This website presents benchmark data sets and results for computer vision and machine learning problems. The benchmark data sets are compiled by our institute. Each dataset provides a public leaderboard which will allow submission of your own results on these datasets. Only results that are/will be published in a journal or conference paper are elligible for publication in the publich leaderboards. Submissions, however, are possible beforehand, but they will be only visible to you.
The German Traffic Sign Recognition Benchmark (GTSRB), a large multi-category classification benchmark. It is provided by the Real-Time Computer Vision research group. The dataset was used in a competition at IJCNN 2011 in San Jose, CA, USA. For details on this dataset and the competition, please see the "GTSRB" section.
The German Traffic Sign Detection Benchmark (GTSDB), is a detection problem in natural images. The task is to pinpoint a traffic sign's location in a full color video image. The competition is proposed to the IJCNN 2013 in Dallas, TX, USA. For details on this dataset and the competition, please see the "GTSDB" section.