Skip to content
SDGs Center UDINUS

Evidence record · UDINUS · SDGs

Integrated Approach for Vehicle Detection, Tracking, and Counting in Urban Traffic Videos Utilizing YOLOv11 and DeepSORT Algorithms

Rektorat UDINUS 2026 Published 2026-10-30

Evidence record · UDINUS · SDGs

Unit
Rektorat UDINUS
Period
2026
Goals
Record
1a0ff607-b762-4bff-b4ad-38ee300bcb0f
Published
2026-10-30

Universitas Dian Nuswantoro conducted an activity addressing the increasingly complex conditions of urban traffic through the development of an automatic system for detecting and tracking vehicles in traffic surveillance videos. The activity involved Nguyen, Minh T.; Setiadi, De R. I. M.; Nguyen, Dung T.; Dinh, Long Q.; Vu, Thang C.; Teague, Keith A.; and Nguyen, Mui D. as participants. The activity focused on challenges encountered by current systems in real-life situations, including obscured vehicles and background noise.

The proposed approach combined the YOLOv11 model with the DeepSORT algorithm to improve the accuracy of vehicle detection and tracking from traffic videos. The use of DeepSORT enabled the simultaneous tracking of multiple objects. The activity also applied a Kalman filter to estimate the motion state of vehicles accurately and to minimize common errors in complex situations. Through this integrated approach, the activity examined how automatic processing could address vehicle visibility and tracking challenges in urban traffic surveillance videos.

Experimental results reported that the proposed system effectively addressed the problem of obscured vehicles, improved detection accuracy, and reduced the rate of missed objects. The results also indicated a promising direction for developing automatic traffic monitoring systems capable of operating stably in diverse real-life conditions. The activity concerns urban traffic monitoring and the development of an approach intended for use in complex urban traffic contexts. Accordingly, UDINUS presents this activity as research related to sustainable cities and communities through the study of automatic vehicle detection and tracking in urban traffic videos.

Reference https://www.scopus.com/pages/publications/105037747441?origin=resultslist