A factor-graph SLAM that uses YOLOv8 trunk detections and a cascade-graph association algorithm maps individual orchard trees with a best-case geo-localization error of 18 cm, beating a clustering baseline on most test rows.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Tree-SLAM: semantic object SLAM for efficient mapping of individual trees in orchards
A factor-graph SLAM that uses YOLOv8 trunk detections and a cascade-graph association algorithm maps individual orchard trees with a best-case geo-localization error of 18 cm, beating a clustering baseline on most test rows.