Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Mar 3, 2026

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
12:06

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

4.8K

Deep Count: Fruit Counting Based on Deep Simulated Learning.

Maryam Rahnemoonfar1, Clay Sheppard2

  • 1Department of Computer Science, Texas A&M University-Corpus Christi, Corpus Christi, TX 78412, USA. maryam.rahnemoonfar@tamucc.edu.

Sensors (Basel, Switzerland)
|April 21, 2017
PubMed
Summary

This study introduces a deep learning model for automated fruit yield estimation, trained on synthetic data and tested on real images. The approach offers an efficient and accurate solution for farmers, overcoming manual counting limitations.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

3DAeroRelief: The first 3D Benchmark UAV Dataset for Post-Disaster Assessment.

Scientific data·2026
Same author

RescueNet: A High Resolution UAV Semantic Segmentation Dataset for Natural Disaster Damage Assessment.

Scientific data·2023
Same author

AI Radar Sensor: Creating Radar Depth Sounder Images Based on Generative Adversarial Network.

Sensors (Basel, Switzerland)·2019
See all related articles

Area of Science:

  • Computer Vision
  • Deep Learning
  • Robotic Agriculture

Background:

  • Deep learning advancements in computer vision require extensive labeled training data, which is costly to acquire.
  • Manual fruit and flower counting for yield estimation is time-consuming, expensive, and impractical for large agricultural fields.

Purpose of the Study:

  • To develop a simulated deep convolutional neural network for accurate automatic yield estimation.
  • To provide farmers with precise crop counts for improved decision-making in cultivation and resource management.

Main Methods:

  • Utilized a modified Inception-ResNet architecture to capture multi-scale features for robust fruit detection.
  • Trained the deep convolutional neural network exclusively on synthetic data.
  • Tested the model's performance on real-world agricultural images.
Keywords:
agricultural sensorsdeep learningsimulated learningyield estimation

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.1K
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

2.1K

Related Experiment Videos

Last Updated: Mar 3, 2026

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
12:06

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

4.8K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.1K
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

2.1K

Main Results:

  • Achieved 91% average test accuracy on real images and 93% on synthetic images.
  • The algorithm demonstrated efficient counting even with occlusions, shadows, and overlapping fruits.
  • The model proves effective in challenging visual conditions common in orchards.

Conclusions:

  • Simulated deep learning offers a cost-effective and accurate method for agricultural yield estimation.
  • Automated yield estimation using robotic agriculture is a viable and practical solution for modern farming.
  • The developed network provides a scalable and efficient tool for precision agriculture.