Gijs Dubbelman is an Assistant Professor with the Video Coding and Architecture (VCA) group at Eindhoven University of Technology (TU/e)/ Here, he heads the Mobile Perception Systems (MPS) research cluster, which focuses on signal processing technologies that allow mobile sensor platforms to perceive the world around them. His areas of expertise include computer vision and multiple-view geometry and robotics and he has been working on topics such as large-scale visual-odometry, simultaneous localization and mapping, bundle adjustment and on-line camera re-calibration. Gijs also has a background in computer graphics, software engineering and project management.
Key research areas are computer vision, pattern recognition, robotics, and sensor fusion. Important application domain of MPS are automotive and transportation. Gijs’ line of research focuses on 3-D computer vision systems for autonomous robots and vehicles. He has designed and developed state-of-the-art computer vision algorithms for obstacle detection, ego-motion estimation, and simultaneous localization and mapping. He contributed the COP-SLAM algorithm for real-time embedded visual-SLAM to the scientific open-source project OpenSLAM.
Gijs Dubbelman obtained his BSc in Information and Communication Technology and his MSc Degree cum laude in Artificial intelligence from the University of Amsterdam. In 2011 he obtained his PhD from the same university on the topic of intrinsic statistical techniques for robust pose estimation. He performed his PhD research on robust estimation of motion parameters from image data using intrinsic statistics in close cooperation with Intelligent Imaging department of the national organization of applied scientific research of the Netherlands (TNO), which funded the research. In 2011 and 2012 Gijs was a member of the internationally renowned Field Robotics Center of Carnegie Mellon's Robotics Institute. He worked in close collaboration with the National Robotics Engineering Center (NREC) and with CMU's Qatar campus.
Development and analysis of a real-time system for automated detection of improvised explosive device indicators from ground vehiclesJournal of Electronic Imaging (2019)
Incremental hopping-window pose-graph fusion for real-time vehicle localization89th IEEE Vehicular Technology Conference, VTC Spring 2019 (2019)
Monocular semantic occupancy grid mapping with convolutional variational encoder-decoder networksIEEE Robotics and Automation Letters (2019)
Training of convolutional networks on multiple heterogeneous datasets for street scene semantic segmentation2018 IEEE Intelligent Vehicles Symposium, IV 2018 (2018)
Testing facilities for end-to-end test of vertical applications enabled by 5G networks20th International Conference on Transparent Optical Networks, (ICTON2018) (2018)
- Training project 1
- Advanced Automotive Sensing
- Advanced Sensing using Deep Learning
- Spectrum of Automotive
- Internship SPS
- Automotive sensing
No ancillary activities