Pose Estimation of Primitive-Shaped Objects from a Depth Image Using Superquadric Representation
Source abstract
Abstract
This paper presents a method for estimating the six Degrees of Freedom (6DoF) pose of texture-less primitive-shaped objects from depth images. As the conventional methods for object pose estimation require rich texture or geometric features to the target objects, these methods are not suitable for texture-less and geometrically simple shaped objects. In order to estimate the pose of the primitive-shaped object, the parameters that represent primitive shapes are estimated. However, these methods explicitly limit the number of types of primitive shapes that can be estimated. We employ superquadrics as a primitive shape representation that can represent various types of primitive shapes with only a few parameters. In order to estimate the superquadric parameters of primitive-shaped objects, the point cloud of the object must be segmented from a depth image. It is known that the parameter estimation is sensitive to outliers, which are caused by the miss-segmentation of the depth image. Therefore, we propose a novel estimation method for superquadric parameters that are robust to outliers. In the experiment, we constructed a dataset in which the person grasps and moves the primitive-shaped objects. The experimental results show that our estimation method outperformed three conventional methods and the baseline method.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Robot Manipulation and Learning · Robotics and Sensor-Based Localization · Image and Object Detection Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Information and Computer Science, Keio University, Yokohama 223-8522, Japan
References (40)
Show source-provided references
1. Rad, M., and Lepetit, V. (2017, January 22–29). BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.413 ↗
2. Sundermeyer, M., Marton, Z.C., Durner, M., Brucker, M., and Triebel, R. (2018, January 8–14). Implicit 3D Orientation Learning for 6D Object Detection from RGB Images. Proceedings of the European Conference on Computer Vision (ECCV) 2018, Munich, Germany.10.1007/978-3-030-01231-1_43 ↗
3. Peng, S., Liu, Y., Huang, Q., Zhou, X., and Bao, H. (2019, January 15–21). PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation. Proceedings of the CVPR 2019, Long Beach, CA, USA.10.1109/CVPR.2019.00469 ↗
4. Rusu, R.B., Blodow, N., and Beetz, M. (2009, January 12–17). Fast Point Feature Histograms (FPFH) for 3D registration. Proceedings of the 2009 IEEE International Conference on Robotics and Automation, Kobe, Japan.10.1109/ROBOT.2009.5152473 ↗
5. Drost, B., Ulrich, M., Navab, N., and Ilic, S. (2010, January 13–18). Model globally, match locally: Efficient and robust 3D object recognition. Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA.10.1109/CVPR.2010.5540108 ↗
6. Wang, H., Sridhar, S., Huang, J., Valentin, J., Song, S., and Guibas, L.J. (2019, January 15–21). Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2019, Long Beach, CA, USA.10.1109/CVPR.2019.00275 ↗
7. Chen, Y., and Medioni, G. (1991, January 9–11). Object modeling by registration of multiple range images. Proceedings of the 1991 IEEE International Conference on Robotics and Automation, Sacramento, CA, USA.
8. Rünz, M., and Agapito, L. (June, January 29). Co-Fusion: Real-time Segmentation, Tracking and Fusion of Multiple Objects. Proceedings of the 2017 IEEE International Conference on Robotics and Automation (ICRA), Las Vegas, NV, USA.10.1109/ICRA.2017.7989518 ↗
9. Runz, M., Buffier, M., and Agapito, L. (2018, January 16–20). MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects. Proceedings of the 2018 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), Munich, Germany.10.1109/ISMAR.2018.00024 ↗
10. Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography10.1145/358669.358692 ↗
11. Tombari, F., and Di Stefano, L. (2012). Hough Voting for 3D Object Recognition under Occlusion and Clutter. IPSJ Trans. Comput. Vis. Appl., 4.10.2197/ipsjtcva.4.20 ↗
12. Superquadrics and angle-preserving transformations10.1109/MCG.1981.1673799 ↗
13. Solina, F., and Bajcsy, R. (1987, January 13–17). Range image interpretation of mail pieces with superquadrics. Proceedings of the 6th National Conference on Artificial Intelligence, Seattle, WA, USA.
14. Xiang, Y., Schmidt, T., Narayanan, V., and Fox, D. (2018). PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes. arXiv.10.15607/RSS.2018.XIV.019 ↗
15. Birdal, T., and Ilic, S. (2015, January 19–22). Point Pair Features Based Object Detection and Pose Estimation Revisited. Proceedings of the 2015 International Conference on 3D Vision, Lyon, France.10.1109/3DV.2015.65 ↗
16. Sano, M., Matsumoto, K., Thomas, B.H., and Saito, H. (2016, January 19–23). [POSTER] Rubix: Dynamic Spatial Augmented Reality by Extraction of Plane Regions with a RGB-D Camera. Proceedings of the 2015 IEEE International Symposium on Mixed and Augmented Reality, Yucatan, Mexico.10.1109/ISMAR.2015.43 ↗
17. Hachiuma, R., and Saito, H. (2016, January 20). Recognition and pose estimation of primitive shapes from depth images for spatial augmented reality. Proceedings of the 2016 IEEE 2nd Workshop on Everyday Virtual Reality (WEVR), Greenville, SC, USA.10.1109/WEVR.2016.7859541 ↗
18. Automatic scene parsing for generic object descriptions using shape primitives10.1016/j.robot.2015.11.003 ↗
19. Stanescu, A., Fleck, P., Schmalstieg, D., and Arth, C. (2018, January 16–20). Semantic Segmentation of Geometric Primitives in Dense 3D Point Clouds. Proceedings of the 2018 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct), Munich, Germany.10.1109/ISMAR-Adjunct.2018.00068 ↗
20. Bebis, G., Boyle, R., Parvin, B., Koracin, D., McMahan, R., Jerald, J., Zhang, H., Drucker, S.M., Kambhamettu, C., and El Choubassi, M. (2014). Object Recognition Using Constraints from Primitive Shape Matching. Advances in Visual Computing, Springer International Publishing.10.1007/978-3-319-14249-4 ↗
21. Extraction of cylinders and estimation of their parameters from point clouds10.1016/j.cag.2014.09.027 ↗
22. Drost, B., and Ilic, S. (2015, January 19–22). Local Hough Transform for 3D Primitive Detection. Proceedings of the 2015 International Conference on 3D Vision, Lyon, France.10.1109/3DV.2015.52 ↗
23. Röfer, T., Mayer, N.M., Savage, J., and Saranlı, U. (2012). Real-Time Plane Segmentation Using RGB-D Cameras, Springer.
