passages with low-light conditions. Cameras #1, 3, 7, 8, 10, 12, 14 are located at the entrances and present both day-time and night-time images. Cameras #15,16 are placed in the garden. The rest of the cameras are located inside the mall.
For download "ThermalWorld Dataset ReID Split" dataset write to vl.kniaz@gosniias.ru
Created date: 2022-10-13 10:15:01
Last update: 2022-10-13 10:15:01