Motorcycles are abundant objects in the transit and often related with traffic and criminal law breaking in many countries. For instance, motorcycles are used to perform rob-and-run crimes and related to an increasing number of accidents that result in severe injuries and deaths. Therefore, it is crucial to identify the motorcycles and monitor its behavior in wide areas, which is an overwhelming work.
Moreover, Motorcycle ReID has some remarkable differences when compared to the classical ReID problems as person and vehicle.
To address the above-mentioned issues and boost the research in the motorcycle ReID problem, we propose the Motorcycle Re-Identification (MoRe) dataset, which is the first large-scale motorcycle ReID database captured by urban traffic cameras.
This repository contains all codes used for evaluating ReID task on MoRe Dataset.
Creates a Conda environment from environment.yml.
conda env create -f environment.ymlAll functions were built to work using MoRe dataset as hdf5 file. So, first create the hdf5 file.
python build_dataset.py -i path-to-more -o MoRe.hdf5Distributed under the MIT License. See LICENSE for more information.
Augusto Maillo - [email protected]