EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Single-Camera AI-Based Traffic Analytics for Heterogeneous Intersections: A Deep Learning Framework for Microscopic Data Extraction from Smartphone Video

Bibek K.C., Ayushma Pokhrel, Deepika Pandey, Dikshya Karna, Dipika Dahal, Ramesh Marikhu, Ramesh Bala

International Journal on Engineering Technology · 18.06.2026 · 3 (2) · 339-348

DOI: 10.3126/injet.v3i2.95661 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal on Engineering Technology, online erschienen am 18.06.2026. Verfasst von Bibek K.C. und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In countries like Nepal, where traffic is heterogeneous, mixed, and non-lane-disciplined, the data collection methods used in transportation planning remain outdated and incapable of producing the microscopic parameters needed to understand local driving behaviors. This paper demonstrates a computer vision framework that converts footage from a single elevated smartphone camera (4K, 24 fps) into microsimulation-ready traffic data at the Koteshwor intersection, a busy three-legged junction in Kathmandu. The framework deploys YOLOv8x for vehicle detection, ByteTrack for multi-object tracking supported by a three-tier identity recovery mechanism, and per-approach planar homography, along with a post-processing pipeline for axial-length reclassification, speed correction, Wiedemann 74 safety-distance extraction, and complementary acceleration/deceleration metrics. From two independent peak-hour datasets yielding 31,882 total vehicle trajectories, 29 stratified validation clips covering 1,805 manually counted vehicles resulted in a 100% GEH pass rate and a class-wise Mean Absolute Percentage Error (MAPE) of 2.48%. The framework outputs volumetric counts across seven vehicle classes, Origin-Destination (OD) matrices, speed distributions, and trajectory-level microscopic parameters, demonstrating that a single smartphone setup can produce richer and more reliable traffic data than traditional manual surveys.

Zitieren

APA

K.C., B., Pokhrel, A., Pandey, D., Karna, D., Dahal, D., Marikhu, R., & Bala, R. (2026). Single-Camera AI-Based Traffic Analytics for Heterogeneous Intersections: A Deep Learning Framework for Microscopic Data Extraction from Smartphone Video. International Journal on Engineering Technology, 3(2), 339-348. https://doi.org/10.3126/injet.v3i2.95661

Vancouver

K.C. B, Pokhrel A, Pandey D, Karna D, Dahal D, Marikhu R, et al. Single-Camera AI-Based Traffic Analytics for Heterogeneous Intersections: A Deep Learning Framework for Microscopic Data Extraction from Smartphone Video. International Journal on Engineering Technology. 2026;3(2):339-348. doi:10.3126/injet.v3i2.95661

BibTeX
@article{KC2026,
  author = {K.C., Bibek and Pokhrel, Ayushma and Pandey, Deepika and Karna, Dikshya and Dahal, Dipika and Marikhu, Ramesh and Bala, Ramesh},
  title = {Single-Camera AI-Based Traffic Analytics for Heterogeneous Intersections: A Deep Learning Framework for Microscopic Data Extraction from Smartphone Video},
  journal = {International Journal on Engineering Technology},
  year = {2026},
  volume = {3},
  number = {2},
  pages = {339--348},
  doi = {10.3126/injet.v3i2.95661}
}
Kostenlos starten →