Creating a Dataset to Boost Civil Engineering Deep Learning Research and Application

Abstract

With cutting edge deep learning breakthrough, numerous innovations in many fields including civil engineering are stimulated. However, a fundamental issue that civil engineering research community currently facing is lack of a publicly available, free, quality-controlled and human-annotated large dataset that supports and drives civil engineering deep learning research and applications on such as intelligent transportation including connected vehicle, structural health monitoring, and bridge inspection. This paper is a general discussion about demanding needs and construction of a long-anticipated dataset for researchers and engineers in civil engineering and beyond for providing critical training, testing and benchmarking data. The establishment of such a free dataset will remove a major hurdle and boost deep learning research in civil engineering and we hope this work will urge researchers, engineers, government agencies and even computer scientists to work together to start building such datasets. A framework has been developed for the proposed database. Also, some pilot study databases were developed for concrete crack detection, pavement crack detection using normal and infrared thermography, as well as pedestrian and bicyclist detection. A convolution neural network model called Faster RCNN was deployed to check the detection accuracy and a 98% detection accuracy of the proposed datasets was obtained.

Exploiting Data Analytics and Deep Learning Systems to Support Pavement Maintenance Decisions

“…However, in many instances, many large databases do not provide particularly useful information to allow for efficient decisions to be made with many of the databases having subjective data [37]. There have been attempts at creating datasets that will help boost deep learning activities in the field of civil engineering where datasets of different infrastructures have been set up [38]. However, these studies have tended to focus on image-based datasets.…”

Bridge Girder Crack Assessment Using Faster RCNN Inception V2 and Infrared Thermography

“…A short tutorial was made for the demonstration of data acquisition in this YouTube video link (https://www.youtube.com/watch?v=q4ZDH7MDh9E). A total of 2088 images of crack and not-crack were collected [37]. All the images were split into two groups of images: one for training and the other for testing or validation purpose.…”

Promoting Educational Reform to Enhance Talent Cultivation Quality of Civil Engineering Majors Based on Deep Learning Background

“…After more than ten years of rapid development, the current problem is industrial adjustment [1][2][3], and the development of the industry will always have an impact on the corresponding development of education. Therefore, the training of construction-related professionals is also facing the new normal [4][5]. With the rapid development of the construction industry for more than ten years, the enrollment scale of civil engineering majors in higher vocational colleges and universities has also developed rapidly for more than ten years [6][7].…”