• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

一个用于检测内陆水域漂浮垃圾的带注释数据集和基准。

An annotated Dataset and Benchmark for Detecting Floating Debris in Inland Waters.

作者信息

Qiao Guangchao, Yang Mingxiang, Wang Hao

机构信息

China Institute of Water Resources and Hydropower Research, Beijing, China.

State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, Beijing, China.

出版信息

Sci Data. 2025 Mar 5;12(1):385. doi: 10.1038/s41597-025-04594-9.

DOI:10.1038/s41597-025-04594-9
PMID:40044696
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11882902/
Abstract

Marine litter is a serious threat to marine ecosystems, and the timely removal of floating waste from inland waters is effective in preventing floating debris from entering the sea. An accurate object detection system is a prerequisite for efficiently clearing floaters. However, complex light conditions in the water, small size objects and other factors pose a huge challenge for floating object detection. In order to facilitate the solution of the floating object pollution problem and promote the application of AI technology in the water industry, we proposed the first floater dataset of waters collected from real water scenarios based on shore-based filming equipment, IWHR_AI_Lable_Floater_V1. The dataset consists of 3000 images containing accurate annotation information to support vision-based water surface floater detection tasks. We conducted a number of baseline experiments to evaluate the performance of mainstream object detection algorithms on this dataset. The results show that the detection accuracies of the models, including the state-of-the-art model YOLOv9, are all low, which also indicates that floating object detection is a challenging task.

摘要

海洋垃圾对海洋生态系统构成严重威胁,及时清除内陆水域的漂浮垃圾对于防止漂浮碎片进入海洋十分有效。精确的目标检测系统是高效清除漂浮物的前提条件。然而,水中复杂的光照条件、小尺寸物体等因素给漂浮物检测带来了巨大挑战。为便于解决漂浮物污染问题并推动人工智能技术在水行业的应用,我们基于岸基拍摄设备提出了首个从真实水域场景采集的水域漂浮物数据集——IWHR_AI_Lable_Floater_V1。该数据集由3000张包含精确标注信息的图像组成,以支持基于视觉的水面漂浮物检测任务。我们进行了多项基线实验,以评估主流目标检测算法在该数据集上的性能。结果表明,包括最先进的模型YOLOv9在内的模型检测准确率都很低,这也表明漂浮物检测是一项具有挑战性的任务。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22dc/11882902/7ee1619dc71c/41597_2025_4594_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22dc/11882902/e9041b885e33/41597_2025_4594_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22dc/11882902/32f8950aace9/41597_2025_4594_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22dc/11882902/a51482976e99/41597_2025_4594_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22dc/11882902/f01aad3fbf25/41597_2025_4594_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22dc/11882902/73fa5c4d66b5/41597_2025_4594_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22dc/11882902/ae9593eb1a33/41597_2025_4594_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22dc/11882902/2446e358ab2a/41597_2025_4594_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22dc/11882902/f7400709c262/41597_2025_4594_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22dc/11882902/7ee1619dc71c/41597_2025_4594_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22dc/11882902/e9041b885e33/41597_2025_4594_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22dc/11882902/32f8950aace9/41597_2025_4594_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22dc/11882902/a51482976e99/41597_2025_4594_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22dc/11882902/f01aad3fbf25/41597_2025_4594_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22dc/11882902/73fa5c4d66b5/41597_2025_4594_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22dc/11882902/ae9593eb1a33/41597_2025_4594_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22dc/11882902/2446e358ab2a/41597_2025_4594_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22dc/11882902/f7400709c262/41597_2025_4594_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/22dc/11882902/7ee1619dc71c/41597_2025_4594_Fig9_HTML.jpg

