YDD-SLAM: Indoor Dynamic Visual SLAM Fusing YOLOv5 with Depth Information
Peichao Cong, Junjie Liu, Jiaxing Li, Yixuan Xiao, Xilai Chen, Xinjie Feng, Xin Zhang, Anastasios Doulamis, Hui Kong · 2023
Read YDD-SLAM: Indoor Dynamic Visual SLAM Fusing YOLOv5 with Depth Information by Peichao Cong, Junjie Liu, Jiaxing Li, Yixuan Xiao, Xilai Chen, Xinjie Feng, Xin Zhang, Anastasios Doulamis, Hui Kong (2023) 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-10708714.txt.
Description
Peichao Cong and co-authors present YDD-SLAM, a mapping system that keeps its bearings in busy indoor spaces, in a 2023 paper. Camera based mapping assumes a still world; people walking through break that assumption and can crash the tracker. Their build starts from a leading open system.
An object detector first sorts what it sees into eight motion classes, using depth to judge which things can move. Feature points inside moving boxes are tested against depth and dropped when they ride on movers. Extra refinement steps steady the rest. On public data and a live dynamic scene, accuracy beat the base system by a wide margin.
Catalog record
| CREATOR | Peichao Cong, Junjie Liu, Jiaxing Li, Yixuan Xiao, Xilai Chen, Xinjie Feng, Xin Zhang, Anastasios Doulamis, Hui Kong |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 92 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |