An unmanned aerial vehicle captured dataset for railroad segmentation and obstacle detection
Rampriya R. S., Taher Al-Shehari, Sabari Nathan, Jenefa A., Suganya R., Shunmuga Perumal P., Taha Alfakih, Hussain Alsalman · 2024
Read An unmanned aerial vehicle captured dataset for railroad segmentation and obstacle detection by Rampriya R. S., Taher Al-Shehari, Sabari Nathan, Jenefa A., Suganya R., Shunmuga Perumal P., Taha Alfakih, Hussain Alsalman (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11612275.txt.
Description
Rampriya and seven co-authors release a drone-photographed dataset for teaching computers to find railway tracks and obstacles. Rail safety depends on spotting hazards early, and drones with smart cameras are becoming the inspectors. The collection holds 315 original aerial images of rail scenes, plus labeled and masked versions for teaching track outlining. Computer enlargement tricks expanded the obstacle set to 2,002 annotated images.
Six obstacle kinds are marked with boxes: a person, a boulder, a barrel, a branch, a jerry can, and an iron rod. The team also ships the original images with a script so users can brew their own enlarged sets. They present the dataset as a shared workbench for researchers building vision tools for railway safety.
Catalog record
| CREATOR | Rampriya R. S., Taher Al-Shehari, Sabari Nathan, Jenefa A., Suganya R., Shunmuga Perumal P., Taha Alfakih, Hussain Alsalman |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 42 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |