MAVSD: A Multi-Angle View Segmentation Dataset for Detection of Solidago Canadensis L.

Abstract Recent advancements in computer vision and deep learning have advanced automated vegetation monitoring, creating new opportunities for invasive species management. To this end, we introduce MAVSD (Multi-Angle View Segmentation Dataset), specifically designed for detecting Solidago canadensi...

Full description

Saved in:
Bibliographic Details
Main Authors: Hanru Li, Tianning Fu, Hongchi Hao, Zhibin Yu
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Data
Online Access:https://doi.org/10.1038/s41597-025-05199-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849731931820785664
author Hanru Li
Tianning Fu
Hongchi Hao
Zhibin Yu
author_facet Hanru Li
Tianning Fu
Hongchi Hao
Zhibin Yu
author_sort Hanru Li
collection DOAJ
description Abstract Recent advancements in computer vision and deep learning have advanced automated vegetation monitoring, creating new opportunities for invasive species management. To this end, we introduce MAVSD (Multi-Angle View Segmentation Dataset), specifically designed for detecting Solidago canadensis L., a globally significant invasive plant. The dataset comprises high-resolution images captured by unmanned aerial vehicles from four angles (30°, 45°, 60°, and 90°), providing comprehensive coverage of plant structures and enabling in-depth understanding from multiple perspectives. MAVSD includes pixel-level semantic segmentation annotations across 13 classes, meticulously categorizing vegetation and environmental elements. Extensive experiments with state-of-the-art segmentation models validate MAVSD’s effectiveness in enhancing invasive species detection and monitoring, with multi-angle training improving mIoU by up to 11% over single-angle baselines. The dataset’s multi-angle, high-resolution characteristics strengthen ecological monitoring capabilities, offering valuable resources for research and environmental protection applications.
format Article
id doaj-art-3a7eb0ea3084494d840fa6779ef5b7ad
institution DOAJ
issn 2052-4463
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Data
spelling doaj-art-3a7eb0ea3084494d840fa6779ef5b7ad2025-08-20T03:08:22ZengNature PortfolioScientific Data2052-44632025-05-0112111510.1038/s41597-025-05199-yMAVSD: A Multi-Angle View Segmentation Dataset for Detection of Solidago Canadensis L.Hanru Li0Tianning Fu1Hongchi Hao2Zhibin Yu3College of Electronic Engineering, Ocean University of ChinaCollege of Electronic Engineering, Ocean University of ChinaCollege of Electronic Engineering, Ocean University of ChinaCollege of Electronic Engineering, Ocean University of ChinaAbstract Recent advancements in computer vision and deep learning have advanced automated vegetation monitoring, creating new opportunities for invasive species management. To this end, we introduce MAVSD (Multi-Angle View Segmentation Dataset), specifically designed for detecting Solidago canadensis L., a globally significant invasive plant. The dataset comprises high-resolution images captured by unmanned aerial vehicles from four angles (30°, 45°, 60°, and 90°), providing comprehensive coverage of plant structures and enabling in-depth understanding from multiple perspectives. MAVSD includes pixel-level semantic segmentation annotations across 13 classes, meticulously categorizing vegetation and environmental elements. Extensive experiments with state-of-the-art segmentation models validate MAVSD’s effectiveness in enhancing invasive species detection and monitoring, with multi-angle training improving mIoU by up to 11% over single-angle baselines. The dataset’s multi-angle, high-resolution characteristics strengthen ecological monitoring capabilities, offering valuable resources for research and environmental protection applications.https://doi.org/10.1038/s41597-025-05199-y
spellingShingle Hanru Li
Tianning Fu
Hongchi Hao
Zhibin Yu
MAVSD: A Multi-Angle View Segmentation Dataset for Detection of Solidago Canadensis L.
Scientific Data
title MAVSD: A Multi-Angle View Segmentation Dataset for Detection of Solidago Canadensis L.
title_full MAVSD: A Multi-Angle View Segmentation Dataset for Detection of Solidago Canadensis L.
title_fullStr MAVSD: A Multi-Angle View Segmentation Dataset for Detection of Solidago Canadensis L.
title_full_unstemmed MAVSD: A Multi-Angle View Segmentation Dataset for Detection of Solidago Canadensis L.
title_short MAVSD: A Multi-Angle View Segmentation Dataset for Detection of Solidago Canadensis L.
title_sort mavsd a multi angle view segmentation dataset for detection of solidago canadensis l
url https://doi.org/10.1038/s41597-025-05199-y
work_keys_str_mv AT hanruli mavsdamultiangleviewsegmentationdatasetfordetectionofsolidagocanadensisl
AT tianningfu mavsdamultiangleviewsegmentationdatasetfordetectionofsolidagocanadensisl
AT hongchihao mavsdamultiangleviewsegmentationdatasetfordetectionofsolidagocanadensisl
AT zhibinyu mavsdamultiangleviewsegmentationdatasetfordetectionofsolidagocanadensisl