Article
Computer Science, Information Systems
Asfak Ali, Ram Sarkar, Debesh Kumar Das
Summary: One of the challenging tasks in computer vision is the classification and detection of vehicles. Researchers worldwide are working on autonomous vehicle detection systems, which have various practical applications. The current trend in AVD is deep learning techniques, although many Indian vehicles are not included in the existing detection datasets. In this research, a dataset for still-image-based vehicle detection is presented, including one class of pedestrians and 13 different types of vehicles commonly seen on Indian roads. A baseline result is provided using state-of-the-art deep learning models, and an ensemble-based object detection and classification model is proposed to further improve accuracy. The dataset consists of 4K images and 14.3K bounding boxes, providing researchers with annotated rectangular boxes for future use.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Sky H. Lee, Henzeh Leeghim
Summary: This study addresses the generation of synthetic infrared (IR) images using CycleGAN based on the structural similarity index measure (SSIM). The analysis focuses on how the window sizes and weight parameters of SSIM would affect the synthetic IR images constructed by CycleGAN. A metric to evaluate the similarities between the synthetic IR images generated by CycleGAN and real images is also considered. The power spectrum analysis and t-SNE analysis are conducted as measures of image similarity.
Article
Computer Science, Artificial Intelligence
Jahongir Azimjonov, Ahmet Ozmen
Summary: This study proposed a method to improve the vehicle classification accuracy of Yolo and developed a bounding box-based vehicle tracking algorithm. By preprocessing highway video images and training classifiers, the classification accuracy of the Yolo-based vehicle detector was increased from 57% to 95.45%. In the vehicle counting task, the accuracy of this developed method was improved by 13.25% and outperformed other vehicle counting systems.
ADVANCED ENGINEERING INFORMATICS
(2021)
Article
Chemistry, Analytical
Adrian-Tiberiu Costin, Daniel Zinca, Virgil Dobrota
Summary: Logging network traffic enables proactive analysis and troubleshooting, providing access to and examination of exchanged information. Innovative technologies like real-time querying and pattern matching integration are crucial for enhancing network traffic analysis. This research introduces an innovative network traffic logging tool that focuses on real-time packet transfer to Apache Kafka and ksqlDB, ensuring swift and reliable storage. By showcasing this solution, the paper demonstrates the benefits of utilizing modern technologies for network traffic analysis and management.
Article
Chemistry, Analytical
Michal Hodon, Ondrej Karpis, Peter Sevcik, Andrea Kocianova
Summary: This study compares the suitability of available sensors for road traffic surveillance, focusing on factors such as efficiency and price of magnetometers. The results are summarized by scoring each sensor, providing the audience with information about the pros and cons of sensors. The study specifically looks at the use of magnetometers for road traffic monitoring placed at the roadside.
Article
Chemistry, Analytical
Laura Leja, Vitalijs Purlans, Rihards Novickis, Andrejs Cvetkovs, Kaspars Ozols
Summary: This paper presents a mathematical model and synthetic data generation framework for uncooled infrared (IR) sensors, which addresses the challenge of improving the capabilities of IR sensors through efficient data pre-processing algorithms.
Article
Computer Science, Artificial Intelligence
Oscar Esneider Acosta Agudelo, Carlos Enrique Montenegro Marin, Ruben Gonzalez Crespo
Summary: The increase in population density in large cities has led to an increase in environmental noise, with road traffic noise being the most prevalent source. It is necessary to have tools to characterize noise and establish strategies to ensure quality of life. The research discusses the implementation of a system to acquire data on road traffic noise and presents methodology for acoustic indicators and vehicular traffic classification. Results show slight differences between sound level meters and measurement microphones, and an error range in vehicle classification and counting.
Article
Engineering, Electrical & Electronic
G. S. R. Satyanarayana, Sudhan Majhi, Santos Kumar Das
Summary: This article presents a method for detecting vehicles in heterogeneous and lane-less traffic using a binary image, demonstrated with virtual loops and a micro-LiDAR array. The proposed method can be implemented with minimal cost, storage, and bandwidth, and achieved a high detection accuracy in real traffic scenarios.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Green & Sustainable Science & Technology
Dorde Vranjes, Bojan Maric, Tihomir Duric, Goran Jovanov, Jovica Vasiljevic, Nemanja Jovanov, Dunja Radovic Stojcic
Summary: This study analyzes the impact of the total number of technical inspection centers for motor vehicles on accidents and their consequences. The results show that in the selected area, the total number of inspections accounts for a larger portion of the accidents caused by technical malfunctions. Furthermore, an increase in the number of inspections relative to the number of registered vehicles does not have a positive impact on the increase in accidents and their consequences, and the number of centers and registered vehicles have different influences on the occurrence of accidents and their consequences.
Article
Engineering, Civil
Yaochen Li, Haochuan Hou, Zikun Dong, Yujie Zang, Ying Zhang, Yonghong Song
Summary: This paper proposes a new framework for spatiotemporal analysis of static and dynamic traffic elements from road scenes. It applies a hierarchical approach combined with hidden conditional random fields (HCRF) to analyze the static traffic elements, and a lightweight multi-stream 3DCNN network for the behavior classification of dynamic traffic elements. Experimental results demonstrate the effectiveness of the proposed framework.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Young-Kook Park, Hyunhee Park, Young-Su Woo, In-Gu Choi, Seung-Soo Han
Summary: This study proposes a system framework for updating map data by mapping objects detected by a road map detection system with objects in a high-definition map. By real-time detection and verification of object locations, the accuracy of map data is improved.
