Zhongze Tang

Mr. Zhongze Tang

Chang'an University, School of Highway, Xi’an, Shaanxi, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 May 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
CZChi Zhang
Chi Zhang
ZTZhongze Tang
Zhongze Tang
MZMin Zhang
Min Zhang
Bo WangBo Wang
Bo Wang
Lei HouLei Hou
Lei Hou
Due to the widespread use of unmanned aerial vehicles (UAVs) in remote sensing, there are fully developed techniques for extracting vehicle speed and trajectory data from aerial video, using either a traditional method based on optical features or a deep learning method; however, there are few papers that discuss how to solve the issue of video shaking, and existing vehicle data are rarely linked to lane lines. To address the deficiencies in current research, in this study, we formulated a more reliable method for real traffic data acquisition that outperforms the traditional methods in terms of data accuracy and integrity. First, this method implements the scale-invariant feature transform (SIFT) algorithm to detect, describe, and match local features acquired from high-altitude fixed-point aerial photographs. Second, it applies “you only look once” version 5 (YOLOv5) and deep simple online and real-time tracking (DeepSORT) to detect and track moving vehicles. Next, it leverages the developed Python program to acquire data on vehicle speed and distance (to the marked reference line). The results show that this method achieved over 95% accuracy in speed detection and less than 20 cm tolerance in vehicle trajectory mapping. This method also addresses common problems involving the lack of quality aerial photographic data and accuracy in lane line recognition. Finally, this approach can be used to establish a Frenet coordinate system, which can further decipher driving behaviors and road traffic safety.

1 September 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YZYiyang Zhai
Yiyang Zhai
CZChi Zhang
Chi Zhang
Bo WangBo Wang
Bo Wang
XWXue Wang
Xue Wang
KLKai Liu
Kai Liu
ZTZhongze Tang
Zhongze Tang
Research on the standardization of interchange BIM components is required to encourage the use of BIM technology in interchange and quicken the development and improvement of relevant standards and specifications. The depth level of the model, classification, and coding of interchange BIM components, and the design and administration of the component library are the main topics of this work. First, the concept and main research content on the standardization of interchange BIM components were proposed. Second, the common forms of interchange were summarized. The basic components of interchanges include through lanes, ramps, connections, overpass bridges, and traffic safety facilities, and can be divided into 14 second-level components, such as the main line, the minor cross highway, the speed-change lane, etc. On this basis, a method for interchange BIM components classification based on faceted classification and a coding method based on a combination code was proposed. The model depth grading of the BIM component of the interchange was studied, and grading was carried out considering three aspects: the level of detail (LOD), geometric accuracy, and information level. Finally, the process of creating interchange BIM component libraries was proposed. The results showed that the interchange BIM components can adopt a three-level coding method, namely “the overall spatial code–classification code–instance code”, and the LOD, geometric accuracy, and information level of the interchange BIM components can be divided into four levels. Additionally, interchange BIM component libraries can be created using five steps: an overall plan of component resources, standard determination, component creation, component audit, component storage, and application.