基于信息論的KL-Reg點(diǎn)云配準(zhǔn)算法
doi: 10.11999/JEIT141248
基金項(xiàng)目:
國家自然科學(xué)基金青年科學(xué)基金(61100113),國家教育部留學(xué)歸國基金教外司留[2012]940號,重慶市首批青年骨干教師項(xiàng)目(渝教人(2011)31號),重慶市基礎(chǔ)與前沿研究計劃項(xiàng)目(cstc2013jcyjA 40062),重慶郵電大學(xué)學(xué)科引進(jìn)人才基金(A2010-12)和重慶市研究生科研創(chuàng)新項(xiàng)目(CYS14142)資助課題
Information Theory Based KL-Reg Point Cloud Registration
-
摘要: 針對含有高噪聲、體外點(diǎn)及不完整點(diǎn)云數(shù)據(jù)的配準(zhǔn)失效問題,該文提出以信息論為理論基礎(chǔ),相對熵度量點(diǎn)云相似度的KL-Reg算法。該算法不需要顯式地建立對應(yīng)關(guān)系,首先將點(diǎn)云數(shù)據(jù)建模為高斯混合模型,然后用相對熵度量高斯混合模型間的分布距離,最后通過最小化分布距離計算模型變換。實(shí)驗(yàn)結(jié)果表明所提的KL-Reg算法配準(zhǔn)精度高、穩(wěn)定性強(qiáng)。
-
關(guān)鍵詞:
- 機(jī)器視覺 /
- 點(diǎn)云配準(zhǔn) /
- KL散度 /
- 高斯混合模型
Abstract: The registration of point clouds with high noises, outliers and missing data will be failure because the correspondence between point clouds is inaccurate. This paper proposes a information theory based point cloud registration method called KL-Reg algorithm without building correspondence. The method represents the point cloud with Gaussian mixture model, then computes the transformation through minimizing the KL divergence without build explicit correspondence. Experimental results show that KL-Reg algorithm is precise and stable.-
Key words:
- Machine vision /
- Point clouds registration /
- KL-divergence /
- Gaussian mixture model
-
Zitova B and Flusser J. Image registration methods: a survey[J]. Image and Vision Computing, 2003, 21(11): 977-1000. Lian Z, Godil A, Bustos B, et al.. A comparison of methods for non-rigid 3D shape retrieval[J]. Pattern Recognition, 2013, 46(1): 449-461. Liu M, Vemuri B C, Amari S I, et al.. Shape retrieval using hierarchical total bregman soft clustering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(12): 2407-2419. Besl P J and McKay N D. Method for registration of 3-D shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(2): 586-606. Tagliasacchi A, Bouaziz S, and Pauly M. Sparse iterative closest point[J]. Computer Graphics Forum, 2013, 32(5): 113-123. Tam G K L, Cheng Z Q, Lai Y K, et al.. Registration of 3D point clouds and meshes: a survey from rigid to nonrigid[J]. IEEE Transactions on Visualization and Computer Graphics, 2013, 19(7): 1199-1217. Jian B and Vemuri B C. Robust point set registration using gaussian mixture models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(8): 1633-1645. Myronenko A and Song X. Point set registration: coherent point drift[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(12): 2262-2275. Tsin Y and Kanade T. A correlation-based approach to robust point set registration[C]. Computer Vision-ECCV 2004. Springer Berlin Heidelberg, Prague, 2004: 558-569. Granger S and Pennec X. Multi-scale EM-ICP: a fast and robust approach for surface registration[C]. Computer VisionECCV 2002, Springer Berlin Heidelberg, Copenhagen, 2002: 418-432. Hermans J, Smeets D, Vandermeulen D, et al.. Robust point set registration using EM-ICP with information-theoretically optimal outlier handling[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colorado, USA, 2011: 2465-2472. Lipman Y, Yagev S, Poranne R, et al.. Feature matching with bounded distortion[J]. ACM Transactions on Graphics, 2014, 33(3), DOI: 10.1145/2602142. Paulus S, Dupuis J, Mahlein A K, et al.. Surface feature based classification of plant organs from 3D laserscanned point clouds for plant phenotyping[J]. BMC Bioinformatics, 2013, 14(1), DOI: 10.1186/147-2105-14-238. Zeng Y, Wang C, Gu X, et al.. A generic deformation model for dense non-rigid surface registration: a higher-order MRF- based approach[C]. IEEE International Conference on Computer Vision (ICCV), Sydney, Australia, 2013: 3360-3367. Hou T and Qin H. Robust dense registration of partial nonrigid shapes[J]. IEEE Transactions on Visualization and Computer Graphics, 2012, 18(8): 1268-1280. Lombaert H, Grady L, Polimeni J R, et al.. FOCUSR: feature oriented correspondence using spectral regularization(a method for precise surface matching[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, Australia, 2013, 35(9): 2143-2160. Chang W and Zwicker M. Automatic registration for articulated shapes[J]. Computer Graphics Forum, 2008, 27(5): 1459-1468. Bronstein M M and Kokkinos I. Scale-invariant heat kernel signatures for non-rigid shape recognition[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, 2010: 1704-1711. Sun J, Ovsjanikov M, and Guibas L. A concise and provably informative multi-scale signature based on heat diffusion[J]. Computer Graphics Forum, 2009, 28(5): 1383-1392. Hershey J R and Olsen P A. Approximating the Kullback Leibler divergence between Gaussian mixture models[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, Honolulu, 2007(4): 317-320. Karaboga D, Gorkemli B, Ozturk C, et al.. A comprehensive survey: artificial bee colony (ABC) algorithm and applications[J]. Artificial Intelligence Review, 2014, 42(1): 21-57. -