Identifying veraison process of colored wine grapes in field conditions combining deep learning and image analysis

Shen, Lei; Chen, Shan; Mi, Zhiwen; Su, Jinya; Song, Yuyang; Fang, Yulin; Su, Baofeng

doi:10.1016/j.compag.2022.107268

Cited by 12 publications

(8 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Véraison is an essential stage of grape ripening, in that during this period, color, aromatic compounds, and minerals accumulate [8]. Red grape varieties start the accumulation of phenolic compounds during véraison [9]. A study conducted on different red grape varieties showed that the extraction of phenolic compounds from Cabernet Sauvignon is easier than from Monastrell grapes [10].…”

Section: Introductionmentioning

confidence: 99%

The Influence of Cabernet Sauvignon Ripeness, Healthy State and Maceration Time on Wine and Fermented Pomace Phenolic Profile

et al. 2023

View full text Add to dashboard Cite

The phenolic composition and antioxidant activity of wine and fermented pomace (FP) from Cabernet Sauvignon grapes harvested at three ripening stages were evaluated using LC-MS/MS and spectrophotometric analyses. An investigation of grey mold’s (Botrytis cinerea) influence on wine phenolic content modulation was conducted as well. Finally, the influence of the plant’s ripening stage on the dynamics of the phenolic compounds extracted from wine and FP obtained from fully ripe grapes was evaluated. In this study, the content of catechin, epicatechin, quercetin, and p-coumaric, gallic, and syringic acids was analyzed. Wine and FP were obtained after extended maceration during the spontaneous and inoculated fermentation of fully ripe grapes. When comparing the wine and FP obtained from véraison, fully ripe, and overripe grapes, catechin was the most abundant in wine (40.13 ± 3.25 mg/L) and quercetin in FP (10.96 ± 0.14 mg/kg). A decrease in analyzed phenolic compounds was noticed in wine produced from grapes affected by Botrytis cinerea, and the highest depletion was found for quercetin. The use of a winemaking technique that involved differing maceration periods and inoculation using yeasts as well as spontaneous fermentation significantly modulated the phenolic content of derived wines and FP. The dynamics of the phenolic compounds extracted into wine, evaluated using a principal component analysis (PCA), highlighted contents of catechin and epicatechin. After a decrease in maceration, the PCA revealed a notable content of gallic and syringic acids, as well as quercetin, in samples of FP. This study offers a perspective for future research and the development of functional food with a high content of phenolic compounds originating from red grape products, such as wine and fermented pomace.

show abstract

Section: Introductionmentioning

confidence: 99%

The Influence of Cabernet Sauvignon Ripeness, Healthy State and Maceration Time on Wine and Fermented Pomace Phenolic Profile

et al. 2023

View full text Add to dashboard Cite

show abstract

“…While numerous computer vision approaches have been developed to identify and measure fruits using deep-learning [ 16 – 18 , 23 , 34 , 38 , 43 ], they mostly aim at inferring their occlusion boundaries (i.e. visible edges), which differs from the true contours of the object of interest in the case of overlapping fruits, thus preventing to access their actual size.…”

Section: Discussionmentioning

confidence: 99%

“…shape, size, colour, degree of light exposure) and to the fact that they frequently overlap with other berries and plant parts. Deep-learning has shown to be an effective solution to this problem for a number of fruits such as oranges [ 16 ], blueberries [ 18 , 34 ], apples [ 17 , 23 ], strawberries [ 38 ] and grapevine berries [ 43 ]. In all these studies, an instance segmentation model (e.g.…”

Section: Introductionmentioning

confidence: 99%

“…Mask R-CNN [ 20 ]) was trained on manual annotations of visible fruit parts to retrieve the apparent contour of each fruit. This strategy is suitable for measuring their colour [ 43 ], counting them to estimate yield [ 51 ], or locating them for automatic fruit picking [ 47 ]. However, it misses the occluded parts of berries that are partially covered by neighbouring fruits, which frequently occurs in ordinary bunches, thus preventing the deduction of statistics related to their real shape such as volume.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Ripening dynamics revisited: an automated method to track the development of asynchronous berries on time-lapse images

