A synthetic-data-trained pipeline for locating rose flower centers in 2D and estimating their depth in stereo images is described, with in-simulation F1 up to about 96-100%, but real-world detection is below a YOLOv5 baseline and real depth is untested.
Voting for voting in online point cloud ob- ject detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Sparse 3D Perception for Rose Harvesting Robots: A Two-Stage Approach Bridging Simulation and Real-World Applications
A synthetic-data-trained pipeline for locating rose flower centers in 2D and estimating their depth in stereo images is described, with in-simulation F1 up to about 96-100%, but real-world detection is below a YOLOv5 baseline and real depth is untested.