CAR CLassification

Dataset Download

Download Prophesee’s N-CARS dataset, a large real-world event-based car classification dataset.

The N-CARS dataset is a large real-world event-based dataset for car classification. It is composed of 12,336 car samples and 11,693 non-cars samples (background).


The data was recorded using an ATIS camera mounted behind the windshield of a car. The data was extracted from various driving sessions.

The dataset is split in 7940 car and 7482 background training samples, 4396 car and 4211 background testing samples. Each example lasts 100 milliseconds.

Fill out the below form to access the download page.



When using the data in an academic context, please cite the following paper: 

Amos Sironi, Manuele Brambilla, Nicolas Bourdis, Xavier Lagorce, Ryad Benosman “HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classification”. To appear in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018

Preprint on ArXiv




Each file is a binary file in which events are encoded using 4 bytes (uint32) for the timestamps and 4 bytes (uint32) for the data, encoding is little-endian ordering.

The data is composed of 14 bits for the x position, 14 bits for the y position and 1 bit for the polarity (encoded as -1/1). See the matlab script inside the downloaded package for more details on how to read the data.

For more information on how the dataset was created, please refer to the paper.