Adaptive Algorithms for Motion Estimation (B04)

• Subject Area: Image and Language Processing, Computer Graphics and Visualisation, Human Computer Interaction, Ubiquitous and Wearable Computing
• Term: since 2015
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 251654672

We aim at the development of accurate, robust, and stable algorithms for motion estimation. To this end, neural networks shall be developed for estimating the 3D motion from stereo sequences (scene flow) by adaptively integrating all available information. In this context, also the stability of such networks shall be investigated along with the integration of 3D information into 2D motion estimation (optical flow). The creation of a flexible novel open-source data set shall support the development of the algorithms. Finally, the developed methods shall be adapted such that they can be used for a variety of applications in the context of visualization, human-machine interaction, and cognitive sciences.

• DFG Programme: CRC/Transregios
• Subproject of: TRR 161: Quantitative Methods for Visual Computing
• Applicant Institution: Universität Stuttgart
• Project Head: Professor Dr.-Ing. Andrés Bruhn