A Local Reference Frame Construction Method Based on the Signed Surface Variation

doi:10.11947/j.JGGS.2021.0303

Abstract

Abstract:

A fast local reference frame (LRF) construction method based on the signed surface variation is proposed, which can adapt to the real-time applications such as self-driving, face recognition, object detection. The z-axis of the LRF is generated based on the concavity of the local surface of keypoint. The x-axis is constructed by the weighted vector sum of a set of projection vectors of the local neighborhoods around keypoint. The performance of the proposed LRF is evaluated on six standard datasets and compared with six state-of-the-art LRF construction methods (e.g., BOARD, FLARE, SHOT, RoPS and TOLDI). Experimental results validate the high repeatability, robustness, universality and time efficiency of our method.

Key words: signed surface variation; local reference frame; point cloud; feature extraction

Xiaopeng YAN,Wei ZHOU,Rencan PENG,Wenliang PAN,Lei WANG,Guoxin HU. A Local Reference Frame Construction Method Based on the Signed Surface Variation[J]. Journal of Geodesy and Geoinformation Science, 2021, 4(3): 25-37.

Figures/Tables 8

Fig.1

Tab.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

References 32

[1]	GUO Yulan, SOHEL F, BENNAMOUN M, et al. An accurate and robust range image registration algorithm for 3D object modeling[J]. IEEE Transactions on Multimedia, 2014,16(5):1377-1390. doi: 10.1109/TMM.2014.2316145
[2]	SHAH S A A, BENNAMOUN M, BOUSSAID F. Keypoints-based surface representation for 3D modeling and 3D object recognition[J]. Pattern Recognition, 2017,64:29-38. doi: 10.1016/j.patcog.2016.10.028
[3]	ABBAD A, ABBAD K, TAIRI H. 3D face recognition: Multi-scale strategy based on geometric and local descriptors[J]. Computers & Electrical Engineering, 2018,70:525-537.
[4]	NAFFOUTI S E, FOUGEROLLE Y, AOUISSAOUI I, et al. Heuristic optimization-based wave kernel descriptor for deformable 3D shape matching and retrieval[J]. Signal, Image and Video Processing, 2018,12(5):915-923. doi: 10.1007/s11760-018-1235-7
[5]	RUSU R B, BRADSKI G, THIBAUX R, et al. Fast 3D recognition and pose using the Viewpoint Feature Histogram[C]//Proceedings of 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems. Taipei, China: IEEE, 2010: 2155-2162.
[6]	MARTON Z C, PANGERCIC D, BLODOW N, et al. Combined 2D-3D categorization and classification for multimodal perception systems[J]. The International Journal of Robotics Research, 2011,30(11):1378-1402. doi: 10.1177/0278364911415897
[7]	TAO Wuyong, HUA Xianghong, WANG Ruisheng, et al. Quintuple local coordinate images for local shape description[J]. Photogrammetric Engineering & Remote Sensing, 2020,86(2):121-132.
[8]	GUO Yulan, SOHEL F, BENNAMOUN M, et al. TriSI: A distinctive local surface descriptor for 3D modeling and object recognition[C]//Proceedings of the 8th International Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. Barcelona: [s.n.], 2013: 86-93.
[9]	GUO Yulan, SOHEL F, BENNAMOUN M, et al. Rotational projection statistics for 3D local surface description and object recognition[J]. International Journal of Computer Vision, 2013,105(1):63-86. doi: 10.1007/s11263-013-0627-y
[10]	AO Sheng, GUO Yulan, TIAN Jindong, et al. A repeatable and robust local reference frame for 3D surface matching[J]. Pattern Recognition, 2020,100:107186. doi: 10.1016/j.patcog.2019.107186
[11]	TOMBARI F, SALTI S, DI STEFANO L. Unique signatures of histograms for local surface description[C]//Proceedings of the 11th European Conference on Computer Vision. Heraklion: Springer, 2010: 356-369.
[12]	TOMBARI F, SALTI S, DI STEFANO L. Unique shape context for 3d data description[C]//Proceedings of the ACM Workshop on 3D Object Retrieval. Firenze: ACM, 2010: 57-62.
[13]	YANG Jiaqi, ZHANG Qian, XIAO Yang, et al. TOLDI: An effective and robust approach for 3D local shape description[J]. Pattern Recognition, 2017,65:175-187. doi: 10.1016/j.patcog.2016.11.019
[14]	FLINT A, DICK A, VAN DEN HENGEL A. Thrift: Local 3D structure recognition[C]//Proceedings of the 9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications. Glenelg, SA: IEEE, 2007: 182-188.
