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: Jun 27, 2026

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

Point Cloud Classification and Segmentation Network Based on Adaptive Feature Extraction.

Chengzhi Deng^1,2, Huaipei Wang², Zhaoming Wu²

¹School of Computer Science and Software, Zhaoqing University, Zhaoqing 526061, China.

Sensors (Basel, Switzerland)

|June 26, 2026

Summary

This summary is machine-generated.

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

A Functional SNP in the AMH Gene Is Associated with Litter Size in Dazu Black Goats.

Animals : an open access journal from MDPI·2026

Same author

Development and internal validation of an early postnatal nomogram for bronchopulmonary dysplasia in very preterm infants with positive respiratory tract Ureaplasma urealyticum results.

BMC pediatrics·2026

Same author

Predicting severe intraventricular hemorrhage in very preterm and/or very low birth weight infants: a nomogram approach.

Frontiers in pediatrics·2026

Same author

Mechanically Interlocked Core-Shell Architecture for Stable Nickel-Rich Cathodes.

Nano letters·2026

Same author

EphB4/EphrinB2 signaling regulates pericyte-like function of DPSCs in angiogenesis via transcriptional factor SRF.

Stem cell research & therapy·2026

Same author

Effects of acupuncture-related therapies on endocrine and metabolic outcomes in obese women with polycystic ovary syndrome: a systematic review and network meta-analysis.

Frontiers in medicine·2026

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

This study introduces AFE-PointNet, a lightweight network for 3D point cloud classification and segmentation. It enhances local feature representation and deep mining for improved accuracy and efficiency in 3D perception tasks.

Area of Science:

Computer Vision
Machine Learning
3D Data Processing

Background:

Point cloud classification and segmentation are crucial for 3D perception and scene understanding.
Existing methods struggle with local feature representation, computational efficiency, and scene applicability.
These limitations hinder high-level applications like 3D modeling and object recognition.

Purpose of the Study:

To propose a novel lightweight network, AFE-PointNet, for enhanced point cloud classification and segmentation.
To address deficiencies in local feature representation and computational efficiency in current methods.
To provide a high-precision and efficient solution for 3D vision tasks.

Main Methods:

Introduced an element-wise weighting set abstraction module using Hadamard product for adaptive feature enhancement.

Keywords:

Hadamard product adaptive feature extraction inverted residual MLP lightweight network point cloud classification point cloud segmentation

Related Experiment Videos

Last Updated: Jun 27, 2026

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

Leveraged geometric topology learning to improve local geometric structure representation.

Employed a cascaded structure of feature aggregation and inverted residual multi-layer perceptron (InvResMLP) for deep feature mining.

Main Results:

AFE-PointNet achieved 93.6% overall accuracy (OA) on ModelNet40 and 84.5% on ScanObjectNN.
Attained a class mean intersection over union (Cls.mIoU) of 83.6% on ShapeNetPart.
Demonstrated significant performance improvements compared to the PointNet++ model.

Conclusions:

The proposed adaptive feature enhancement and lightweight deep mining strategies significantly improve point cloud representation.
AFE-PointNet offers a high-precision and efficient solution for 3D vision tasks.
The network effectively addresses limitations in local feature representation and computational efficiency.