Archive Meta Data

Author(s)

Sebastian Houben, Johannes Stallkamp, Jan Salmen, Marc Schlipsing, Christian Igel

Title

German Traffic Sign Detection Benchmark GTSDB

Description

Data from the German Traffic Sign Detection Benchmark (GTSDB). This archive contains the training set used during the IJCNN 2013 competition. 

The main archive FullIJCNN2013.zip includes the 900 training images (1360 x 800 pixels) in PPM format, the image sections containing only the traffic signs, a file in CSV format with the ground truth, and a ReadMe.txt with more details.

For historic reasons, we also provide the data split as in the competition:

FullIJCNN2013.zip: Entire dataset consisting of 900 full images 
TrainIJCNN2013.zip: Training dataset from the IJCNN 2013 competition consisting of 600 full images
TestIJCNN2013.zip: Test dataset from the IJCNN 2013 competition consisting of 300 full images, without ground truth annotations
gt.txt: Ground truth annotations for test dataset

Reference: 
Sebastian Houben, Johannes Stallkamp, Jan Salmen, Marc Schlipsing, and Christian Igel. Detection of Traffic Signs in Real-World Images: The German Traffic Sign Detection Benchmark.International Joint Conference on Neural Networks (IJCNN 2013), pp. 715-722, IEEE Press