Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Light Acquisition

Light Acquisition

In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.

You might also read

Related Articles

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

Sort by

Same author

A dual-mechanism activated fluorescent chemosensor for nanomolar bismuth(III) detection with demonstrated real-sample, anticounterfeit, swab/strip, smartphone, imaging & logic-gate applications.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2026

Same author

Secured framework for IoT based healthcare application.

Scientific reports·2026

Same author

Performance analysis of various codec of voice traffic in IEEE 802.22 cognitive radio network module using NETSIM.

Scientific reports·2026

Same author

Machine learning driven clustering for silhouetting 5G network throughput.

Scientific reports·2026

Same author

Dynamic channel allocation for secondary users in cognitive radio network.

Scientific reports·2026

Same author

Smart IoT applications of multi attack detection using cluster F1MI approach.

Scientific reports·2026

Search research articles

Related Experiment Video

Updated: Jan 12, 2026

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

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

Published on: February 9, 2024

Detection of commercial crop weeds using machine learning algorithms.

Parameswaran Ramesh^1,2, G Prabakaran³, Vidhya Nagavel⁴

¹Department of Electronics Engineering, Madras Institute of Technology, Anna University, Chennai, India. parameswaran0789@gmail.com.

Scientific Reports

|November 5, 2025

Summary

This study enhances YOLOv5 for crop classification, improving weed detection in tomatoes, chili, and cotton. The modified algorithm boosts accuracy and efficiency in agricultural applications.

Keywords:

Crops Machine learning Precision Spatial feature Yolo

More Related Videos

Protocols for Robust Herbicide Resistance Testing in Different Weed Species

Protocols for Robust Herbicide Resistance Testing in Different Weed Species

Published on: July 2, 2015

Measuring Rates of Herbicide Metabolism in Dicot Weeds with an Excised Leaf Assay

Measuring Rates of Herbicide Metabolism in Dicot Weeds with an Excised Leaf Assay

Published on: September 7, 2015

Related Experiment Videos

Last Updated: Jan 12, 2026

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

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

Published on: February 9, 2024

Protocols for Robust Herbicide Resistance Testing in Different Weed Species

Protocols for Robust Herbicide Resistance Testing in Different Weed Species

Published on: July 2, 2015

Measuring Rates of Herbicide Metabolism in Dicot Weeds with an Excised Leaf Assay

Measuring Rates of Herbicide Metabolism in Dicot Weeds with an Excised Leaf Assay

Published on: September 7, 2015

Area of Science:

Agricultural Science
Computer Vision
Machine Learning

Background:

Accurate crop classification and weed detection are crucial for optimizing agricultural practices and yields.
Traditional methods often struggle with the complexity and variability of field conditions.
Object detection algorithms offer a promising avenue for automated agricultural monitoring.

Purpose of the Study:

To investigate the performance of YOLOv5 for classifying commercial crops (tomatoes, chili, cotton) and detecting weeds.
To evaluate and enhance the YOLOv5 algorithm's accuracy, detection time, and mean Average Precision (mAP) using adaptively spatial feature fusion (ASFF) modules.
To assess the impact of the enhanced algorithm on computational efficiency and model compactness.

Main Methods:

Utilized YOLOv5 object detection algorithm on datasets comprising images of tomatoes, chili, cotton, and weeds from Tamil Nadu farms.
Computed performance metrics including F1 score, detection time, and mAP for the baseline YOLOv5 model.
Integrated adaptively spatial feature fusion (ASFF) blocks into the YOLOv5 architecture to create an enhanced model for further evaluation.

Main Results:

Baseline YOLOv5 achieved F1 scores of 98% (tomato), 91% (cotton), and 78% (chili), with high mAP values.
The enhanced YOLOv5 with ASFF modules improved F1 scores to 99.7% (tomato), 93.53% (cotton), and 79.4% (chili).
The enhanced model showed a ~0.5% increase in mAP with a negligible increase in computations, resulting in a more compact model.

Conclusions:

The enhanced YOLOv5 algorithm significantly improves weed detection and crop classification accuracy in agricultural settings.
Adaptively spatial feature fusion (ASFF) modules are effective in boosting YOLOv5 performance without substantial computational overhead.
This research demonstrates the potential of advanced deep learning models for precision agriculture and automated farm management.