Abstract
We present a pipeline for fast object pose estimation using RGB-D images, which does not rely on image features or machine learning. We are interested in segmenting objects with large variety in app.earance, from lack of texture to presence of strong textures, with a focus on the task of robotic grasping. The proposed pipeline is divided into an object segmentation part and a pose estimation part. We first find candidate object clusters using a graph-based image segmentation technique. A modified Canny edge detector is introduced for extracting robust graph edges by fusing RGB and depth information. A suitable cost function is used for building the graph, which is then partitioned using the concept of internal and external differences between graph regions. The extracted object regions are then used to initialize the 3D position of a quaternion-based Particle Swarm Optimization algorithm (Q-PSO), that fits a 3D model of the object to the depth image. The fitness function is based on depth information only and the quaternion formulation avoids singularities and the need for conversions between rotation representations. In this work we focus on the details of the GPU implementation of Q-PSO, in order to fully exploit the highly parallelizable nature of the particular implementation of the particle swarm algorithm, and discuss critic implementation details. We then test the app.roach on different publicly available RGB-D object datasets, and provide numeric comparisons with other state-of-the-art methods, as well as a discussion on robustness and an extension to the case of articulated objects. We show how Q-PSO offers comparable performances to current learning-based app.roaches, while not suffering from the problems of lack of features in objects or issues related to training, such as the need for a large training set and long training times.
Similar content being viewed by others
References
Amazon Picking Challenge. Website, http://amazonpickingchallenge.org (2016)
Abramov, A., Pauwels, K., Papon, J., Worgotter, F., Dellen, B.: Depth-supported real-time video segmentation with the kinect. In: 2012 IEEE Workshop on App.lications of Computer Vision (WACV), pp. 457–464 (2012). http://doi.org/10.1109/WACV.2012.6163000
Aldoma, A., Tombari, F., Rusu, R.B., Vincze, M.: Pattern Recognition: Joint 34th DAGM and 36th OAGM Symposium, Graz, Austria, August 28–31, 2012. Proceedings, Springer Berlin Heidelberg, Berlin, chap OUR-CVFH – Oriented, Unique and Repeatable Clustered Viewpoint Feature Histogram for Object Recognition and 6DOF Pose Estimation, pp. 113–122 (2012). https://doi.org/10.1007/978-3-642-32717-9_12
Bastos-Filho, C., Nascimento, D., Junior, M.O.: Running particle swarm optimization on graphic processing units. INTECH Open Access Publisher (2011)
Bonde, U., Badrinarayanan, V., Cipolla, R.: Robust instance recognition in presence of occlusion and clutter. In: European Conference on Computer Vision, pp. 520–535. Springer, Berlin (2014)
Brachmann, E., Krull, A., Michel, F., Gumhold, S., Shotton, J., Rother, C.: Learning 6d object pose estimation using 3d object coordinates. In: European Conference on Computer Vision, pp. 536–551. Springer, Berlin (2014)
Carpin, S., Birk, A., Jucikas, V.: On map merging. Robot. Auton. Syst. 53(1), 1–14 (2005). https://doi.org/10.1016/j.robot.2005.07.001. http://www.sciencedirect.com/science/article/pii/S0921889005001041
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vis. 59(2), 167–181 (2004)
Hinterstoisser, S., Lepetit, V., Ilic, S., Holzer, S., Bradski, G., Konolige, K., Navab, N.: Model based training, detection and pose estimation of texture-less 3d objects in heavily cluttered scenes. In: Computer Vision–ACCV 2012, pp. 548–562. Springer, Berlin (2012)
Holzer, H.S.S., Cagniart, C., Ilic, S., Konolige, K., Navab, N., Lepetit, V.: Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes (2011)
Hodaň, T, Zabulis, X., Lourakis, M., Obdrlek, C., Matas, J.: Detection and fine 3d pose estimation of texture-less objects in rgb-d images. In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4421–4428 (2015). https://doi.org/10.1109/IROS.2015.7354005
Holzer, S., Rusu, R., Dixon, M., Gedikli, S., Navab, N.: Adaptive neighborhood selection for real-time surface normal estimation from organized point cloud data using integral images. In: 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2684–2689 (2012). https://doi.org/10.1109/IROS.2012.6385999
Kennedy, J.: Particle swarm optimization. In: Encyclopedia of Machine Learning, pp. 760–766. Springer, Berlin (2010)
Michel, F., Krull, A., Brachmann, E., Yang, M.Y., Gumhold, S., Rother, C.: Pose estimation of kinematic chain instances via object coordinate regression. In: Proceedings of the British Machine Vision Conference 2015, BMVC 2015, pp. 181.1–181.11, Swansea (2015). https://doi.org/10.5244/C.29.181
Mishra, A.K., Shrivastava, A., Aloimonos, Y.: Segmenting simple objects using rgb-d. In: 2012 IEEE International Conference on Robotics and Automation (ICRA), pp. 4406–4413. IEEE (2012)
de P, Veronese, L., Krohling, R.A.: Swarm’s flight: accelerating the particles using c-cuda. In: IEEE Congress on Evolutionary Computation, 2009. CEC’09, pp. 3264–3270. IEEE, New Jersey (2009)
Pineda, J.: A parallel algorithm for polygon rasterization. In: ACM SIGGRAPH Computer Graphics, vol. 22, pp. 17–20. ACM, New York (1988)
Rao, D., Le, Q.V., Phoka, T., Quigley, M., Sudsang, A., Ng, A.Y.: Grasping novel objects with depth segmentation. In: 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2578–2585. IEEE, New Jersey (2010)
Rennie, C., Shome, R., Bekris, K.E., De Souza, A.F.: A dataset for improved rgbd-based object detection and pose estimation for warehouse pick-and-place. CoRR arXiv:1509.01277 (2016)
Rosa, S., Toscana, G.: Fast feature-less quaternion-based particle swarm optimization for object pose estimation from rgb-d images. In: Proceedings of the British Machine Vision Conference (BMVC) (2016)
Schäfer, H., Lenzen, F., Garbe, C.S.: Depth and intensity based edge detection in time-of-flight images. In: 3DV, pp. 111–118 (2013)
Shoemake, K.: Animating rotation with quaternion curves. In: ACM SIGGRAPH computer graphics, vol. 19, pp. 245–254. ACM, New York (1985)
Sola J: Quaternion kinematics for the error-state kf (2017)
Tejani, A., Tang, D., Kouskouridas, R., Kim, T.K.: Latent-class hough forests for 3d object detection and pose estimation. In: Computer Vision–ECCV 2014, pp. 462–477. Springer, Berlin (2014)
Toscana, G., Rosa, S.: Fast graph-based object segmentation for rgb-d images. CoRR arXiv:1605.03746 (2016)
Zhou, Y., Tan, Y.: Gpu-based parallel particle swarm optimization. In: IEEE Congress on Evolutionary Computation, 2009. CEC’09, pp. 1493–1500. IEEE, New Jersey (2009)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Rosa, S., Toscana, G. & Bona, B. Q-PSO: Fast Quaternion-Based Pose Estimation from RGB-D Images. J Intell Robot Syst 92, 465–487 (2018). https://doi.org/10.1007/s10846-017-0714-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10846-017-0714-3