Yield estimation in vineyards by visual grape detection

Nuske, Stephen; Achar, Supreeth; Bates, Terry; Narasimhan, Srinivasa G.; Singh, Sanjiv

doi:10.1109/iros.2011.6095069

Cited by 122 publications

(28 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To overcome the limitations of the manual methods, modern techniques have employed sensors attached to automatic harvesters to monitor yield during the harvesting process [3]. Yield estimation before harvest is becoming possible, with increasing accuracies when making use of non-invasive proximal remote sensing (PRS) technology and techniques [8,9,10,11,12].…”

Section: Introductionmentioning

confidence: 99%

Investigating 2-D and 3-D Proximal Remote Sensing Techniques for Vineyard Yield Estimation

Hacking

Poona

Manzan

et al. 2019

Sensors

View full text Add to dashboard Cite

Vineyard yield estimation provides the winegrower with insightful information regarding the expected yield, facilitating managerial decisions to achieve maximum quantity and quality and assisting the winery with logistics. The use of proximal remote sensing technology and techniques for yield estimation has produced limited success within viticulture. In this study, 2-D RGB and 3-D RGB-D (Kinect sensor) imagery were investigated for yield estimation in a vertical shoot positioned (VSP) vineyard. Three experiments were implemented, including two measurement levels and two canopy treatments. The RGB imagery (bunch- and plant-level) underwent image segmentation before the fruit area was estimated using a calibrated pixel area. RGB-D imagery captured at bunch-level (mesh) and plant-level (point cloud) was reconstructed for fruit volume estimation. The RGB and RGB-D measurements utilised cross-validation to determine fruit mass, which was subsequently used for yield estimation. Experiment one’s (laboratory conditions) bunch-level results achieved a high yield estimation agreement with RGB-D imagery (r2 = 0.950), which outperformed RGB imagery (r2 = 0.889). Both RGB and RGB-D performed similarly in experiment two (bunch-level), while RGB outperformed RGB-D in experiment three (plant-level). The RGB-D sensor (Kinect) is suited to ideal laboratory conditions, while the robust RGB methodology is suitable for both laboratory and in-situ yield estimation.

show abstract

Section: Introductionmentioning

confidence: 99%

Investigating 2-D and 3-D Proximal Remote Sensing Techniques for Vineyard Yield Estimation

Hacking

Poona

Manzan

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Other research in this field [10], [11] have results near to 98% in the first case, and 91% in the second. But in the first case the results came from the detection of individual berries, reason why, are not comparable with our result, because we estimate bunch's area.…”

Section: Discussionmentioning

confidence: 72%

Feature extraction on vineyard by Gustafson Kessel FCM and K-means

Correa

Valero

Elorza

et al. 2012

2012 16th IEEE Mediterranean Electrotechnical Conference

View full text Add to dashboard Cite

Image segmentation is a process by which an image is partitioned into regions with similar features. Many approaches have been proposed for color images segmentation, but Fuzzy CMeans has been widely used, because it has a good performance in a wide class of images. However, it is not adequate for noisy images and it takes longer runtimes, as compared to other method like K-means. For this reason, several methods have been proposed to improve these weaknesses. Methods like Fuzzy C-Means with Gustafson-Kessel algorithm (FCM-GK), which improve its performance against the noise, but increase significantly the runtime. In this paper we propose to use the centroids generated by GK-FCM algorithms as seeding for K-means algorithm in order to accelerate the runtime and improve the performance of K-means with random seeding. These segmentation techniques were applied to feature extraction on vineyard images. Segmented images were evaluated using several quality parameters such as the rate of correctly classified area and runtime.

show abstract

“…This volume limited by the hull (Vc) collects half of the whole cluster due to the field of view of the camera and the limitations of the branches and leaves, closing the hidden side of the cluster by a flat surface. Because the convex hull includes empty spaces where there are no berries, as well as the exclusivity of the visible side of the bunch it is necessary to include an empirical correction factor (K) (Nuske et al, 2011;Nuske et al, 2012) that will refine the estimated volume (Ve).…”

Section: Vmmentioning

confidence: 99%

“…For these reasons, in recent years image analysis has begun to be applied in viticulture in attempts to assess the vegetative state or performance of vineyards in some countries such as Australia http://dx.doi.org/10.1016/j.compag.2014.10.003 0168-1699/Ó 2014 Elsevier B.V. All rights reserved. (Dunn and Martin, 2004) or the U.S. (Nuske et al, 2011). More concretely, Dunn and Martin (2004) captured in field images using a white screen behind the canopy and extracted the colour features to classify the berry clusters, using manual thresholds and tolerances for the segmentation.…”

Section: Introductionmentioning

confidence: 99%

“…More concretely, Dunn and Martin (2004) captured in field images using a white screen behind the canopy and extracted the colour features to classify the berry clusters, using manual thresholds and tolerances for the segmentation. The work of Nuske et al (2011) involves a visible light camera boarded in a small vehicle to survey the entire vineyard. The berries are detected based on a 2D radial symmetry transform to extract their center, and then are classified based on their colour and texture.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation