Single-Shot Convolution Neural Networks for Real-Time Fruit Detection Within the Tree

@article{Bresilla2019SingleShotCN,
  title={Single-Shot Convolution Neural Networks for Real-Time Fruit Detection Within the Tree},
  author={Kushtrim Bresilla and Giulio Demetrio Perulli and Alexandra Boini and Brunella Morandi and Luca Corelli Grappadelli and Luigi Manfrini},
  journal={Frontiers in Plant Science},
  year={2019},
  volume={10}
}
Image/video processing for fruit detection in the tree using hard-coded feature extraction algorithms has shown high accuracy on fruit detection during recent years. While accurate, these approaches even with high-end hardware are still computationally intensive and too slow for real-time systems. This paper details the use of deep convolution neural networks architecture based on single-stage detectors. Using deep-learning techniques eliminates the need for hard-code specific features for… 

Figures and Tables from this paper

Tomato Fruit Detection and Counting in Greenhouses Using Deep Learning

TLDR
Results on the detection of tomatoes in images taken in a greenhouse, using the MaskRCNN algorithm, which detects objects and also the pixels corresponding to each object are comparable to or better than the metrics reported by earlier work, even though those were obtained in laboratory conditions or using higher resolution images.

High-Quality Coarse-to-Fine Fruit Detector for Harvesting Robot in Open Environment

TLDR
An improved method based on coarse-to-fine multitask cascaded convolutional networks (MTCNN) with three aspects to enable the practical application of fruit detection in orchards and it was concluded that the detector could be applied practically in the actual orchard environment.

Recent Advancements in Fruit Detection and Classification Using Deep Learning Techniques

TLDR
This article intensively discussed the datasets used by many scholars, the practical descriptors, the model’s implementation, and the challenges of using deep learning to detect and categorize fruits, and summarized the results of different deep learning methods applied in previous studies for the purpose of fruit detection and classification.

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

TLDR
A detector of bunches of one fruit, grape, based on a deep convolutional neural network trained to detect vine bunches directly on the field is presented, showing a 91% mean Average Precision.

Automatic Bunch Detection in White Grape Varieties Using YOLOv3, YOLOv4, and YOLOv5 Deep Learning Algorithms

Over the last few years, several Convolutional Neural Networks for object detection have been proposed, characterised by different accuracy and speed. In viticulture, yield estimation and prediction

Convolutional Neural Networks for Detection of Storage Disorders on ‘Abbé Fétel’ pears

TLDR
The present study tested the fast and operational convolution neural networks with “YOLO v3” architecture using the online platform Supervise.ly to detect on pear fruit ‘Abbé Fétel’ physiological disorders such as superficial scald and senescence scald.

Recognition and Classification of Fruits using Deep Learning Techniques

TLDR
This project attempts to address some of the challenges faced by the previous researchers by developing a methodology for the recognition and classification of fruits by using CNN, VGG16, and ResNet50 deep learning models.

Grading Methods for Fruit Freshness Based on Deep Learning

TLDR
A novel neural network model is constructed for fruit detection and freshness grading regarding multiclass fruit classification based on visual analysis of digital images using computer vision and deep learning.
...

References

SHOWING 1-10 OF 40 REFERENCES

Deep fruit detection in orchards

TLDR
The use of a state-of-the-art object detection framework, Faster R-CNN, in the context of fruit detection in orchards, including mangoes, almonds and apples, has resulted in the best yet detection performance for these orchard relative to previous works.

DeepFruits: A Fruit Detection System Using Deep Neural Networks

TLDR
A novel multi-modal Faster R-CNN model, which achieves state-of-the-art results compared to prior work with the F1 score, which takes into account both precision and recall performances improving from 0.807 to 0.838 for the detection of sweet pepper.

Deep Count: Fruit Counting Based on Deep Simulated Learning

TLDR
A simulated deep convolutional neural network for yield estimation based on robotic agriculture that counts efficiently even if fruits are under shadow, occluded by foliage, branches, or if there is some degree of overlap amongst fruits.

Apple detection in nighttime tree images using the geometry of light patches around highlights

Apple detection algorithm for robotic harvesting using a RGB-D camera

TLDR
The developed algorithm to detect apples on tree based on the color and depth images acquired with an RGB-D camera can meet the requirements for the robotic harvesting system and could be used for yield estimation and orchard monitoring in a management decision support system.

You Only Look Once: Unified, Real-Time Object Detection

TLDR
Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.

End-to-End Airplane Detection Using Transfer Learning in Remote Sensing Images

TLDR
This paper uses object detection technology based on deep learning for airplane detection in remote sensing images and adopts a single deep convolutional neural network and limited training samples to implement end-to-end trainable airplane detection.