These are tight pedestrian masks for the thermal images present in the KAIST Multispectral pedestrian dataset, available at https://soonminhwang.github.io/rgbt-ped-detection/

Both the thermal images themselves as well as the original annotations are a part of the parent dataset. Using the annotation files provided by the authors, we develop the binary segmentation masks for the pedestrians, using the Segment Anything Model from Meta.

DOI Link: 
https://doi.org/10.1016/j.inffus.2024.102618
Read more

Dataset Files

You must be an IEEE Dataport Subscriber to access these files. Subscribe now or login.

[1] Suranjan Goswami, Satish Kumar Singh, "Tight Masks for KAIST thermal pedestrian images", IEEE Dataport, 2024. [Online]. Available: http://dx.doi.org/https://doi.org/10.1016/j.inffus.2024.102618. Accessed: Oct. 06, 2024.
@data{-24,
doi = {https://doi.org/10.1016/j.inffus.2024.102618},
url = {http://dx.doi.org/https://doi.org/10.1016/j.inffus.2024.102618},
author = {Suranjan Goswami; Satish Kumar Singh },
publisher = {IEEE Dataport},
title = {Tight Masks for KAIST thermal pedestrian images},
year = {2024} }
TY - DATA
T1 - Tight Masks for KAIST thermal pedestrian images
AU - Suranjan Goswami; Satish Kumar Singh
PY - 2024
PB - IEEE Dataport
UR - https://doi.org/10.1016/j.inffus.2024.102618
ER -
Suranjan Goswami, Satish Kumar Singh. (2024). Tight Masks for KAIST thermal pedestrian images. IEEE Dataport. http://dx.doi.org/https://doi.org/10.1016/j.inffus.2024.102618
Suranjan Goswami, Satish Kumar Singh, 2024. Tight Masks for KAIST thermal pedestrian images. Available at: http://dx.doi.org/https://doi.org/10.1016/j.inffus.2024.102618.
Suranjan Goswami, Satish Kumar Singh. (2024). "Tight Masks for KAIST thermal pedestrian images." Web.
1. Suranjan Goswami, Satish Kumar Singh. Tight Masks for KAIST thermal pedestrian images [Internet]. IEEE Dataport; 2024. Available from : http://dx.doi.org/https://doi.org/10.1016/j.inffus.2024.102618
Suranjan Goswami, Satish Kumar Singh. "Tight Masks for KAIST thermal pedestrian images." doi: https://doi.org/10.1016/j.inffus.2024.102618