[15]	RUSU R B, BLODOW N, BEETZ M. Fast point feature histograms (FPFH) for 3D registration[C]//Proceedings of 2009 IEEE International Conference on Robotics and Automation. Kobe: IEEE, 2009: 3212-3217.
[16]	MIAN A S, BENNAMOUN M, OWENS R. Three-dimensional model-based object recognition and segmentation in cluttered scenes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006,28(10):1584-1601. doi: 10.1109/TPAMI.2006.213
[17]	GUO Yulan, BENNAMOUN M, SOHEL F, et al. An integrated framework for 3-D modeling, object detection, and pose estimation from point-clouds[J]. IEEE Transactions on Instrumentation and Measurement, 2015,64(3):683-693. doi: 10.1109/TIM.2014.2358131
[18]	TOMBARI F, DI STEFANO L. Object recognition in 3D scenes with occlusions and clutter by Hough voting[C]//Proceedings of the 4th Pacific-Rim Symposium on Image and Video Technology. Singapore: IEEE, 2010: 349-355.
[19]	PETRELLI A, DI STEFANO L. On the repeatability of the local reference frame for partial shape matching[C]//Proceedings of 2011 International Conference on Computer Vision. Barcelona: IEEE, 2011: 2244-2251.
[20]	PETRELLI A, DI STEFANO L. Pairwise registration by local orientation cues[J]. Computer Graphics Forum, 2016,35(6):59-72.
[21]	YANG Jiaqi, XIAO Yang, CAO Zhiguo. Toward the repeatability and robustness of the local reference frame for 3D shape matching: An evaluation[J]. IEEE Transactions on Image Processing, 2018,27(8):3766-3781. doi: 10.1109/TIP.2018.2827330 pmid: 29698208
[22]	NIE Jianhui, LIU Ye, GAO Hao, et al. Feature line detection from point cloud based on signed surface variation and region segmentation[J]. Journal of Computer-Aided Design & Computer Graphics, 2015,27(12):2332-2339.
[23]	NOVATNACK J, NISHINO K. Scale-dependent/invariant local 3D shape descriptors for fully automatic registration of multiple sets of range images[C]//Proceedings of the 10th European Conference on Computer Vision. Marseille: Springer, 2008: 440-453.
[24]	MIAN A, BENNAMOUN M, OWENS R. On the repeatability and quality of keypoints for local feature-based 3D object retrieval from cluttered scenes[J]. International Journal of Computer Vision, 2010,89(2-3):348-361. doi: 10.1007/s11263-009-0296-z
[25]	CHUA C S, JARVIS R. Point signatures: A new representation for 3D object recognition[J]. International Journal of Computer Vision, 1997,25(1):63-85. doi: 10.1023/A:1007981719186
[26]	TOMBARI F, SALTI S, DI STEFANO L. Performance evaluation of 3D keypoint detectors[J]. International Journal of Computer Vision, 2013,102(1-3):198-220. doi: 10.1007/s11263-012-0545-4
[27]	SALTI S, TOMBARI F, DI STEFANO L. A performance evaluation of 3D keypoint detectors[C]//Proceedings of 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission. Hangzhou, China: IEEE, 2011: 236-243.
[28]	MIAN A S, BENNAMOUN M, OWENS R. Three-dimensional model-based object recognition and segmentation in cluttered scenes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006,28(10):1584-1601. doi: 10.1109/TPAMI.2006.213
[29]	CURLESS B, LEVOY M. A volumetric method for building complex models from range images[C]//Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques. New York: ACM, 1996: 303-312.
[30]	RUSU R B, COUSINS S. 3D is here: Point cloud library (PCL)[C]//Proceedings of 2011 IEEE International Conference on Robotics and Automation. Shanghai, China: IEEE, 2011: 1-4.
[31]	PRAKHYA S M, LIN Jie, CHANDRASEKHAR V, et al. 3DHoPD: A fast low-dimensional 3-D descriptor[J]. IEEE Robotics and Automation Letters, 2017,2(3):1472-1479. doi: 10.1109/LRA.2017.2667721
[32]	ZHANG Kailin, ZHANG Liang. 3D object recognition and 6 DoF pose estimation in scenes with occlusions and clutter based on C-SHOT 3D descriptor[J]. Journal of Computer-Aided Design & Computer Graphics, 2017,29(5):846-853.

No.	Dataset name	Acquisition	Quality	Occlusion	Clutter	Noise	Mesh decimation	Model	Scene	#Models	#Scenes
1	Retrieval	Synthetic	High	Y	N	Y	N	3D	3D	6	54
2	Bologna	Synthetic	High	N	Y	N	Y	3D	3D	6	45
3	Random Views	Synthetic	High	Y	Y	Y	N	3D	2.5D	6	36
4	UWA	Minolta Vivid 910	High	Y	Y	Y	N	3D	2.5D	5	50
5	Space Time	Space Time stereo	Medium	Y	Y	Y	N	2.5D	2.5D	6	12
6	Kinect	Microsoft Kinect	Low	Y	Y	Y	N	2.5D	2.5D	27	16