SegICP: Integrated deep semantic segmentation and pose estimation
Author(s)Wong, Jay M.; Kee, Vincent; Le, Tiffany; Wagner, Syler; Mariottini, Gian-Luca; Schneider, Abraham; Hamilton, Lei; Chipalkatty, Rahul; Hebert, Mitchell; Johnson, David M.S.; Wu, Jimmy; Zhou, Bolei; Torralba, Antonio; ... Show more Show less
MetadataShow full item record
© 2017 IEEE. Recent robotic manipulation competitions have highlighted that sophisticated robots still struggle to achieve fast and reliable perception of task-relevant objects in complex, realistic scenarios. To improve these systems' perceptive speed and robustness, we present SegICP, a novel integrated solution to object recognition and pose estimation. SegICP couples convolutional neural networks and multi-hypothesis point cloud registration to achieve both robust pixel-wise semantic segmentation as well as accurate and real-time 6-DOF pose estimation for relevant objects. Our architecture achieves 1 cm position error and < 5° angle error in real time without an initial seed. We evaluate and benchmark SegICP against an annotated dataset generated by motion capture.
Wong, Jay M., Kee, Vincent, Le, Tiffany, Wagner, Syler, Mariottini, Gian-Luca et al. 2017. "SegICP: Integrated deep semantic segmentation and pose estimation."
Author's final manuscript