检索结果-南通市图书馆

Traffic Scene Captioning with Multi-Stage Feature Enhancement

Computers, Materials & Continua 2023年第9期76卷 2901-2920页

作者： Dehai Zhang Yu Ma Qing Liu Haoxing Wang Anquan Ren Jiashu Liang School of Software Yunnan UniversityKunming650091China

Traffic scene captioning technology automatically generates one or more sentences to describe the content of traffic scenes by analyzing the content of the input traffic scene images,ensuring road safety while providing an important decision-making function for sustainable transportation.In order to provide a comprehensive and reasonable description of complex traffic scenes,a traffic scene semantic captioningmodel withmulti-stage feature enhancement is proposed in this paper.In general,the model follows an encoder-decoder structure.First,multilevel granularity visual features are used for feature enhancement during the encoding process,which enables the model to learn more detailed content in the traffic scene image.Second,the scene knowledge graph is applied to the decoding process,and the semantic features provided by the scene knowledge graph are used to enhance the features learned by the decoder again,so that themodel can learn the attributes of objects in the traffic scene and the relationships between objects to generate more reasonable captions.This paper reports extensive experiments on the challenging MS-COCO dataset,evaluated by five standard automatic evaluation metrics,and the results show that the proposed model has improved significantly in all metrics compared with the state-of-the-art methods,especially achieving a score of 129.0 on the CIDEr-D evaluation metric,which also indicates that the proposed model can effectively provide a more reasonable and comprehensive description of the traffic scene.

关键词： Traffic scene captioning sustainable transportation feature enhancement encoder-decoder structure multi-level granularity scene knowledge graph

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A Web-based Analysis of sustainable transportation Curricula

A Web-based Analysis of Sustainable Transportation Curricula

引用

The 4th International Conference on Engineering and Business Management

作者： Yen-Chun Jim Wu Chung-Cheng Lu Taih-Cherng Lirn Chih-Hung Yuan Dept of Business Management National Sun Yat-sen University Graduate Institute of Information and Logistics Management National Taipei Uni. of Tech. Dept.of Shipping & transportation Management National Taiwan Ocean University

The purpose of this study is analyzed the public content on the websites of targeted universities to determine their commitment to educating the world about sustainable transportation. We created a list of academic organizations based on the compendium of papers from the transportation Research Board’s 2012 annual meeting. Then we analyzed the content from the public websites of these organizations to distinguish differences in the way universities in North America and Europe designed courses related to sustainable transport. After analyzing information from about 5,000 such courses, we found that most of them were worth 3 credits, more courses were offered for graduate students than for undergraduates, lecturing was the most common teaching method, the most commonly offered course was transportation Engineering, and, on average, North American universities offered more sustainable transport courses than their European counterparts. Finally, the environmental issue was emphasized and discussed far more than the economic and social issue. Our findings suggest diverse differences in sustainability-related curriculum design from transport schools of different backgrounds. This is first article try to provide a holistic picture of the current state of sustainable transport, based on an exploratory empirical study of the world’s major transport schools.

关键词： Content Analysis Curriculum sustainable transportation North America Europe

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Are shared electric scooters energy efficient?

引用

Communications in transportation Research 2021年第1期1卷 182-192页

作者： Yuxuan Wang Jiaming Wu Kequan Chen Pan Liu Jiangsu Key Laboratory of Urban ITS School of TransportationSoutheast UniversitySi Pai Lou#2Nanjing210096China Department of Architecture and Civil Engineering Chalmers University of TechnologyGothenburgSE41296Sweden

Shared electric scooters(e-scooter)are booming across the world and widely regarded as a sustainable mobility service.An increasing number of studies have investigated the e-scooter trip patterns,safety risks,and environmental impacts,but few considered the energy efficiency of e-scooters.In this research,we collected the operational data of e-scooters from a major provider in Gothenburg to shed light on the energy efficiency performance of e-scooters in real cases.We first develop a multiple logarithmic regression model to examine the energy consumption of single trips and influencing factors.With the regression model,a Monte Carlo simulation framework is proposed to estimate the fleet energy consumption in various scenarios,taking into account both trip-related energy usage and energy loss in idle status.The results indicate that 40%of e-scooter battery energy was wasted in idle status in the current practice,mainly due to the relatively low usage rate(0.83)of e-scooters.If the average usage rate drops below 0.5,the wasted energy could reach up to 53%.In the end,we present a field example to showcase how to optimally integrate public transport with e-scooters from the perspective of energy efficiency.We hope the findings of this study could help understand and resolve the current and future challenges regarding the ever-growing e-scooter services.

关键词： E-scooters Shared mobility sustainable transportation Monte Carlo simulation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：