The evaluation of computer vision and pattern recognition systems is usually a burdensome and time-consuming activity. In this chapter all the benchmarks publicly available for re-identification will be reviewed and compared, starting from the ancestors VIPeR and Caviar to the most recent datasets for 3D modeling such as SARC3d (with calibrated cameras) and RGBD-ID (with range sensors). Specific requirements and constraints are highlighted and reported for each of the described collections. In addition, details on themetrics that aremostly used to test and evaluate the re-identification systems are provided.
CITATION STYLE
Vezzani, R., & Cucchiara, R. (2014). Benchmarking for person re-identification. In Advances in Computer Vision and Pattern Recognition (Vol. 56, pp. 333–349). Springer-Verlag London Ltd. https://doi.org/10.1007/978-1-4471-6296-4_16
Mendeley helps you to discover research relevant for your work.