相似文献

1
An annotated Dataset and Benchmark for Detecting Floating Debris in Inland Waters.一个用于检测内陆水域漂浮垃圾的带注释数据集和基准。
Sci Data. 2025 Mar 5;12(1):385. doi: 10.1038/s41597-025-04594-9.
2
A Dataset for Detection and Segmentation of Underwater Marine Debris in Shallow Waters.一个用于浅水区水下海洋垃圾检测与分割的数据集。
Sci Data. 2024 Aug 24;11(1):921. doi: 10.1038/s41597-024-03759-2.
3
An Image-Based Benchmark Dataset and a Novel Object Detector for Water Surface Object Detection.用于水面目标检测的基于图像的基准数据集及新型目标检测器
Front Neurorobot. 2021 Sep 24;15:723336. doi: 10.3389/fnbot.2021.723336. eCollection 2021.
4
Synthetic polymers in the marine environment: a rapidly increasing, long-term threat.海洋环境中的合成聚合物:一种迅速增加的长期威胁。
Environ Res. 2008 Oct;108(2):131-9. doi: 10.1016/j.envres.2008.07.025.
5
MAR-YOLOv9: A multi-dataset object detection method for agricultural fields based on YOLOv9.MAR-YOLOv9:一种基于 YOLOv9 的农业领域多数据集目标检测方法。
PLoS One. 2024 Oct 29;19(10):e0307643. doi: 10.1371/journal.pone.0307643. eCollection 2024.
6
Abundance and composition of floating marine macro litter on the eastern sector of the Mediterranean Sea.地中海东部海域漂浮海洋大型垃圾的丰度和组成。
Mar Pollut Bull. 2019 Jan;138:260-265. doi: 10.1016/j.marpolbul.2018.11.008. Epub 2018 Nov 26.
7
Development of automated marine floating plastic detection system using Sentinel-2 imagery and machine learning models.利用哨兵 - 2 影像和机器学习模型开发自动化海洋漂浮塑料检测系统
Mar Pollut Bull. 2022 May;178:113527. doi: 10.1016/j.marpolbul.2022.113527. Epub 2022 Apr 2.
8
First observations on the abundance and composition of floating debris in the North-western Black Sea.对黑海西北部漂浮垃圾的丰度和组成的初步观察
Mar Environ Res. 2015 Jun;107:45-49. doi: 10.1016/j.marenvres.2015.03.011. Epub 2015 Apr 2.
9
Identity-Preserved Human Posture Detection in Infrared Thermal Images: A Benchmark.身份保留的人体红外热图像姿态检测:基准
Sensors (Basel). 2022 Dec 22;23(1):92. doi: 10.3390/s23010092.
10
MARIDA: A benchmark for Marine Debris detection from Sentinel-2 remote sensing data.MARIDA:利用 Sentinel-2 遥感数据进行海洋垃圾检测的基准
PLoS One. 2022 Jan 7;17(1):e0262247. doi: 10.1371/journal.pone.0262247. eCollection 2022.

本文引用的文献

1
An Image-Based Benchmark Dataset and a Novel Object Detector for Water Surface Object Detection.用于水面目标检测的基于图像的基准数据集及新型目标检测器
Front Neurorobot. 2021 Sep 24;15:723336. doi: 10.3389/fnbot.2021.723336. eCollection 2021.
2
Ridding our rivers of plastic: A framework for plastic pollution capture device selection.清除河流中的塑料:塑料污染捕获装置选择框架。
Mar Pollut Bull. 2021 Apr;165:112095. doi: 10.1016/j.marpolbul.2021.112095. Epub 2021 Feb 6.
3
Using citizen science to investigate the spatial-temporal distribution of floating marine litter in the waters around Taiwan.
利用公民科学调查台湾周边海域漂浮海洋垃圾的时空分布。
Mar Pollut Bull. 2020 Aug;157:111301. doi: 10.1016/j.marpolbul.2020.111301. Epub 2020 May 29.
4
Focal Loss for Dense Object Detection.用于密集目标检测的焦散损失
IEEE Trans Pattern Anal Mach Intell. 2020 Feb;42(2):318-327. doi: 10.1109/TPAMI.2018.2858826. Epub 2018 Jul 23.
5
Underwater Image Enhancement by Dehazing With Minimum Information Loss and Histogram Distribution Prior.基于最小信息损失和直方图分布先验的去雾水下图像增强
IEEE Trans Image Process. 2016 Dec;25(12):5664-5677. doi: 10.1109/TIP.2016.2612882. Epub 2016 Sep 22.
6
Plastic waste in the marine environment: A review of sources, occurrence and effects.海洋环境中的塑料垃圾:来源、存在和影响综述。
Sci Total Environ. 2016 Oct 1;566-567:333-349. doi: 10.1016/j.scitotenv.2016.05.084. Epub 2016 May 24.