.png){kind=icon}
.png){kind=icon}
Return
City-4Band: A four-band urban street scene dataset for semantic segmentation
.png){kind=icon}
PRE
AI
J
L
Y
Q
J
S
S
DOI：10.1016/j.infrared.2025.106352.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A four-band urban dataset including VIS, SWIR, MWIR, and LWIR images is proposed. • A full preprocessing pipeline ensures temporal and spatial alignment across bands. • Lightweight annotation targets person, vehicle, and bicycle in complex urban scenes. • Four-band fusion improves low-light segmentation and supports multi-band fusion research.
Journal
I
IF:
3.4
Papers:
5.8K
Citations:
1.2W
Organization
Cited Papers