Automated Scene Flow Data Generation for Training and Verification

Autor: Wasenm��ller, Oliver, Schuster, Ren��, Stricker, Didier, Leiss, Karl, Pfister, J��rger, Ganus, Oleksandra, Tatsch, Julian, Savkin, Artem, Brasch, Nikolas
Jazyk: angličtina
Rok vydání: 2018
Předmět:
Popis: Scene flow describes the 3D position as well as the 3D motion of each pixel in an image. Such algorithms are the basis for many state-of-the-art autonomous or automated driving functions. For verification and training large amounts of ground truth data is required, which is not available for real data. In this paper, we demonstrate a technology to create synthetic data with dense and precise scene flow ground truth.
Databáze: OpenAIRE