TNeXt：用于远程港口分类的卷积神经网络

IF 5.9 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

Ain Shams Engineering Journal Pub Date : 2025-06-23 DOI:10.1016/j.asej.2025.103545

Mert Gurturk , Sengul Dogan , Turker Tuncer

{"title":"TNeXt：用于远程港口分类的卷积神经网络","authors":"Mert Gurturk , Sengul Dogan , Turker Tuncer","doi":"10.1016/j.asej.2025.103545","DOIUrl":null,"url":null,"abstract":"<div><div>Harbor recognition from aerial images faces two main challenges: deep models are often too large for real-time use on drones, and there is no large, diverse harbor dataset to train them. This work overcomes these obstacles in two ways.</div><div>We built the Turkish Harbor Image Dataset (THID) by flying a UAV over 207 harbors in Türkiye and capturing 13,199 clear-weather images. We split THID into 73.4 % training, 18.3 % validation, and 8.3 % test sets, and applied simple augmentations (rotations, flips) to improve robustness.</div><div>TNeXt, a fully convolutional network is proposed in this research. On THID, TNeXt achieved 97.71 % accuracy. Without changing its architecture, it scored 83.30 % top-1 on ImageNet1k. For the UC-Merced Land Use dataset, TNeXt reached 97.14 % accuracy; when used as a feature extractor in a simple pipeline, it hit 99.76 %.</div><div>This research provides high accuracy and rapid inference and is therefore suitable for real-time harbor detection for autonomous platforms.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 10","pages":"Article 103545"},"PeriodicalIF":5.9000,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"TNeXt: A convolutional neural network for remote harbor classification\",\"authors\":\"Mert Gurturk , Sengul Dogan , Turker Tuncer\",\"doi\":\"10.1016/j.asej.2025.103545\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Harbor recognition from aerial images faces two main challenges: deep models are often too large for real-time use on drones, and there is no large, diverse harbor dataset to train them. This work overcomes these obstacles in two ways.</div><div>We built the Turkish Harbor Image Dataset (THID) by flying a UAV over 207 harbors in Türkiye and capturing 13,199 clear-weather images. We split THID into 73.4 % training, 18.3 % validation, and 8.3 % test sets, and applied simple augmentations (rotations, flips) to improve robustness.</div><div>TNeXt, a fully convolutional network is proposed in this research. On THID, TNeXt achieved 97.71 % accuracy. Without changing its architecture, it scored 83.30 % top-1 on ImageNet1k. For the UC-Merced Land Use dataset, TNeXt reached 97.14 % accuracy; when used as a feature extractor in a simple pipeline, it hit 99.76 %.</div><div>This research provides high accuracy and rapid inference and is therefore suitable for real-time harbor detection for autonomous platforms.</div></div>\",\"PeriodicalId\":48648,\"journal\":{\"name\":\"Ain Shams Engineering Journal\",\"volume\":\"16 10\",\"pages\":\"Article 103545\"},\"PeriodicalIF\":5.9000,\"publicationDate\":\"2025-06-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Ain Shams Engineering Journal\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2090447925002862\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ain Shams Engineering Journal","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2090447925002862","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}

引用次数: 0

摘要

从航空图像中识别港口面临两个主要挑战：深度模型通常太大，无法在无人机上实时使用，而且没有大型、多样化的港口数据集来训练它们。这项工作从两个方面克服了这些障碍。我们通过在土耳其的207个港口上空飞行一架无人机，并捕获了13199张晴朗天气的图像，建立了土耳其港口图像数据集（THID）。我们将THID分成73.4%的训练集、18.3%的验证集和8.3%的测试集，并应用简单的增强（旋转、翻转）来提高鲁棒性。本文提出了一种全卷积网络TNeXt。在THID上，TNeXt的准确率达到97.71%。在不改变其架构的情况下，它在ImageNet1k上获得了83.30%的前1分。对于UC-Merced土地利用数据集，TNeXt的准确率达到97.14%；当在简单的管道中用作特征提取器时，它达到了99.76%。该研究提供了高精度和快速的推理，因此适用于自主平台的实时港口检测。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

TNeXt: A convolutional neural network for remote harbor classification

Harbor recognition from aerial images faces two main challenges: deep models are often too large for real-time use on drones, and there is no large, diverse harbor dataset to train them. This work overcomes these obstacles in two ways.

We built the Turkish Harbor Image Dataset (THID) by flying a UAV over 207 harbors in Türkiye and capturing 13,199 clear-weather images. We split THID into 73.4 % training, 18.3 % validation, and 8.3 % test sets, and applied simple augmentations (rotations, flips) to improve robustness.

TNeXt, a fully convolutional network is proposed in this research. On THID, TNeXt achieved 97.71 % accuracy. Without changing its architecture, it scored 83.30 % top-1 on ImageNet1k. For the UC-Merced Land Use dataset, TNeXt reached 97.14 % accuracy; when used as a feature extractor in a simple pipeline, it hit 99.76 %.

This research provides high accuracy and rapid inference and is therefore suitable for real-time harbor detection for autonomous platforms.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Ain Shams Engineering Journal Engineering-General Engineering

CiteScore

10.80

自引率

13.30%

发文量

441

审稿时长

49 weeks

期刊介绍： in Shams Engineering Journal is an international journal devoted to publication of peer reviewed original high-quality research papers and review papers in both traditional topics and those of emerging science and technology. Areas of both theoretical and fundamental interest as well as those concerning industrial applications, emerging instrumental techniques and those which have some practical application to an aspect of human endeavor, such as the preservation of the environment, health, waste disposal are welcome. The overall focus is on original and rigorous scientific research results which have generic significance. Ain Shams Engineering Journal focuses upon aspects of mechanical engineering, electrical engineering, civil engineering, chemical engineering, petroleum engineering, environmental engineering, architectural and urban planning engineering. Papers in which knowledge from other disciplines is integrated with engineering are especially welcome like nanotechnology, material sciences, and computational methods as well as applied basic sciences: engineering mathematics, physics and chemistry.