Real-time Learning and Detection of 3D Texture-less Objects: A Scalable Approach

We present a method for the learning and detection of multipl e rigid texture-less 3D objects intended to operate at frame rate speeds for video in put. The method is geared for fast and scalable learning and detection by combining tr actable extraction of edgelet constellations with library lookup based on rotationand s cale-invariant descriptors. The approach learns object views in real-time, and is generativ e enabling more objects to be learnt without the need for re-training. During testing, a random sample of edgelet constellations is tested for the presence of known objects. We perform testing of single and multi-object detection on a 30 objects dataset showing d etections of any of them within milliseconds from the object’s visibility. The resu lts show the scalability of the approach and its framerate performance.