24. Paschalidou, D., Ulusoy, A.O., and Geiger, A. (2019, January 15–21). Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2019, Long Beach, CA, USA.10.1109/CVPR.2019.01059 ↗
25. Vezzani, G., Pattacini, U., and Natale, L. (June, January 29). A grasping approach based on superquadric models. Proceedings of the 2017 IEEE International Conference on Robotics and Automation (ICRA), Las Vegas, NV, USA.10.1109/ICRA.2017.7989187 ↗
26. Makhal, A., Thomas, F., and Gracia, A.P. (February, January 31). Grasping Unknown Objects in Clutter by Superquadric Representation. Proceedings of the 2018 Second IEEE International Conference on Robotic Computing (IRC), Laguna Hills, CA, USA.10.1109/IRC.2018.00062 ↗
27. Vaskevicius, N., Pathak, K., and Birk, A. (2014, January 18–22). Fitting superquadrics in noisy, partial views from a low-cost RGBD sensor for recognition and localization of sacks in autonomous unloading of shipping containers. Proceedings of the 2014 IEEE International Conference on Automation Science and Engineering (CASE), Taipei, Taiwan.10.1109/CoASE.2014.6899335 ↗
28. Hachiuma, R., Ozasa, Y., and Saito, H. (March, January 27). Primitive Shape Recognition via Superquadric Representation using Large Margin Nearest Neighbor Classifier. Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Porto, Portugal.
29. Holzer, S., Rusu, R.B., Dixon, M., Gedikli, S., and Navab, N. (2012, January 7–12). Adaptive neighborhood selection for real-time surface normal estimation from organized point cloud data using integral images. Proceedings of the 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, Algarve, Portugal.10.1109/IROS.2012.6385999 ↗
30. Tateno, K., Tombari, F., and Navab, N. (October, January 28). Real-time and scalable incremental segmentation on dense SLAM. Proceedings of the 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany.10.1109/IROS.2015.7354011 ↗
31. Nguyen, C.V., Izadi, S., and Lovell, D. (2012, January 13–15). Modeling Kinect Sensor Noise for Improved 3D Reconstruction and Tracking. Proceedings of the 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization Transmission, Zurich, Switzerland.10.1109/3DIMPVT.2012.84 ↗
32. Moré, J.J. (1978). The Levenberg-Marquardt algorithm: Implementation and theory. Numerical Analysis, Springer.10.1007/BFb0067700 ↗
33. Girardeau-Montaut, D. (2020, May 08). CloudCompare. Available online: https://www.danielgm.net/cc/.
34. Lee, K.M., Matsushita, Y., Rehg, J.M., and Hu, Z. (2013). Model Based Training, Detection and Pose Estimation of Texture-Less 3D Objects in Heavily Cluttered Scenes, Springer.
35. Brachmann, E., Michel, F., Krull, A., Yang, M.Y., Gumhold, S., and Rother, C. (26–1, January 26). Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.366 ↗
36. Bierbaum, A., Gubarev, I., and Dillmann, R. (2008, January 22–26). Robust shape recovery for sparse contact location and normal data from haptic exploration. Proceedings of the 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, Nice, France.10.1109/IROS.2008.4650982 ↗
37. Buch, A.G., Kraft, D., Kamarainen, J., Petersen, H.G., and Krüger, N. (2013, January 6–10). Pose estimation using local structure-specific shape and appearance context. Proceedings of the 2013 IEEE International Conference on Robotics and Automation, Karlsruhe, Germany.10.1109/ICRA.2013.6630856 ↗
38. Magnusson, M. (2009). The Three-Dimensional Normal-Distributions Transform—An Efficient Representation for Registration, Surface Analysis, and Loop Detection. [Ph.D. Thesis, Örebro University].
39. Duncan, K., Sarkar, S., Alqasemi, R., and Dubey, R. (2013, January 6–10). Multi-scale superquadric fitting for efficient shape and pose recovery of unknown objects. Proceedings of the 2013 IEEE International Conference on Robotics and Automation, Karlsruhe, Germany.10.1109/ICRA.2013.6631176 ↗
40. Gpufit: An open-source toolkit for GPU-accelerated curve fitting10.1038/s41598-017-15313-9 ↗