Man vs. computer: benchmarking machine learning algorithms for traffic sign recognition
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
Man vs. computer : benchmarking machine learning algorithms for traffic sign recognition. / Stallkamp, J.; Schlipsing, M.; Salmen, J.; Igel, Christian.
In: Neural Networks, Vol. 32, 2012, p. 323-332.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Man vs. computer
AU - Stallkamp, J.
AU - Schlipsing, M.
AU - Salmen, J.
AU - Igel, Christian
N1 - Selected Papers from IJCNN 2011
PY - 2012
Y1 - 2012
N2 - Traffic signs are characterized by a wide variability in their visual appearance in real-world environments. For example, changes of illumination, varying weather conditions and partial occlusions impact the perception of road signs. In practice, a large number of different sign classes needs to be recognized with very high accuracy. Traffic signs have been designed to be easily readable for humans, who perform very well at this task. For computer systems, however, classifying traffic signs still seems to pose a challenging pattern recognition problem. Both image processing and machine learning algorithms are continuously refined to improve on this task. But little systematic comparison of such systems exist. What is the status quo? Do today’s algorithms reach human performance? For assessing the performance of state-of-the-art machine learning algorithms, we present a publicly available traffic sign dataset with more than 50,000 images of German road signs in 43 classes. The data was considered in the second stage of the GermanTraffic Sign Recognition Benchmark held at IJCNN 2011. The results of this competition are reported and the best-performing algorithms are briefly described. Convolutional neural networks (CNNs) showed particularly high classification accuracies in the competition. We measured the performance of human subjects on the same data—and the CNNs outperformed the human test persons.
AB - Traffic signs are characterized by a wide variability in their visual appearance in real-world environments. For example, changes of illumination, varying weather conditions and partial occlusions impact the perception of road signs. In practice, a large number of different sign classes needs to be recognized with very high accuracy. Traffic signs have been designed to be easily readable for humans, who perform very well at this task. For computer systems, however, classifying traffic signs still seems to pose a challenging pattern recognition problem. Both image processing and machine learning algorithms are continuously refined to improve on this task. But little systematic comparison of such systems exist. What is the status quo? Do today’s algorithms reach human performance? For assessing the performance of state-of-the-art machine learning algorithms, we present a publicly available traffic sign dataset with more than 50,000 images of German road signs in 43 classes. The data was considered in the second stage of the GermanTraffic Sign Recognition Benchmark held at IJCNN 2011. The results of this competition are reported and the best-performing algorithms are briefly described. Convolutional neural networks (CNNs) showed particularly high classification accuracies in the competition. We measured the performance of human subjects on the same data—and the CNNs outperformed the human test persons.
U2 - 10.1016/j.neunet.2012.02.016
DO - 10.1016/j.neunet.2012.02.016
M3 - Conference article
C2 - 22394690
VL - 32
SP - 323
EP - 332
JO - Neural Networks
JF - Neural Networks
SN - 0893-6080
Y2 - 31 July 2011 through 5 August 2011
ER -
ID: 40393629