J
Jan Salmen
Researcher at Ruhr University Bochum
Publications - 26
Citations - 3112
Jan Salmen is an academic researcher from Ruhr University Bochum. The author has contributed to research in topics: Traffic sign recognition & Benchmark (computing). The author has an hindex of 12, co-authored 25 publications receiving 2312 citations. Previous affiliations of Jan Salmen include Continental Automotive Systems.
Papers
More filters
Journal ArticleDOI
2012 Special Issue: Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition
TL;DR: A publicly available traffic sign dataset with more than 50,000 images of German road signs in 43 classes is presented, and Convolutional neural networks showed particularly high classification accuracies in the competition, and the CNNs outperformed the human test persons.
Proceedings ArticleDOI
The German Traffic Sign Recognition Benchmark: A multi-class classification competition
TL;DR: The “German Traffic Sign Recognition Benchmark” is a multi-category classification competition held at IJCNN 2011, and a comprehensive, lifelike dataset of more than 50,000 traffic sign images has been collected.
Proceedings ArticleDOI
Detection of traffic signs in real-world images: The German traffic sign detection benchmark
TL;DR: This work introduces a real-world benchmark data set for traffic sign detection together with carefully chosen evaluation metrics, baseline results, and a web-interface for comparing approaches, and presents the best-performing algorithms of the IJCNN competition.
Proceedings ArticleDOI
Real-time stereo vision: Optimizing Semi-Global Matching
TL;DR: This study proposes a straight-forward extension of theSemi-Global Matching algorithm's parametrization that significantly improves the performance of SGM and considers individual penalties for different path orientations, weighted integration of paths, and penalties depending on intensity gradients.
Book ChapterDOI
Real-Time Stereo Vision: Making More Out of Dynamic Programming
TL;DR: This work presents a refined DP stereo processing algorithm which is based on a standard implementation, however it is more flexible and shows increased performance, and introduces the idea of multi-path backtracking to exploit the information gained from DP more effectively.