Object class and instance recognition on rgb-d data

Viktor Seib, Susanne Christ-Friedmann, Susanne Thierfelder, Dietrich Paulus, Branislav Vuksanovic, Jianhong Zhou, Antanas Verikas
2013 Sixth International Conference on Machine Vision (ICMV 2013)  
We present a novel approach for combining 3D depth and visual information for object class and object instance recognition. Object classes are recognized by first assigning local geometric primitive labels using a CRF, followed by an SVM classification. Object instances are recognized using Hough-transform clustering of SURF features. Both algorithms perform well on publicly available object databases as well as on acquired data with an RGB-D camera. The object instance recognition algorithm
more » ... further evaluated during the RoboCup world championship 2012 in Mexico-City and won the first place in the Technical Challenge of the @Home-league.
doi:10.1117/12.2049915 fatcat:pv5fg4kv4zgwnodv4b3rt7x6l4