Details
| Original language | English |
|---|---|
| Pages (from-to) | 296-308 |
| Number of pages | 13 |
| Journal | Transportation research record |
| Volume | 2678 |
| Issue number | 1 |
| Early online date | 16 May 2023 |
| Publication status | Published - Jan 2024 |
Abstract
An essential application in intelligent transportation systems is multi-target multi-camera tracking (MTMCT), where the target’s activity is tracked from different cameras. Although the tracking-by-detection scheme is the primary paradigm in MTMCT, the object association information from the video frames is lost. This is mainly because the multi-camera multi-object matching uses the information from the video frames separately. To solve this problem and leverage this association information, we propose an MTMCT framework, where features are built in the form of a graph and a graph similarity algorithm is used to match multi-camera objects. In this paper, we focus on the real-time scenario, where only the past images are used to match an object. Our method achieves an IDF1 score (the ratio of the number of correctly identified objects to the number of ground truth and average objects) of 0.75 with a rate of 14 frames per second (fps).
Keywords
- automatic vehicle detection and identification systems, data and data science, machine vision, pattern recognition, vehicle detection
ASJC Scopus subject areas
- Engineering(all)
- Civil and Structural Engineering
- Engineering(all)
- Mechanical Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Transportation research record, Vol. 2678, No. 1, 01.2024, p. 296-308.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Real-Time Multi-Vehicle Multi-Camera Tracking with Graph-Based Tracklet Features
AU - Nguyen, Tuan T.
AU - Nguyen, Hoang H.
AU - Sartipi, Mina
AU - Fisichella, Marco
N1 - Funding Information: The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This material is based on work partially supported by the U.S. Department of Energy’s Office of Energy Efficiency and Renewable Energy (EERE) under Award Number DE-EE0009208. This work was also supported by the European Union’s Horizon 2020 research and innovation program under grant agreement No. 833635 (project ROXANNE: Real-Time Network, Text, and Speaker Analytics for Combating Organized Crime, 2019–2022).
PY - 2024/1
Y1 - 2024/1
N2 - An essential application in intelligent transportation systems is multi-target multi-camera tracking (MTMCT), where the target’s activity is tracked from different cameras. Although the tracking-by-detection scheme is the primary paradigm in MTMCT, the object association information from the video frames is lost. This is mainly because the multi-camera multi-object matching uses the information from the video frames separately. To solve this problem and leverage this association information, we propose an MTMCT framework, where features are built in the form of a graph and a graph similarity algorithm is used to match multi-camera objects. In this paper, we focus on the real-time scenario, where only the past images are used to match an object. Our method achieves an IDF1 score (the ratio of the number of correctly identified objects to the number of ground truth and average objects) of 0.75 with a rate of 14 frames per second (fps).
AB - An essential application in intelligent transportation systems is multi-target multi-camera tracking (MTMCT), where the target’s activity is tracked from different cameras. Although the tracking-by-detection scheme is the primary paradigm in MTMCT, the object association information from the video frames is lost. This is mainly because the multi-camera multi-object matching uses the information from the video frames separately. To solve this problem and leverage this association information, we propose an MTMCT framework, where features are built in the form of a graph and a graph similarity algorithm is used to match multi-camera objects. In this paper, we focus on the real-time scenario, where only the past images are used to match an object. Our method achieves an IDF1 score (the ratio of the number of correctly identified objects to the number of ground truth and average objects) of 0.75 with a rate of 14 frames per second (fps).
KW - automatic vehicle detection and identification systems
KW - data and data science
KW - machine vision
KW - pattern recognition
KW - vehicle detection
UR - http://www.scopus.com/inward/record.url?scp=85179880936&partnerID=8YFLogxK
U2 - 10.1177/03611981231170591
DO - 10.1177/03611981231170591
M3 - Article
AN - SCOPUS:85179880936
VL - 2678
SP - 296
EP - 308
JO - Transportation research record
JF - Transportation research record
SN - 0361-1981
IS - 1
ER -