HqiTao/TextInPlace

Official code for IROS 2025 paper "TextInPlace: Indoor Visual Place Recognition in Repetitive Structures with Scene Text Spotting and Verification"

20
/ 100
Experimental

This tool helps autonomous robots, like those used in warehouses or large office buildings, recognize their exact location even in highly similar-looking indoor areas. By taking visual input (images) from the robot's cameras, it identifies and verifies scene text (like room numbers or signs) to pinpoint where the robot is. It's designed for robotics engineers and researchers working on robot navigation and localization.

Use this if your autonomous robot struggles with accurate indoor localization due to repetitive visual environments and you want to leverage text visible in those scenes.

Not ideal if your robot operates in environments without significant scene text, or if you need to identify locations solely based on visual appearance without text assistance.

robotics indoor-navigation localization visual-place-recognition autonomous-systems
No License No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

16

Forks

Language

Python

License

Last pushed

Dec 27, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/HqiTao/TextInPlace"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.