Exploiting 2D Neural Network Frameworks for 3D Segmentation Through Depth Map Analytics of Harvested Wild Blueberries (Vaccinium angustifolium Ait.)
Connor C Mullins, Travis J Esau, Qamar U Zaman, Ahmad A Al-Mallahi, Aitazaz A Farooque, Pierre Gouton · 2024
Read Exploiting 2D Neural Network Frameworks for 3D Segmentation Through Depth Map Analytics of Harvested Wild Blueberries (Vaccinium angustifolium Ait.) by Connor C Mullins, Travis J Esau, Qamar U Zaman, Ahmad A Al-Mallahi, Aitazaz A Farooque, Pierre Gouton (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-11676057.txt.
Description
Mullins and co-authors sort blueberries in 3D in a 2024 study, using flat image tools in a fresh way. Wild blueberries are picked by machine and land in totes mixed with debris. The team filmed filled totes with a depth camera and a color camera, building both depth and color views.
Depth maps were painted by height, so flat neural nets could read them as pictures. Two known net families were tested on the task. The faster family won clearly, the team reports, scoring high on overlap while taking a third of the rival's time. Its masks also had smoother edges. Fast, clean sorting could lift pack-out quality for wild blueberry growers without slowing the line.
Catalog record
| CREATOR | Connor C Mullins, Travis J Esau, Qamar U Zaman, Ahmad A Al-Mallahi, Aitazaz A Farooque, Pierre Gouton |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 29 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |