3D object detection for vehicle-mounted LiDAR based on deep learning and euclidean clustering algorithm
Nan Zhang, Maolong Xi, Juan Fang, Fangqin Wang · 2026
Read 3D object detection for vehicle-mounted LiDAR based on deep learning and euclidean clustering algorithm by Nan Zhang, Maolong Xi, Juan Fang, Fangqin Wang (2026) 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/plos-pone-0348581.txt.
Description
Nan Zhang and co-authors improved three dimensional object detection from vehicle LiDAR in 2026. Self driving cars read the world as point clouds, which are sparse and uneven, so grouping points into objects is error prone.
Their method first separates ground from objects with a cloth simulation filter, then clusters with a tree structure that adapts its settings. An upgraded point network reads features at several scales with skip links. On two public benchmarks it reached high segmentation accuracy with fast per frame times. The pairing of careful clustering with deep reading is the design's answer to messy real road data.
Catalog record
| CREATOR | Nan Zhang, Maolong Xi, Juan Fang, Fangqin Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 67810 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |