Abstract Aiming at fast recognition of 3D point clouds, a point cloud recognition algorithm based on local surface feature histogram is proposed. Firstly, the cyclic voxel filtering algorithm is applied to filter the point clouds with different resolutions to the specified resolution. Secondly, the points with obvious local characteristics are selected as the key points based on the key point search algorithm with the maximum mean curvature of the neighborhood. The feature descriptor of the key point is calculated according to the relationship between the center of gravity of the point clouds in the neighborhood and the normal and distance of each point in the neighborhood surface. Then, the features are matched according to the spatial relationship between the adjacent key points and the Euclidean distance of the feature descriptor. Finally, the multithread recognition framework is adopted to speed up the online recognition. The experimental results show that the recognition speed is high.
Corresponding Authors:LU Jun, Ph.D., professor. His research interests include computer vision and intelligent control.
About author:: HUA Bowen, master student. His research interests include computer vision.ZHU Bo, master student. His research interests include computer vision.
[1] NGUYEN X S, MOUADDIB A I, PHUONG T, et al. Action Recog-nition in Depth Videos Using Hierarchical Gaussian Descriptor. Multimedia Tools and Applications, 2018, 77(12): 21617-21652. [2] YAO H X, JIANG X H, SUN T F, et al. 3D Human Action Recognition Based on the Spatial-Temporal Moving Skeleton Descriptor // Proc of the IEEE International Conference on Multimedia and Expo. Washington, USA: IEEE, 2017: 937-942. [3] GUO Y L, BENNAMOUN M, SOHEL F, et al. An Integrated Framework for 3-D Modeling, Object Detection, and Pose Estimation from Point-Clouds. IEEE Transactions on Instrumentation and Measurement, 2015, 64(3): 683-693. [4] LIE Y J, GUO Y L, HAYAT M, et al. A Two-Phase Weighted Co-llaborative Representation for 3D Partial Face Recognition with Single Sample. Pattern Recognition, 2016, 52: 218-237. [5] TIAN C W, ZHANG Q, ZHANG J, et al. 2D-PCA Representation and Sparse Representation for Image Recognition. Journal of Computational and Theoretical Nanoscience, 2017, 14(1): 829-834. [6] FAN Z, LI Z X, LI W J, et al. A Combined Texture-Shape Global 3D Feature Descriptor for Object Recognition and Grasping // Proc of the International Conference on Industrial Informatics-Computing Technology, Intelligent Technology, Industrial Information Integration. Washington, USA: IEEE, 2017: 47-54. [7] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 39(6): 1137-1149. [8] LI R F, LU W C, LIANG H Y, et al. Multiple Features with Extreme Learning Machines for Clothing Image Recognition. IEEE Access, 2018, 6: 36283-36294. [9] LU T T, HU W D, LIU C, et al. Relative Pose Estimation of a Lander Using Crater Detection and Matching. Optical Engineering, 2016, 55(2). DOI: 10.1117/1.OE.55.2.023102. [10] YANG J Q, XIAO Y, CAO Z G. Toward the Repeatability and Robustness of the Local Reference Frame for 3D Shape Matching: An Evaluation. IEEE Transactions on Image Processing, 2018, 27(8): 3766-3781. [11] GUO Y L, BENNAMOUN M, SOHEL F, et al. 3D Object Recognition in Cluttered Scenes with Local Surface Features: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(11): 2270-2287. [12] KECHAGIAS-STAMATIS O, AOUF N, CHERMAK L. B-HoD: A Lightweight and Fast Binary Descriptor for 3D Object Recognition and Registration // Proc of the 14th IEEE International Conference on Networking, Sensing and Control. Washington, USA: IEEE, 2017. DOI: 10.1109/ICNSC.2017.8000064. [13] SHAH S A A, BENNAMOUN M, BOUSSAID F. A Novel Feature Representation for Automatic 3D Object Recognition in Cluttered Scenes. Neurocomputing, 2016, 205: 1-15. [14] SALES D O, AMARO J, OSÓRIO F S. 3D Shape Descriptor for Objects Recognition // Proc of the Latin American Robotics Symposium(LARS) and Brazilian Symposium on Robotics(SBR). Washington, USA: IEEE, 2017. DOI: 10.1109/SBR-LARS-R.2017.8215285. [15] GUO Y L, SOHEL F, BENNAMOUN M, et al. A Novel Local Surface Feature for 3D Object Recognition under Clutter and Occlusion. Information Sciences, 2015, 293: 196-213. [16] 张哲,许宏丽,尹辉.一种基于关键点选择的快速点云配准算法.激光与光电子学进展, 2017, 54(12): 121002-1-121002-9. (ZHANG Z, XU H L, YI H. A Fast Point Cloud Registration Algorithm Based on Key Point Selection. Laser and Optoelectronics Progress, 2017, 54(12): 149-157.)
2020, Vol. 33 
