A
Andreas Mogelmose
Researcher at Aalborg University
Publications - 31
Citations - 1581
Andreas Mogelmose is an academic researcher from Aalborg University. The author has contributed to research in topics: Traffic sign recognition & Pedestrian detection. The author has an hindex of 16, co-authored 29 publications receiving 1276 citations. Previous affiliations of Andreas Mogelmose include University of California, San Diego & MediaTech Institute.
Papers
More filters
Journal ArticleDOI
Vision-Based Traffic Sign Detection and Analysis for Intelligent Driver Assistance Systems: Perspectives and Survey
TL;DR: A survey of the traffic sign detection literature, detailing detection systems for traffic sign recognition (TSR) for driver assistance and discussing future directions of TSR research, including the integration of context and localization.
Journal ArticleDOI
Vision for Looking at Traffic Lights: Issues, Survey, and Perspectives
Morten Bornø Jensen,Mark Philip Philipsen,Andreas Mogelmose,Thomas B. Moeslund,Mohan M. Trivedi +4 more
TL;DR: The evaluation of TLR systems is studied and discussed in depth, and a common evaluation procedure is proposed, which will strengthen evaluation and ease comparison, and an extensive public data set based on footage from U.S. roads is published.
Journal ArticleDOI
Part-Based Pedestrian Detection and Feature-Based Tracking for Driver Assistance: Real-Time, Robust Algorithms, and Evaluation
Antonio Prioletti,Andreas Mogelmose,Paolo Grisleri,Mohan M. Trivedi,Alberto Broggi,Thomas B. Moeslund +5 more
TL;DR: The novelty of this system relies on the combination of a HOG part-based approach, tracking based on a specific optimized feature, and porting on a real prototype and offers high performance in terms of detection rate, false positives per hour, and frame rate.
Proceedings ArticleDOI
Traffic Light Detection: A Learning Algorithm and Evaluations on Challenging Dataset
Mark Philip Philipsen,Morten Bornø Jensen,Andreas Mogelmose,Thomas B. Moeslund,Mohan M. Trivedi +4 more
TL;DR: An extensive public database is collected based on footage from US roads, which shows that the learning based detector achieves an AUC of 0.4 and 0.32 for day sequence 1 and 2, respectively, which is more than an order of magnitude better than the two heuristic model-based detectors.
Journal ArticleDOI
Multi-modal RGB---Depth---Thermal Human Body Segmentation
Cristina Palmero,Albert Clapés,Chris Holmberg Bahnsen,Andreas Mogelmose,Thomas B. Moeslund,Sergio Escalera +5 more
TL;DR: The baseline, using Gaussian mixture models for the probabilistic modeling and Random Forest for the stacked learning, is superior to other state-of-the-art methods, obtaining an overlap above 75 % on the novel dataset when compared to the manually annotated ground-truth of human segmentations.