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

Search research articles

Related Experiment Video

Updated: May 28, 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

PlantEFRSegnet: A Plant Point Cloud Segmentation Network Based on Edge Point Preservation and Feature Feedback

Bin Li¹, Peng Liu¹, Yonghan Zhang²

¹School of Computer Science, Northeast Electric Power University, Jilin 132012, China.

Sensors (Basel, Switzerland)

|May 27, 2026

Summary

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

ADFCNN-BiLSTM: A Deep Neural Network Based on Attention and Deformable Convolution for Network Intrusion Detection.

Sensors (Basel, Switzerland)·2025

Same author

Online Learning State Evaluation Method Based on Face Detection and Head Pose Estimation.

Sensors (Basel, Switzerland)·2024

Same author

ADFireNet: An Anchor-Free Smoke and Fire Detection Network Based on Deformable Convolution.

Sensors (Basel, Switzerland)·2023

Same author

A Local and Non-Local Features Based Feedback Network on Super-Resolution.

Sensors (Basel, Switzerland)·2022

Same author

MASPC_Transform: A Plant Point Cloud Segmentation Network Based on Multi-Head Attention Separation and Position Code.

Sensors (Basel, Switzerland)·2022

Same author

A Single Stage and Single View 3D Point Cloud Reconstruction Network Based on DetNet.

Sensors (Basel, Switzerland)·2022

This study introduces PlantEFRSegnet, a novel network for segmenting 3D plant point clouds. It improves accuracy in plant organ segmentation for phenotype analysis by preserving edge details and repairing features.

Area of Science:

Computer Vision
Plant Science
Computational Biology

Background:

Accurate segmentation of 3D plant point clouds is crucial for monitoring plant growth and phenotype analysis.
Plant point cloud segmentation presents unique challenges due to the complex, interwoven structures of plant organs like stems, leaves, and flowers.

Purpose of the Study:

To propose a universal point cloud segmentation network, PlantEFRSegnet, capable of segmenting multi-species plants.
To enhance the accuracy of plant organ segmentation by addressing challenges posed by complex plant structures.

Main Methods:

Developed PlantEFRSegnet, a novel network featuring an edge point preservation downsampling module to retain organ contour information.
Implemented supervised feature repair to mitigate feature loss during downsampling and enhance point cloud features.

Keywords:

plant phenotyping plant point cloud point cloud downsampling point cloud segmentation

Related Experiment Videos

Last Updated: May 28, 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

Utilized a four-module encoder with local feature extraction and a point attention mechanism to enhance salient point features.

Main Results:

PlantEFRSegnet demonstrated superior segmentation performance on a laser-scanned plant point cloud dataset compared to existing state-of-the-art methods.
The edge point preservation and feature repair mechanisms effectively improved the identification of plant organ boundaries.
The network achieved enhanced feature representation through local feature extraction and attention mechanisms.

Conclusions:

PlantEFRSegnet offers a robust and accurate solution for 3D plant point cloud segmentation across multiple species.
The proposed methods for downsampling and feature enhancement significantly advance the capabilities of plant phenotype analysis.
This work provides a valuable tool for researchers in plant science and computer vision seeking precise plant organ segmentation.