Low-Cost, Computer Vision-Based, Prebloom Cluster Count Prediction in Vineyards
Traditional methods for estimating the number of grape clusters in a vineyard generally involve manually counting the number of clusters per vine in a subset of the vineyard and scaling by the total number of vines; a technique that can be laborious, costly, and with an accuracy that depends on the...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-04-01
|
| Series: | Frontiers in Agronomy |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fagro.2021.648080/full |
| _version_ | 1818409307068170240 |
|---|---|
| author | Jonathan Jaramillo Justine Vanden Heuvel Kirstin H. Petersen |
| author_facet | Jonathan Jaramillo Justine Vanden Heuvel Kirstin H. Petersen |
| author_sort | Jonathan Jaramillo |
| collection | DOAJ |
| description | Traditional methods for estimating the number of grape clusters in a vineyard generally involve manually counting the number of clusters per vine in a subset of the vineyard and scaling by the total number of vines; a technique that can be laborious, costly, and with an accuracy that depends on the size of the sample. We demonstrate that traditional cluster counting has a high variance in yield estimate accuracy and is highly sensitive to the particular counter and choice of the subset of counted vines. We propose a simple computer vision-based method for improving the reliability of these yield estimates using cheap and easily accessible hardware for growers. This method detects, tracks, and counts clusters and shoots in videos collected using a smartphone camera that is driven or walked through the vineyard at night. With a random selection of calibration data, this method achieved an average cluster count error of 4.9% across two growing seasons and two cultivars by detecting and counting clusters. Traditional methods yielded an average cluster count error of 7.9% across the same dataset. Moreover, the proposed method yielded a maximum error of 12.6% while the traditional method yielded a maximum error of 23.5%. The proposed method can be deployed before flowering, while the canopy is sparse, which improves maximum visibility of clusters and shoots, generalizability across different cultivars and growing seasons, and earlier yield estimates compared to prior work in the area. |
| first_indexed | 2024-12-14T09:57:32Z |
| format | Article |
| id | doaj.art-35964cd078da457b9846cd3789ca91d8 |
| institution | Directory Open Access Journal |
| issn | 2673-3218 |
| language | English |
| last_indexed | 2024-12-14T09:57:32Z |
| publishDate | 2021-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Agronomy |
| spelling | doaj.art-35964cd078da457b9846cd3789ca91d82022-12-21T23:07:21ZengFrontiers Media S.A.Frontiers in Agronomy2673-32182021-04-01310.3389/fagro.2021.648080648080Low-Cost, Computer Vision-Based, Prebloom Cluster Count Prediction in VineyardsJonathan Jaramillo0Justine Vanden Heuvel1Kirstin H. Petersen2Collective Embodied Intelligence Lab, Electrical and Computer Engineering, Cornell University, Ithaca, NY, United StatesCollege of Agriculture and Life Sciences, School of Integrative Plant Science, Cornell University, Ithaca, NY, United StatesCollective Embodied Intelligence Lab, Electrical and Computer Engineering, Cornell University, Ithaca, NY, United StatesTraditional methods for estimating the number of grape clusters in a vineyard generally involve manually counting the number of clusters per vine in a subset of the vineyard and scaling by the total number of vines; a technique that can be laborious, costly, and with an accuracy that depends on the size of the sample. We demonstrate that traditional cluster counting has a high variance in yield estimate accuracy and is highly sensitive to the particular counter and choice of the subset of counted vines. We propose a simple computer vision-based method for improving the reliability of these yield estimates using cheap and easily accessible hardware for growers. This method detects, tracks, and counts clusters and shoots in videos collected using a smartphone camera that is driven or walked through the vineyard at night. With a random selection of calibration data, this method achieved an average cluster count error of 4.9% across two growing seasons and two cultivars by detecting and counting clusters. Traditional methods yielded an average cluster count error of 7.9% across the same dataset. Moreover, the proposed method yielded a maximum error of 12.6% while the traditional method yielded a maximum error of 23.5%. The proposed method can be deployed before flowering, while the canopy is sparse, which improves maximum visibility of clusters and shoots, generalizability across different cultivars and growing seasons, and earlier yield estimates compared to prior work in the area.https://www.frontiersin.org/articles/10.3389/fagro.2021.648080/fullviticulturefield roboticscomputer visionmachine learningearly yield prediction |
| spellingShingle | Jonathan Jaramillo Justine Vanden Heuvel Kirstin H. Petersen Low-Cost, Computer Vision-Based, Prebloom Cluster Count Prediction in Vineyards Frontiers in Agronomy viticulture field robotics computer vision machine learning early yield prediction |
| title | Low-Cost, Computer Vision-Based, Prebloom Cluster Count Prediction in Vineyards |
| title_full | Low-Cost, Computer Vision-Based, Prebloom Cluster Count Prediction in Vineyards |
| title_fullStr | Low-Cost, Computer Vision-Based, Prebloom Cluster Count Prediction in Vineyards |
| title_full_unstemmed | Low-Cost, Computer Vision-Based, Prebloom Cluster Count Prediction in Vineyards |
| title_short | Low-Cost, Computer Vision-Based, Prebloom Cluster Count Prediction in Vineyards |
| title_sort | low cost computer vision based prebloom cluster count prediction in vineyards |
| topic | viticulture field robotics computer vision machine learning early yield prediction |
| url | https://www.frontiersin.org/articles/10.3389/fagro.2021.648080/full |
| work_keys_str_mv | AT jonathanjaramillo lowcostcomputervisionbasedprebloomclustercountpredictioninvineyards AT justinevandenheuvel lowcostcomputervisionbasedprebloomclustercountpredictioninvineyards AT kirstinhpetersen lowcostcomputervisionbasedprebloomclustercountpredictioninvineyards |