The German Traffic Sign Recognition Benchmark: A multi-class classification competition

TLDR

The German Traffic Sign Recognition Benchmark is a multi‑category classification competition at IJCNN 2011 that tackles the challenging real‑world problem of automatic traffic sign recognition for advanced driver assistance systems. The benchmark supplies a lifelike dataset of over 50,000 images across 43 unbalanced classes, featuring extensive variations in appearance and precomputed feature sets, and asks participants to classify two test sets of more than 12,500 images each. The paper reports results on the first test set, briefly describing and comparing the top‑performing methods to human recognition performance and baseline results.

Abstract

The "German Traffic Sign Recognition Benchmark" is a multi-category classification competition held at IJCNN 2011. Automatic recognition of traffic signs is required in advanced driver assistance systems and constitutes a challenging real-world computer vision and pattern recognition problem. A comprehensive, lifelike dataset of more than 50,000 traffic sign images has been collected. It reflects the strong variations in visual appearance of signs due to distance, illumination, weather conditions, partial occlusions, and rotations. The images are complemented by several precomputed feature sets to allow for applying machine learning algorithms without background knowledge in image processing. The dataset comprises 43 classes with unbalanced class frequencies. Participants have to classify two test sets of more than 12,500 images each. Here, the results on the first of these sets, which was used in the first evaluation stage of the two-fold challenge, are reported. The methods employed by the participants who achieved the best results are briefly described and compared to human traffic sign recognition performance and baseline results.