GBCNet: In-Field Grape Berries Counting for Yield Estimation by Dilated CNNs

Coviello, Luca; Cristoforetti, Marco; Jurman, Giuseppe; Furlanello, Cesare

doi:10.3390/app10144870

Cited by 37 publications

(13 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…That work was continued by Mirbod et al [ 45 ] that used two algorithms (Angular invariant maximal detector and Sum of gradient estimator) for berry diameter estimation. Coviello et al [ 46 ] introduced the Grape Berry Counting Network (GBCNet). It belongs to the family of Dilated CNNs and it is composed by ten pre-trained convolutional layers for feature extraction and by a dilated CNN for density map generation.…”

Section: Introductionmentioning

confidence: 99%

In-Field Automatic Detection of Grape Bunches under a Totally Uncontrolled Environment

Ghiani

Sassu

Palumbo

et al. 2021

Sensors

View full text Add to dashboard Cite

An early estimation of the exact number of fruits, flowers, and trees helps farmers to make better decisions on cultivation practices, plant disease prevention, and the size of harvest labor force. The current practice of yield estimation based on manual counting of fruits or flowers by workers is a time consuming and expensive process and it is not feasible for large fields. Automatic yield estimation based on robotic agriculture provides a viable solution in this regard. In a typical image classification process, the task is not only to specify the presence or absence of a given object on a specific location, while counting how many objects are present in the scene. The success of these tasks largely depends on the availability of a large amount of training samples. This paper presents a detector of bunches of one fruit, grape, based on a deep convolutional neural network trained to detect vine bunches directly on the field. Experimental results show a 91% mean Average Precision.

show abstract

Section: Introductionmentioning

confidence: 99%

In-Field Automatic Detection of Grape Bunches under a Totally Uncontrolled Environment

Ghiani

Sassu

Palumbo

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Harvest estimation is a problem to which machine learning, computer vision, and image processing can be applied using one or a combination of techniques [86][87][88]. In proximal sensing methods, detection, segmentation, and counting of either individual grapes or bunches are complex in most image-based methodologies [38,59,89], especially in non-disturbed canopies where occlusion [15,90], illumination, colors, and contrast [91,92] are challenging and in most cases are only demonstrated conceptually at a small scale [89].…”

Section: Resultsmentioning

confidence: 99%

Vineyard Yield Estimation, Prediction, and Forecasting: A Systematic Literature Review

2021

View full text Add to dashboard Cite

Purpose—knowing in advance vineyard yield is a critical success factor so growers and winemakers can achieve the best balance between vegetative and reproductive growth. It is also essential for planning and regulatory purposes at the regional level. Estimation errors are mainly due to the high inter-annual and spatial variability and inadequate or poor performance sampling methods; therefore, improved applied methodologies are needed at different spatial scales. This paper aims to identify the alternatives to traditional estimation methods. Design/methodology/approach—this study consists of a systematic literature review of academic articles indexed on four databases collected based on multiple query strings conducted on title, abstract, and keywords. The articles were reviewed based on the research topic, methodology, data requirements, practical application, and scale using PRISMA as a guideline. Findings—the methodological approaches for yield estimation based on indirect methods are primarily applicable at a small scale and can provide better estimates than the traditional manual sampling. Nevertheless, most of these approaches are still in the research domain and lack practical applicability in real vineyards by the actual farmers. They mainly depend on computer vision and image processing algorithms, data-driven models based on vegetation indices and pollen data, and on relating climate, soil, vegetation, and crop management variables that can support dynamic crop simulation models. Research limitations—this work is based on academic articles published before June 2021. Therefore, scientific outputs published after this date are not included. Originality/value—this study contributes to perceiving the approaches for estimating vineyard yield and identifying research gaps for future developments, and supporting a future research agenda on this topic. To the best of the authors’ knowledge, it is the first systematic literature review fully dedicated to vineyard yield estimation, prediction, and forecasting methods.

show abstract

“…Several papers show that machine learning-based methods for analyzing data from imaging sensors provide an objective and fast method for counting visible berries (Diago et al, 2012;Kicherer et al, 2014;Nuske et al, 2014;Roscher et al, 2014;Aquino et al, 2017;Coviello et al, 2020;Zabawa et al, 2020), and thus for automated yield predictions in the field. One of the main challenges in deriving berry counts from image data taken in the field is occlusions, which generally causes an underestimation of the number of berries and yield (Zabawa et al 1 ).…”

Section: Introductionmentioning

confidence: 99%

Behind the Leaves: Estimation of Occluded Grapevine Berries With Conditional Generative Adversarial Networks

Kierdorf

Weber

Kicherer

et al. 2022

Front. Artif. Intell.

View full text Add to dashboard Cite

The need for accurate yield estimates for viticulture is becoming more important due to increasing competition in the wine market worldwide. One of the most promising methods to estimate the harvest is berry counting, as it can be approached non-destructively, and its process can be automated. In this article, we present a method that addresses the challenge of occluded berries with leaves to obtain a more accurate estimate of the number of berries that will enable a better estimate of the harvest. We use generative adversarial networks, a deep learning-based approach that generates a highly probable scenario behind the leaves exploiting learned patterns from images with non-occluded berries. Our experiments show that the estimate of the number of berries after applying our method is closer to the manually counted reference. In contrast to applying a factor to the berry count, our approach better adapts to local conditions by directly involving the appearance of the visible berries. Furthermore, we show that our approach can identify which areas in the image should be changed by adding new berries without explicitly requiring information about hidden areas.

show abstract

GBCNet: In-Field Grape Berries Counting for Yield Estimation by Dilated CNNs

Cited by 37 publications

References 41 publications

In-Field Automatic Detection of Grape Bunches under a Totally Uncontrolled Environment

In-Field Automatic Detection of Grape Bunches under a Totally Uncontrolled Environment

Vineyard Yield Estimation, Prediction, and Forecasting: A Systematic Literature Review

Behind the Leaves: Estimation of Occluded Grapevine Berries With Conditional Generative Adversarial Networks

Contact Info

Product

Resources

About