Daviet,

Fournier,

Cabrera-Bosquet

et al. 2023

Plant Methods

View full text Add to dashboard Cite

Background Grapevine berries undergo asynchronous growth and ripening dynamics within the same bunch. Due to the lack of efficient methods to perform sequential non-destructive measurements on a representative number of individual berries, the genetic and environmental origins of this heterogeneity, remain nearly unknown. To address these limitations, we propose a method to track the growth and coloration kinetics of individual berries on time-lapse images of grapevine bunches. Results First, a deep-learning approach is used to detect berries with at least 50 ± 10% of visible contours, and infer the shape they would have in the absence of occlusions. Second, a tracking algorithm was developed to assign a common label to shapes representing the same berry along the time-series. Training and validation of the methods were performed on challenging image datasets acquired in a robotised high-throughput phenotyping platform. Berries were detected on various genotypes with a F1-score of 91.8%, and segmented with a mean absolute error of 4.1% on their area. Tracking allowed to label and retrieve the temporal identity of more than half of the segmented berries, with an accuracy of 98.1%. This method was used to extract individual growth and colour kinetics of various berries from the same bunch, allowing us to propose the first statistically relevant analysis of berry ripening kinetics, with a time resolution lower than one day. Conclusions We successfully developed a fully-automated open-source method to detect, segment and track overlapping berries in time-series of grapevine bunch images acquired in laboratory conditions. This makes it possible to quantify fine aspects of individual berry development, and to characterise the asynchrony within the bunch. The interest of such analysis was illustrated here for one cultivar, but the method has the potential to be applied in a high throughput phenotyping context. This opens the way for revisiting the genetic and environmental variations of the ripening dynamics. Such variations could be considered both from the point of view of fruit development and the phenological structure of the population, which would constitute a paradigm shift.

show abstract

“…On the other hand, Shen et al [21] introduced a novel method to accurately identify veraison in colored wine grapes under natural field-growing conditions. Initially, the authors utilized a semantic segmentation model to effectively eliminate the irrelevant background, and then a Mask R-CNN pipeline, which incorporates anchor parameter optimization, was utilized to further enhance the accuracy and robustness of the grape identification process.…”

Section: Introductionmentioning

confidence: 99%

A Grape Dataset for Instance Segmentation and Maturity Estimation

Blekos,

Chatzis,

Kotaidou

et al. 2023

Agronomy

View full text Add to dashboard Cite

Grape maturity estimation is vital in precise agriculture as it enables informed decision making for disease control, harvest timing, grape quality, and quantity assurance. Despite its importance, there are few large publicly available datasets that can be used to train accurate and robust grape segmentation and maturity estimation algorithms. To this end, this work proposes the CERTH grape dataset, a new sizeable dataset that is designed explicitly for evaluating deep learning algorithms in grape segmentation and maturity estimation. The proposed dataset is one of the largest currently available grape datasets in the literature, consisting of around 2500 images and almost 10 k grape bunches, annotated with masks and maturity levels. The images in the dataset were captured under various illumination conditions and viewing angles and with significant occlusions between grape bunches and leaves, making it a valuable resource for the research community. Thorough experiments were conducted using a plethora of general object detection methods to provide a baseline for the future development of accurate and robust grape segmentation and maturity estimation algorithms that can significantly advance research in the field of viticulture.

show abstract

Identifying veraison process of colored wine grapes in field conditions combining deep learning and image analysis

Cited by 12 publications

References 33 publications

The Influence of Cabernet Sauvignon Ripeness, Healthy State and Maceration Time on Wine and Fermented Pomace Phenolic Profile

The Influence of Cabernet Sauvignon Ripeness, Healthy State and Maceration Time on Wine and Fermented Pomace Phenolic Profile

Ripening dynamics revisited: an automated method to track the development of asynchronous berries on time-lapse images

A Grape Dataset for Instance Segmentation and Maturity Estimation

Contact Info

Product

Resources

About