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

Expectation Violation Influences Neural Responses to the Accessibility of Cognitions Related to Suicide and Life: A Simultaneous EEG-fNIRS Study.

Brain sciences·2026

Same author

Linking changes in sulcal morphometry to cognitive development from childhood to adolescence.

Communications biology·2026

Same author

Spatiotemporal dynamics of the human cortical functional hierarchy across the lifespan.

Nature communications·2026

Same author

Automatic measurement of mesenteric vascular and portal vein parameters via PE-NET in the diagnosis of Crohn's disease.

Frontiers in medicine·2025

Same author

Expectation violation reduces the accessibility of implicit suicidal concepts and explicit life concepts.

Frontiers in psychology·2025

Same author

A precision grading method for walnut leaf brown spot disease integrating hierarchical feature selection and dynamic multi-scale convolution.

Frontiers in plant science·2025

Search research articles

Related Experiment Video

Updated: Feb 17, 2026

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

PointNeXt-DBSCAN: a hybrid point cloud deep learning framework for multi-stage cotton leaf instance segmentation.

Zeyu Lei^1,2, Debin Zeng^1,3, Liangfang Zheng^1,3

¹College of Information Engineering, Tarim University, Alaer, China.

Frontiers in Plant Science

|February 16, 2026

Summary

This summary is machine-generated.

This study introduces a novel hybrid framework for precise cotton leaf segmentation from 3D point clouds. The method significantly improves accuracy in identifying individual leaves, aiding in automated plant phenotyping.

Keywords:

3D point clouds cotton plant leaves deep learning multi-stage growth monitoring point cloud segmentation

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: Feb 17, 2026

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Area of Science:

Agricultural Engineering
Computer Vision
Plant Science

Background:

Organ-level instance segmentation in cotton point clouds is challenging due to morphological variations and leaf occlusion.
Accurate leaf extraction is crucial for automated phenotyping and trait analysis.

Purpose of the Study:

To develop a high-precision framework for cotton leaf instance segmentation.
To address challenges in segmenting cotton plants across various growth stages.

Main Methods:

A hybrid framework combining PointNeXt for semantic segmentation and density-adaptive DBSCAN for instance segmentation was proposed.
A dataset of 1,065 cotton plants was constructed and augmented.
A two-stage pipeline was employed for semantic and instance segmentation.

Main Results:

Semantic segmentation achieved a mean Intersection over Union (mIoU) of 0.9846, a 7.2% improvement over PointNet++.
Instance segmentation achieved an Adjusted Rand Index (ARI) of 0.983, reducing over-segmentation by 63%.
The framework maintained <3% error for leaves <5 cm².

Conclusions:

The proposed hybrid framework offers reliable technical support for automated extraction of key cotton phenotypic traits.
This method enhances the accuracy of leaf area index and leaf inclination distribution measurements.
The framework effectively handles morphological variations and leaf occlusion in cotton plants.