Article
Neurosciences
Zhengchen Cai, Makoto Uji, Umit Aydin, Giovanni Pellegrino, Amanda Spilkin, Edouard Delaire, Chifaou Abdallah, Jean-Marc Lina, Christophe Grova
Summary: In this study, a personalized NIROT workflow using fNIRS for spatiotemporal imaging of cortical hemodynamic fluctuations was proposed and evaluated. The MEM framework showed better spatial accuracy compared to the MNE method, while both methods exhibited similar temporal accuracy in reconstructing concentration changes of HbO and HbR. The complete workflow was made available for further application in the brainstorm fNIRS processing plugin-NIRSTORM.
HUMAN BRAIN MAPPING
(2021)
Correction
Computer Science, Artificial Intelligence
Oscar Esneider Acosta Agudelo, Carlos Enrique Montenegro Marin, Ruben Gonzalez Crespo
Summary: A correction to the paper has been published.
Article
Computer Science, Information Systems
Usman Ahmed, Jerry Chun-Wei Lin, Gautam Srivastava
Summary: Consumer demand for automobiles is changing, with a focus on dependability, utility, design, and comfort. This research focuses on creating and implementing a deep learning-based traffic analysis system that can recognize, categorize, and count vehicles in real-time traffic flow using video feeds and vehicle information.
Article
Construction & Building Technology
Zheda Zhu, Spencer E. Quiel, Clay J. Naito
Summary: This paper numerically investigates the thermal impact of vehicle fire hazards on exposed electrical conduits in roadway tunnels. The analysis results provide performance-based design guidance for allowable temperature increases before the conduit and its contents fail. Sensitivity analyses are performed to examine the influence of various factors on the results.
TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY
(2022)
Article
Environmental Studies
Lambros K. Mitropoulos, Panos D. Prevedouros
TRANSPORTATION RESEARCH PART D-TRANSPORT AND ENVIRONMENT
(2015)
Article
Engineering, Civil
Lambros K. Mitropoulos, Panos D. Prevedouros
JOURNAL OF URBAN PLANNING AND DEVELOPMENT
(2016)
Article
Transportation Science & Technology
Lambros K. Mitropoulos, Panos D. Prevedouros
TRANSPORTATION PLANNING AND TECHNOLOGY
(2016)
Article
Engineering, Civil
Lambros K. Mitropoulos, Panos D. Prevedouros
JOURNAL OF URBAN PLANNING AND DEVELOPMENT
(2016)
Article
Engineering, Civil
Xin Alyx Yu, Panos D. Prevedouros
JOURNAL OF TRANSPORTATION ENGINEERING
(2013)
Article
Engineering, Civil
Lambros K. Mitropoulos, Panos D. Prevedouros
TRANSPORTATION RESEARCH RECORD
(2013)
Article
Engineering, Civil
L. K. Mitropoulos, P. D. Prevedouros
TRANSPORTATION RESEARCH RECORD
(2014)
Article
Transportation
Lin Zhang, Panos D. Prevedouros
Article
Engineering, Civil
Xi Zhuo, Panos D. Prevedouros, Yongqiang Zhang, Changtai Lu, Yuxin Xiao, Weifan Zheng
Summary: The superblock has become a common land use in China and other Asian cities, but the access points cause traffic congestion and conflicts. To improve the design, detailed access point models were developed, considering various conflicts and safety indexes. A case study showed that the updated design reduced crash risk.
JOURNAL OF ADVANCED TRANSPORTATION
(2022)
Proceedings Paper
Transportation
Lambros K. Mitropoulos, Panos D. Prevedouros, Pantelis Kopelias
3RD CONFERENCE ON SUSTAINABLE URBAN MOBILITY (3RD CSUM 2016)
(2017)
Proceedings Paper
Transportation
Lambros K. Mitropoulos, Panos D. Prevedouros, Xin (Alyx) Yu, Eftihia G. Nathanail
3RD CONFERENCE ON SUSTAINABLE URBAN MOBILITY (3RD CSUM 2016)
(2017)
Proceedings Paper
Transportation
Liang Shi, Panos D. Prevedouros
INTERNATIONAL SYMPOSIUM ON ENHANCING HIGHWAY PERFORMANCE (ISEHP), (7TH INTERNATIONAL SYMPOSIUM ON HIGHWAY CAPACITY AND QUALITY OF SERVICE, 3RD INTERNATIONAL SYMPOSIUM ON FREEWAY AND TOLLWAY OPERATIONS)
(2016)
Proceedings Paper
Transportation
Panos D. Prevedouros, Bill M. Halkias
INTERNATIONAL SYMPOSIUM ON ENHANCING HIGHWAY PERFORMANCE (ISEHP), (7TH INTERNATIONAL SYMPOSIUM ON HIGHWAY CAPACITY AND QUALITY OF SERVICE, 3RD INTERNATIONAL SYMPOSIUM ON FREEWAY AND TOLLWAY OPERATIONS)
(2016)
Proceedings Paper
Transportation
Panos D. Prevedouros, Lambros K. Mitropoulos
INTERNATIONAL SYMPOSIUM ON ENHANCING HIGHWAY PERFORMANCE (ISEHP), (7TH INTERNATIONAL SYMPOSIUM ON HIGHWAY CAPACITY AND QUALITY OF SERVICE, 3RD INTERNATIONAL SYMPOSIUM ON FREEWAY AND TOLLWAY OPERATIONS)
(2016)
Letter
Engineering, Civil
Panos D. Prevedouros, Carlton C. Urban
ITE JOURNAL-INSTITUTE OF TRANSPORTATION ENGINEERS
(2014)