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 Concept Videos

Extraction: Advanced Methods00:56

Extraction: Advanced Methods

493
Metal ions can be separated from one another by complexation with organic ligands–the chelating agent– to form uncharged chelates. Here, the chelating agent must contain hydrophobic groups and behave as a weak acid, losing a proton to bind with the metal. Since most organic ligands used in this process are insoluble or undergo oxidation in the aqueous phase, the chelating agent is initially added to the organic phase and extracted into the aqueous phase. The metal-ligand complex is...
493

You might also read

Related Articles

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

Sort by
Same author

Muriicola marianensis sp. nov., isolated from seawater.

International journal of systematic and evolutionary microbiology·2014
Same author

Protective effect of apigenin on ischemia/reperfusion injury of the isolated rat heart.

Cardiovascular toxicology·2014
Same author

Inhibition of monocyte adhesion to brain-derived endothelial cells by dual functional RNA chimeras.

Molecular therapy. Nucleic acids·2014
Same author

Presynaptic GABAergic inhibition regulated by BDNF contributes to neuropathic pain induction.

Nature communications·2014
Same author

Advances in malignant peritoneal mesothelioma.

International journal of colorectal disease·2014
Same author

Regulation of BGC-823 cell sensitivity to adriamycin via miRNA-135a-5p.

Oncology reports·2014

Related Experiment Video

Updated: Jul 23, 2025

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.0K

Fruit Detection and Counting in Apple Orchards Based on Improved Yolov7 and Multi-Object Tracking Methods.

Jing Hu1, Chuang Fan1, Zhoupu Wang1

  • 1School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan 430024, China.

Sensors (Basel, Switzerland)
|July 14, 2023
PubMed
Summary

This study introduces an improved fruit yield counting model combining Vision Transformer and Yolov7, enhancing accuracy in complex agricultural settings. The new model significantly boosts performance in detecting and tracking fruits, aiding logistics and storage optimization.

Keywords:
multi-object tracingobject detectself-attentionyolov7

More Related Videos

Olfactory Behaviors Assayed by Computer Tracking Of Drosophila in a Four-quadrant Olfactometer
08:52

Olfactory Behaviors Assayed by Computer Tracking Of Drosophila in a Four-quadrant Olfactometer

Published on: August 20, 2016

15.8K
Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.3K

Related Experiment Videos

Last Updated: Jul 23, 2025

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.0K
Olfactory Behaviors Assayed by Computer Tracking Of Drosophila in a Four-quadrant Olfactometer
08:52

Olfactory Behaviors Assayed by Computer Tracking Of Drosophila in a Four-quadrant Olfactometer

Published on: August 20, 2016

15.8K
Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.3K

Area of Science:

  • Computer Vision
  • Agricultural Technology
  • Machine Learning

Background:

  • Accurate fruit yield prediction is vital for optimizing logistics and storage, especially with rising online fruit sales.
  • Existing manual, sensor, and CNN-based methods face limitations in fruit yield counting due to issues like crop overlap, variable lighting, occlusion, and fruit dissimilarity.
  • There is a need for advanced computer vision models to overcome these challenges in agricultural settings.

Purpose of the Study:

  • To develop a novel object detection model for accurate fruit yield counting in complex agricultural environments.
  • To enhance the effectiveness of existing object detection models by integrating attention mechanisms and multi-object tracking.
  • To improve the precision of fruit counting across video frames for better yield assessment.

Main Methods:

  • A novel variant model was proposed, combining the self-attentive mechanism of Vision Transformer with the Yolov7 object detection model.
  • The model incorporates two attention mechanisms: Convolutional Block Attention Module (CBAM) and Coordinate Attention (CA).
  • Multi-objective tracking methods, SORT and Cascade-SORT, were integrated for inter-frame fruit counting in video sequences.

Main Results:

  • The Yolov7-CA model achieved a 91.3% mean Average Precision (mAP) and a 0.85 F1 score, outperforming standard Yolov7 by 4% in mAP and 0.02 in F1 score.
  • The integrated multi-object tracking methods showed significant Mean Absolute Error (MAE) improvements for inter-frame counting across test videos.
  • A 0.642 improvement in MAE was observed using the proposed multi-object tracking method compared to Yolov7 alone.

Conclusions:

  • The proposed model, integrating Vision Transformer's attention with Yolov7, significantly improves fruit yield counting accuracy.
  • The incorporation of multi-object tracking enhances the model's capability for continuous fruit counting in dynamic video sequences.
  • These advancements hold potential for improving fruit yield assessment and decision-making within the fruit industry.