- Browse by Author
Browsing by Author "Chen, Donghui"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Development of an Automated Visibility Analysis Framework for Pavement Markings Based on the Deep Learning Approach(MDPI, 2020-11) Kang, Kyubyung; Chen, Donghui; Peng, Cheng; Koo, Dan; Kang, Taewook; Kim, Jonghoon; Computer and Information Science, School of SciencePavement markings play a critical role in reducing crashes and improving safety on public roads. As road pavements age, maintenance work for safety purposes becomes critical. However, inspecting all pavement markings at the right time is very challenging due to the lack of available human resources. This study was conducted to develop an automated condition analysis framework for pavement markings using machine learning technology. The proposed framework consists of three modules: a data processing module, a pavement marking detection module, and a visibility analysis module. The framework was validated through a case study of pavement markings training data sets in the U.S. It was found that the detection model of the framework was very precise, which means most of the identified pavement markings were correctly classified. In addition, in the proposed framework, visibility was confirmed as an important factor of driver safety and maintenance, and visibility standards for pavement markings were defined.Item Temporary Traffic Control Device Detection for Road Construction Projects Using Deep Learning Application(ASCE, 2022-03-07) Seo, Sungchul; Chen, Donghui; Kim, Kwangcheol; Kang, Kyubyung; Koo, Dan; Chae, Myungjin; Park, Hyung Keun; Mechanical and Energy Engineering, School of Engineering and TechnologyTraffic control devices in road construction zones play important roles, which (1) provide critical traffic-related information for the drivers, (2) prevent potential crashes near work zones, and (3) protect work crews’ safety. Due to the number of devices in each site, transportation agencies have faced challenges in timely and frequently inspecting traffic control devices, including temporary devices. Deep learning applications can support these inspection processes. The first step of the inspection using deep learning is recognizing traffic control devices in the work zone. This study collected road images using vehicle-mounted cameras from various illuminance and weather conditions. Then, the study (1) labeled eight classes of temporary traffic control devices (TTCDs), (2) modified and trained a machine-learning model using the YOLOv3 algorithm, and (3) tested the detection outcomes of various TTCDs. The key finding shows that the proposed model recognized more than 98% of the temporary traffic signs correctly and approximately 81% of temporary traffic control devices correctly. The construction barricade had the lowest mean Average Precision (50%) out of eight classes. The outcomes can be used as the first step of autonomous safety inspections for road construction projects.