Exploració per autor "Behnke, Sven"
Ara es mostren els items 1-2 de 2
-
Combining semantic and geometric features for object class segmentation of indoor scenes
Husain, Syed Farzad; Schulz, Hannes; Dellen, Babette; Torras, Carme; Behnke, Sven (Institute of Electrical and Electronics Engineers (IEEE), 2016)
Article
Accés obertScene understanding is a necessary prerequisite for robots acting autonomously in complex environments. Low-cost RGB-D cameras such as Microsoft Kinect enabled new methods for analyzing indoor scenes and are now ubiquitously ... -
Semantic segmentation priors for object discovery
Martín García, Germán; Husain, Syed Farzad; Schulz, Hannes; Frintrop, Simone; Torras, Carme; Behnke, Sven (IEEE Press, 2016)
Text en actes de congrés
Accés obertReliable object discovery in realistic indoor scenes is a necessity for many computer vision and service robot applications. In these scenes, semantic segmentation methods have made huge advances in recent years. Such ...