Research  

 

  • GTI
  • data
  • Nighttime Vehicle Detection database (NVD)

Nighttime Vehicle Detection database (NVD)

Description

This database, Nighttime Vehicle Detection database (NVD), has been gathered from real traffic cameras publicly available from five different locations on highways: Richmond, Walnut, California, Connecticut and Gelderland. The cameras record monochrome video (gray scale) at night, and in the five scenarios, vehicles usually appear with complex illumination patterns and large flashes, instead of well-defined lights.

Samples of the five scenarios:

 
Walnut Connecticut California

Walnut

Connecticut

California

 

Richmond Gelderland

Richmond

Gelderland

 

Dataset structure:

The annotated database has been split into training and test as it can be seen in the link. There is a README here about how to use NVD.

Download

Citation

Please, cite the following paper in your publications if you use this database in your work:

A. Bell, T. Mantecón, C. Dí­az, C.R. del Blanco, F. Jaureguizar, N. Garcí­a, "A Novel System for Nighttime Vehicle Detection Based on Foveal Classifiers with Real-Time Performance", IEEE Trans. Intelligent Transportation Systems, vol. xx, no. x, pp. xxx-xxx, xxx 2021 (Article in press) (doi: 10.1109/TITS.2021.3053863)

For questions about this dataset, please contact:

Andrés Bell: This email address is being protected from spambots. You need JavaScript enabled to view it..

Carlos R. del Blanco: This email address is being protected from spambots. You need JavaScript enabled to view it..