GBCNet: In-Field Grape Berries Counting for Yield Estimation by Dilated CNNs
We introduce here the Grape Berries Counting Net (GBCNet), a tool for accurate fruit yield estimation from smartphone cameras, by adapting Deep Learning algorithms originally developed for crowd counting. We test GBCNet using cross-validation procedure on two original datasets CR1 and CR2 of grape p...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/14/4870 |
| _version_ | 1797562367441108992 |
|---|---|
| author | Luca Coviello Marco Cristoforetti Giuseppe Jurman Cesare Furlanello |
| author_facet | Luca Coviello Marco Cristoforetti Giuseppe Jurman Cesare Furlanello |
| author_sort | Luca Coviello |
| collection | DOAJ |
| description | We introduce here the Grape Berries Counting Net (GBCNet), a tool for accurate fruit yield estimation from smartphone cameras, by adapting Deep Learning algorithms originally developed for crowd counting. We test GBCNet using cross-validation procedure on two original datasets CR1 and CR2 of grape pictures taken in-field before veraison. A total of 35,668 berries have been manually annotated for the task. GBCNet achieves good performances on both the seven grape varieties dataset CR1, although with a different accuracy level depending on the variety, and on the single variety dataset CR2: in particular Mean Average Error (MAE) ranges from 0.85% for Pinot Gris to 11.73% for Marzemino on CR1 and reaches 7.24% on the Teroldego CR2 dataset. |
| first_indexed | 2024-03-10T18:27:14Z |
| format | Article |
| id | doaj.art-eeaee14b282a4da9b9964b5877de1c6f |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T18:27:14Z |
| publishDate | 2020-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-eeaee14b282a4da9b9964b5877de1c6f2023-11-20T06:55:15ZengMDPI AGApplied Sciences2076-34172020-07-011014487010.3390/app10144870GBCNet: In-Field Grape Berries Counting for Yield Estimation by Dilated CNNsLuca Coviello0Marco Cristoforetti1Giuseppe Jurman2Cesare Furlanello3Fondazione Bruno Kessler, 38123 Trento, ItalyFondazione Bruno Kessler, 38123 Trento, ItalyFondazione Bruno Kessler, 38123 Trento, ItalyFondazione Bruno Kessler, 38123 Trento, ItalyWe introduce here the Grape Berries Counting Net (GBCNet), a tool for accurate fruit yield estimation from smartphone cameras, by adapting Deep Learning algorithms originally developed for crowd counting. We test GBCNet using cross-validation procedure on two original datasets CR1 and CR2 of grape pictures taken in-field before veraison. A total of 35,668 berries have been manually annotated for the task. GBCNet achieves good performances on both the seven grape varieties dataset CR1, although with a different accuracy level depending on the variety, and on the single variety dataset CR2: in particular Mean Average Error (MAE) ranges from 0.85% for Pinot Gris to 11.73% for Marzemino on CR1 and reaches 7.24% on the Teroldego CR2 dataset.https://www.mdpi.com/2076-3417/10/14/4870digital agriculturegrape yield estimateberries countingdeep learningDilated CNN |
| spellingShingle | Luca Coviello Marco Cristoforetti Giuseppe Jurman Cesare Furlanello GBCNet: In-Field Grape Berries Counting for Yield Estimation by Dilated CNNs Applied Sciences digital agriculture grape yield estimate berries counting deep learning Dilated CNN |
| title | GBCNet: In-Field Grape Berries Counting for Yield Estimation by Dilated CNNs |
| title_full | GBCNet: In-Field Grape Berries Counting for Yield Estimation by Dilated CNNs |
| title_fullStr | GBCNet: In-Field Grape Berries Counting for Yield Estimation by Dilated CNNs |
| title_full_unstemmed | GBCNet: In-Field Grape Berries Counting for Yield Estimation by Dilated CNNs |
| title_short | GBCNet: In-Field Grape Berries Counting for Yield Estimation by Dilated CNNs |
| title_sort | gbcnet in field grape berries counting for yield estimation by dilated cnns |
| topic | digital agriculture grape yield estimate berries counting deep learning Dilated CNN |
| url | https://www.mdpi.com/2076-3417/10/14/4870 |
| work_keys_str_mv | AT lucacoviello gbcnetinfieldgrapeberriescountingforyieldestimationbydilatedcnns AT marcocristoforetti gbcnetinfieldgrapeberriescountingforyieldestimationbydilatedcnns AT giuseppejurman gbcnetinfieldgrapeberriescountingforyieldestimationbydilatedcnns AT cesarefurlanello gbcnetinfieldgrapeberriescountingforyieldestimationbydilatedcnns |