Grape detection with convolutional neural networks

Cecotti, Hubert; Rivera, Agustín; Farhadloo, Majid; Pedroza, Miguel A.

doi:10.1016/j.eswa.2020.113588

Cited by 67 publications

(41 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In today's pattern recognition applications and methods, the convolutional neural network (CNN) structures represent a huge breakthrough in image analyzing. The CNN structures largely exploit the texture content and can be found at the core of everything from remote sensing to automated tumor segmentation (Mahmood et al 2017;Ullah et al 2018;de Assis Neto et al 2020;Cecotti et al 2020).…”

Section: Convolutional Neural Network Designmentioning

confidence: 99%

TPCNN: Two-path convolutional neural network for tumor and liver segmentation in CT images using a novel encoding approach

Aghamohammadi

Ranjbarzadeh

Naiemi

et al. 2021

Expert Systems with Applications

View full text Add to dashboard Cite

Automatic liver and tumour segmentation in CT images are crucial in numerous clinical applications, such as postoperative assessment, surgical planning, and pathological diagnosis of hepatic diseases. However, there are still a considerable number of difficulties to overcome due to the fuzzy boundary, irregular shapes, and complex tissues of the liver. In this paper, for liver and tumor segmentation and to overcome the mentioned challenges a simple but powerful strategy is presented based on a cascade convolutional neural network. At the first, the input image is normalized using the Z-Score algorithm. This normalized image provides more information about the boundary of tumor and liver. Also, the Local Direction of Gradient (LDOG) which is a novel encoding algorithm is proposed to demonstrate some key features inside the image. The proposed encoding image is highly effective in recognizing the border of liver, even in the regions close to the touching organs. Then, a cascade CNN structure for extracting both local and semi-global features is used which utilized the original image and two other obtained images as the input data.Rather than using a complex deep CNN model with a lot of hyperparameters, we employ a simple but effective model to decrease the train and testing time. Our technique outperforms the state-ofthe-art works in terms of segmentation accuracy and efficiency.

show abstract

Section: Convolutional Neural Network Designmentioning

confidence: 99%

TPCNN: Two-path convolutional neural network for tumor and liver segmentation in CT images using a novel encoding approach

Aghamohammadi

Ranjbarzadeh

Naiemi

et al. 2021

Expert Systems with Applications

View full text Add to dashboard Cite

show abstract

“…For the evaluation of the GBCNet performance the dataset was randomly split in 102 images for train and 26 images for test, corresponding to 13,353 berries in training and 3653 berries in test. The same 80-20% split is adopted, for example, in [30,31] . Resampling by 5-fold Cross Validation (5-CV) was applied on the training dataset.…”

Section: In-field Imagesmentioning

confidence: 99%

“…Different network architecture and training solutions have been proposed in the literature, from early attempts [24] to the use of LeNet [25], or AlexNet [26] or data augmentation with simulated training [27] aiming at different tasks such as grape variety identification. However, Convolutional (CNN) architectures and their several variants such as Mask R-CNN [28] have become the de facto standard for yield estimation [13,29], also enhanced by companion techniques like semantic segmentation [5], transfer learning [30] and three-dimensional association to integrate and spatialize the detection results [31] to overcome multiple counting and occlusions, and even extending to generic fruit detection [32] or integrating with non-imaging approaches, for instance, using historical data [33].…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2020

View full text Add to dashboard Cite

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.

show abstract

“…In particular, the peduncle of grapes is often small and easily obscured by branches and leaves. Therefore, accurate position information relies on extracting the appearance features of fruit, including the color, size, shape, and texture ( Lu and Sang, 2015 ; Rizon et al, 2015 ; Yu et al, 2019 ; Cecotti et al, 2020 ). In the study by Luo et al (2018) , color features were used to extract more effective color components for grapes, which were then segmented to capture images using the k-means clustering algorithm and obtain contours of the grapes.…”

Section: Introductionmentioning

confidence: 99%

Fruit Detection and Pose Estimation for Grape Cluster–Harvesting Robot Using Binocular Imagery Based on Deep Neural Networks

et al. 2021

View full text Add to dashboard Cite

Reliable and robust fruit-detection algorithms in nonstructural environments are essential for the efficient use of harvesting robots. The pose of fruits is crucial to guide robots to approach target fruits for collision-free picking. To achieve accurate picking, this study investigates an approach to detect fruit and estimate its pose. First, the state-of-the-art mask region convolutional neural network (Mask R-CNN) is deployed to segment binocular images to output the mask image of the target fruit. Next, a grape point cloud extracted from the images was filtered and denoised to obtain an accurate grape point cloud. Finally, the accurate grape point cloud was used with the RANSAC algorithm for grape cylinder model fitting, and the axis of the cylinder model was used to estimate the pose of the grape. A dataset was acquired in a vineyard to evaluate the performance of the proposed approach in a nonstructural environment. The fruit detection results of 210 test images show that the average precision, recall, and intersection over union (IOU) are 89.53, 95.33, and 82.00%, respectively. The detection and point cloud segmentation for each grape took approximately 1.7 s. The demonstrated performance of the developed method indicates that it can be applied to grape-harvesting robots.

show abstract

Grape detection with convolutional neural networks

Cited by 67 publications

References 32 publications

TPCNN: Two-path convolutional neural network for tumor and liver segmentation in CT images using a novel encoding approach

TPCNN: Two-path convolutional neural network for tumor and liver segmentation in CT images using a novel encoding approach

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

Fruit Detection and Pose Estimation for Grape Cluster–Harvesting Robot Using Binocular Imagery Based on Deep Neural Networks

Contact Info

Product

Resources

About