Speedup 3-D Texture-Less Object Recognition Against Self-Occlusion for Intelligent Manufacturing

Realtime 3-D object detection and 6-DOF pose estimation in clutter background is crucial for intelligent manufacturing, for example, robot feeding and assembly, where robustness and efficiency are the two most desirable goals. Especially for various metal parts with a textless surface, it is hard for most state of the arts to extract robust feature from the clutter background with various occlusions. To overcome this, in this paper, we propose an online 3-D object detection and pose estimation method to overcome self-occlusion for textureless objects. For feature representation, we only adopt the raw 3-D point clouds with normal cues to define our local reference frame and we automatically learn the compact 3-D feature from the simple local normal statistics via autoencoder. For a similarity search, a new basis buffer k-d tree method is designed without suffering branch divergence; therefore, ours can maximize the GPU parallel processing capabilities especially in practice. We then generate the hypothesis candidates via the hough voting, filter the false hypotheses, and refine the pose estimation via the iterative closest point strategy. For the experiments, we build a new 3-D dataset including industrial objects with heavy self-occlusions and conduct various comparisons with the state of the arts to justify the effectiveness and efficiency of our method.