Nighttime vehicle detection database
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, Conneticut 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
The annotated database has been split into training and test as it can be seen in the link. There is a README about how to use NVD.
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 (Early Access) (doi: 10.1109/TITS.2021.3053863https://doi.org/10.1016/j.image.2021.116135)
A. Bell, C. R. del-Blanco, F. Jaureguizar and N. García, "Robust Nighttime Vehicle Detection Based on Foveal Classifiers," 2020 IEEE International Symposium on Circuits and Systems (ISCAS), Sevilla, 2020, pp. 1-5, doi: 10.1109/ISCAS45731.2020.9180730.