Deep learning has received a growing interest in recent years for detecting different types of pavement distresses and automating pavement condition assessment.A proper choice of deep learning models is key for succes...Deep learning has received a growing interest in recent years for detecting different types of pavement distresses and automating pavement condition assessment.A proper choice of deep learning models is key for successful pavement assessment applications.In this study,we first present a comprehensive experimental comparison of state-of-the-art image classification models to evaluate their performances on 11 pavement objects classification.Our experiments are conducted in different dimensions of comparison,including deep classifier architecture,effects of network depth,and computational costs.Five convolutional neural network(CNN)classifiers widely used in transportation applications,including VGG16,VGG19,ResNet50,DenseNet121,and a generic CNN(as the control model),are tested with a comprehensive pixel-level annotated dataset for 11 different distress and non-distress classes(UCF-PAVE 2017).In addition,we investigate a simple yet effective approach of encoding contextual information with multi-scale input tiles to classify highly random pavement objects in size,shape,intensity,texture,and direction.Our comparison results show that the multi-scale approach significantly improves the classification accuracy for all compared deep classifiers at a negligible extra computational cost.Finally,we provide recommendations of how to improve the classification performance of deep CNNs for automated pavement condition assessment based on the comparison results.展开更多
Based on the initiative of ＂One Belt and One Road＂ and the demand analysis of the international shipping market for high-quality maritime talents with good skills of communicating ability and international vision, t...Based on the initiative of ＂One Belt and One Road＂ and the demand analysis of the international shipping market for high-quality maritime talents with good skills of communicating ability and international vision, this paper analyzes the feasibility, necessity, construction goal, construction principle, construction content, tutorial setting, tutorial structure and tutorial demonstration and explore how＂ to make China maritime universities＇ have ability to train the international students in an efficient and orderly manner; by investigating the relevant enterprises and institutions, and presents a plan for the construction of ＂One Hundred Courses, One Thousand Class-Hours＂.展开更多
基金supported by Data Transfer Solutions,a company located in Orlando,Florida,U.S.A.Korea Institute of Civil Engineering and Building Technology(KICT)。
文摘Deep learning has received a growing interest in recent years for detecting different types of pavement distresses and automating pavement condition assessment.A proper choice of deep learning models is key for successful pavement assessment applications.In this study,we first present a comprehensive experimental comparison of state-of-the-art image classification models to evaluate their performances on 11 pavement objects classification.Our experiments are conducted in different dimensions of comparison,including deep classifier architecture,effects of network depth,and computational costs.Five convolutional neural network(CNN)classifiers widely used in transportation applications,including VGG16,VGG19,ResNet50,DenseNet121,and a generic CNN(as the control model),are tested with a comprehensive pixel-level annotated dataset for 11 different distress and non-distress classes(UCF-PAVE 2017).In addition,we investigate a simple yet effective approach of encoding contextual information with multi-scale input tiles to classify highly random pavement objects in size,shape,intensity,texture,and direction.Our comparison results show that the multi-scale approach significantly improves the classification accuracy for all compared deep classifiers at a negligible extra computational cost.Finally,we provide recommendations of how to improve the classification performance of deep CNNs for automated pavement condition assessment based on the comparison results.
文摘Based on the initiative of ＂One Belt and One Road＂ and the demand analysis of the international shipping market for high-quality maritime talents with good skills of communicating ability and international vision, this paper analyzes the feasibility, necessity, construction goal, construction principle, construction content, tutorial setting, tutorial structure and tutorial demonstration and explore how＂ to make China maritime universities＇ have ability to train the international students in an efficient and orderly manner; by investigating the relevant enterprises and institutions, and presents a plan for the construction of ＂One Hundred Courses, One Thousand Class-Hours＂.
