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

Design Example: Alignment of a Road Line Using GIS

Design Example: Alignment of a Road Line Using GIS

The alignment of a road line using Geographic Information Systems (GIS) is a critical process in civil engineering, combining advanced technology with practical decision-making. This methodology begins with the collection of geospatial data, including information on land cover, geomorphology, drainage patterns, slope, and contour details. Such data is typically acquired through satellite imagery and GIS tools, offering a comprehensive understanding of the terrain.Once the data is gathered, it...

You might also read

Related Articles

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

Sort by

Same author

A Novel DS-MADDPG Algorithm-Based Swarm-to-Swarm Interception Strategy.

IEEE transactions on neural networks and learning systems·2026

Same author

Spatiotemporal heterogeneity of recurrence and predictors after radical surgery for pancreatic ductal adenocarcinoma: a retrospective observational study.

Surgical endoscopy·2026

Same author

Randomised, triple-blind, placebo-controlled trial of atosiban in women with previous embryo implantation failure and abnormal uterine contractions undergoing single blastocyst-stage embryo transfer: a study protocol.

BMJ open·2026

Same author

Microinjection molded PLA/ZnO-TiO<sub>2</sub> composites with <i>in situ</i> fibrillation: achieving mechanical matching cortical bone and enhanced osteoinduction.

RSC advances·2026

Same author

Learning curve of laparoscopic duodenum-preserving total pancreatic head resection: a single-center dual CUSUM and risk-adjusted CUSUM analysis.

Surgical endoscopy·2026

Same author

A web-based self-assessment tool for root caries in older adults: development, validation, and transformation of the Root-caries Assessment Nomogram (RAN).

BMC geriatrics·2026

Search research articles

Related Experiment Video

Updated: Jan 18, 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

A Rapid Segmentation Method Based on Few-Shot Learning: A Case Study on Roadways.

He Cai¹, Jiangchuan Chen¹, Yunfei Yin¹

¹School of Transportation Science and Engineering, Harbin Institute of Technology, Nangang District, Harbin 150006, China.

Sensors (Basel, Switzerland)

|September 13, 2025

Summary

This study introduces a novel few-shot learning algorithm for efficient road segmentation. It achieves high accuracy with minimal data, enabling cost-effective edge deployment for road imagery analysis.

Keywords:

back-projection few-shot learning road segmentation unmanned aerial vehicles

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Related Experiment Videos

Last Updated: Jan 18, 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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Area of Science:

Computer Vision
Machine Learning
Artificial Intelligence

Background:

Deep learning models offer accurate image segmentation but are computationally expensive.
High costs of training and deployment hinder the widespread application of segmentation models.
Efficient road segmentation is crucial for various applications, including autonomous driving and infrastructure monitoring.

Purpose of the Study:

To develop a novel road segmentation algorithm that reduces deployment costs and resource intensity.
To enable efficient application of segmentation models for road imagery using few-shot learning.
To facilitate rapid segmentation across diverse scenarios with minimal sample requirements.

Main Methods:

Introduced a few-shot learning-based road segmentation algorithm comprising a back-projection module (BPM) and a segmentation module (SM).
Proposed a learning mechanism that utilizes both positive and negative samples to capture environmental and object color features.
Designed a workflow enabling rapid segmentation across different scenarios without transfer learning and with minimal prompts.

Main Results:

Achieved high intersection over union (IoU) segmentation accuracies: 94.9%, 92.7%, 94.9%, and 94.7% across various scenarios.
Demonstrated precise segmentation with significantly fewer local road image prompts compared to state-of-the-art methods.
Validated the algorithm's efficiency for edge deployment.

Conclusions:

The proposed few-shot learning algorithm significantly reduces the cost and resource requirements for road segmentation.
The algorithm offers a practical solution for deploying accurate road segmentation models in real-world applications.
This approach enables efficient and precise road image segmentation even with limited data, paving the way for broader adoption in edge computing environments.