Search for Articles
Others
-
Special Issue Engineering in General Information Sciences Others
- Yuhei Yamamoto
- Masaya Nakahara
- Ryo Sumiyoshi
- Wenyuan Jiang
- Daisuke Kamiya
- Ryuichi Imai
The turning movement count is investigated to understand the traffic conditions at intersections and identify bottleneck locations. In recent years, methods utilizing probe data and AI-based analysis of video images have been developed to streamline the survey process. Existing methods can count vehicles as they pass but struggle to classify vehicle types. Therefore, the objective of this study is to develop a method for counting turning movement count by vehicle type using deep learning. In this method, YOLOv8 is used to detect cars, buses, and trucks in video images, and BoT-SORT is used for tracking. When a vehicle being tracked crosses the cross-sectional lines and auxiliary lines at the intersection captured in the video images, it is counted by class. In this case, the entry direction of vehicles that cannot be determined upon entering the intersection is estimated based on accurately counted vehicles. Additionally, the entry direction is inferred from a series of vector information within the detection bounding boxes. The results of the verification experiment showed that the proposed method can count the directional traffic volume with an accuracy of over 95.0% and classify the three vehicle classes—car, bus, and truck—with an accuracy of over 90.0%.
-
Technical Article Information Sciences Others
3D Point Studio: Utilization Platform for Point Cloud Data
- Kenji Nakamura
- Ryuichi Imai
- Yoshinori Tsukada
- Yoshimasa Umehara
- Shigenori Tanaka
As Laser measurement technology has made remarkable progress in recent years and the means of measuring the three-dimensional shapes of road spaces as point cloud data have diversified, point cloud data has been measured and accumulated throughout Japan. Point cloud data is useful as a means of accurately grasping the present shape and is expected to be utilized for a wide range of purposes with i-Construction as a turning point. Existing efforts have promoted development of new technologies and open data, steadily increasing opportunities to use point cloud data. However, it is difficult to use point cloud data wisely in accordance with its intended purpose because it is merely a vast set of points that indicate locations in space and does not hold information about the features indicated by the points or about their relationships to other points. Therefore, it is essential to develop an environment for utilizing point cloud data. In this study, we develop 3D Point Studio, a platform for utilizing and sharing 3D data including point cloud data by utilizing area data. The usefulness of this research will be confirmed through examples of applications in the actual sites, and its future development will be discussed.