BOLD Project Page
BOLD features are image descriptors specifically proposed for the detection of texture-less objects. Nevertheless, they also showed to deal with textured objects with a performance comparable to that of state-of-the-art image descriptors. They are efficiently implementable and run in real-time on an off-the-shelf CPU.
BOLD features were proposed within the following scientific work:
The BOLD algorithm has been developed by CVLab in cooperation with Datalogic Automation within the VIALAB Project, funded by Regione Emilia Romagna. Please note that a patent has been filed covering the invention associated with BOLD features.
A pre-compiled library including the implementation of BOLD as well as of the object detection pipeline described in  is available here.
Be bold, go BOLD!