Garment Recognition and Reconstruction Using Object Simultaneous Localization and Mapping
Yilin Zhang, Koichi Hashimoto, Erfu Yang, Rafal Szczepanski · 2024
Read Garment Recognition and Reconstruction Using Object Simultaneous Localization and Mapping by Yilin Zhang, Koichi Hashimoto, Erfu Yang, Rafal Szczepanski (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-11644764.txt.
Description
Yilin Zhang and co-authors built a vision system that lets robots recognize garments and rebuild them, plus their surroundings, in three dimensions, in a 2024 study. Robots are rare in garment work because cloth bends and folds in hard ways. Their system rests on object SLAM, a method that maps a scene and tracks the camera at the same time.
The team made two data sets: flat garment images to train a segmentation model, and fake 3D garments to sharpen a shape model. A second model finds planes such as tables and floors, which grounds the scene. Tests with a depth camera showed garments and planes detected and rebuilt together in real time.
Catalog record
| CREATOR | Yilin Zhang, Koichi Hashimoto, Erfu Yang, Rafal Szczepanski |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |