Leibe Group

The Chair for Computer Science 13 (Computer Vision) has long-standing research expertise in computer vision and machine learning, especially for applications in dynamic visual scene understanding. Research areas include object and person detection, multi-object tracking, semantic segmentation, and detailed human body pose analysis. In particular, the chair is a leading developer of video object segmentation, multi-object tracking and segmentation, and 3D human body pose estimation methods and has published several state-of-the-art approaches in those areas that have won international benchmarks and challenges in recent years. Chaired by Prof. Bastian Leibe, the research work of the group is internationally highly visible and has received many awards, including an ERC Starting Grant and an ERC Consolidator Grant.

Discover our homepage here.

Methods

• Visual Object Recognition
• Multi-Object Tracking and Segmentation
• Human Pose Estimation
• Deep Learning

5 selected publications

1. P. Voigtlaender, M. Krause, A. Osep, J. Luiten, BBG Sekar, A. Geiger, B. Leibe (2019), MOTS: Multi-Object Tracking and Segmentation, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
2. T. Sattler, B. Leibe, L. Kobbelt (2016), Efficient and Effective Prioritized Matching for Large-Scale Image-based Localization, in IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 39(9), pp. 1744-1756.
3. A. Ess, K. Schindler, B. Leibe. L. Van Gool (2010), Object Detection and Tracking for Autonomous Navigation in Dynamic Environments, in International Journal of Robotics Research, Vol. 29(14), pp. 1707-1725.
4. B. Leibe, K. Schindler, N. Cornelis, L. Van Gool (2008), Coupled Object Detection and Tracking from Static Cameras and Moving Vehicles, in IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 30, No. 10, pp.1683-1698.
5. B. Leibe, A. Leonardis, B. Schiele (2008), Robust Object Detection with Interleaved Object Categorization and Segmentation, in International Journal of Computer Vision, Vol. 77, No. 1-3, pp. 259-289.