3D Map Reconstruction in Indoor Environment Based on Normal Distribution Transformation Under Gravity Constraint

doi:DOI: 10.16183/j.cnki.jsjtu.2018.01.005

Abstract

Abstract: A method for offline reconstruction of indoor 3D map is proposed based on an improved normal distribution transform (NDT) algorithm. First, a constraint in the gravity direction is incorporated into a 3D NDT, so that map deformation in extra dimensions is rectified. Then a cyclic gradient matching scheme is proposed to deal with the matching error resulted from scarce overlap between consecutive frames. Finally, a graph optimization is adopted in the back-end map construction. By using a swinging laser, experiments validate its performance and high accuracy.

Key words: indoor 3D map; reconstruction; gravity constraint; normal distributions transform (NDT); cyclic gradient matching; graph optimization

CLC Number:

TP 391.41

QI Mingxua,b,YANG Minga,b,WANG Chunxiangc,WANG Binga,b. 3D Map Reconstruction in Indoor Environment Based on Normal Distribution Transformation Under Gravity Constraint[J]. Journal of Shanghai Jiao Tong University, 2018, 52(1): 26-32.

References

［1］MADDERN W, PASCOE G, NEWMAN P. Leveraging experience for large-scale LIDAR localisation in changing cities［C］∥IEEE International Conference on Robotics and Automation (ICRA). Washington, USA: IEEE, 2015: 1684-1691. ［2］YONEDA K, TEHRANI H, OGAWA T, et al. Lidar scan feature for localization with highly precise 3-D map［C］∥IEEE Intelligent Vehicles Symposium Proceedings. Dearborn, USA: IEEE, 2014: 1345-1350. ［3］肖已达, 王冰, 杨明, 等. 基于激光雷达的道路可通行区域检测［J］. 机电一体化, 2013, 19(2): 62-66. XIAO Yida, WANG Bing, YANG Ming, et al. The detection of road traffic zone based on laser radar［J］. Mechatronics, 2013, 19 (2): 62-66. ［4］BUONOCORE L, SANTOS S R B D, NETO A A, et al. FastSLAM filter implementation for indoor autonomous robot［C］∥IEEE Intelligent Vehicles Symposium (IV). Gothenburg, Sweden: IEEE, 2016: 484-489. ［5］REDONDO E L, MARTINEZ-MARIN T. A compact representation of the environment and its frontiers for autonomous vehicle navigation［C］∥IEEE Intelligent Vehicles Symposium (IV). Gothenburg, Sweden: IEEE, 2016: 851-857. ［6］WULF O, WAGNER B. Fast 3D scanning methods for laser measurement systems［C］∥International Conference on Control Systems & Computer Science, 2003: 1-6. ［7］YOSHIDA T, IRIE K, KOYANAGI E, et al. 3D laser scanner with gazing ability［C］∥IEEE International Conference on Robotics and Automation. Shanghai, China: IEEE, 2011, 47(10): 3098-3103. ［8］谷晓杰,卜春光,陈成,等. 三维激光测距系统设计与标定方法研究［J］. 沈阳理工大学学报, 2014, 33(5): 10-14. GU Xiaojie, BU Chunguang, CHEN Cheng, et al. Design, implementation and calibration of 3-D LIDAR scanning system［J］. Journal of Shenyang Ligong University, 2014, 33(5): 10-14. ［9］ROHDE J, JATZKOWSKI I, MIELENZ H, et al. Vehicle pose estimation in cluttered urban environments using multilayer adaptive Monte Carlo localization［C］∥International Conference on Information Fusion. Heidelberg, Germany: IEEE, 2016. ［10］POMERLEAU F, COLAS F, SIEGWART R, et al. Comparing ICP variants on real-world data sets［J］. Autonomous Robots, 2013, 34(3):133-148. ［11］MAGNUSSON M, LILIENTHAL J A, DUCKETT T. Scan registration for autonomous mining vehicles using 3D-NDT［J］. Journal of Field Robotics, 2007, 24(10):803-827. ［12］MAGNUSSON M, NCHTER A, LRKEN C, et al. Evaluation of 3D registration reliability and speed—A comparison of ICP and NDT［C］∥IEEE International Conference on Robotics and Automation. Kobe, Japan: IEEE, 2009: 3907-3912. ［13］DRYANOVSKI I, VALENTI R G, XIAO J Z. Fast visual odometry and mapping from RGB-D data［C］∥IEEE International Conference on Robotics and Automation. Karlsruhe, Germany: IEEE, 2013: 2305-2310. ［14］KMMERLE R, GRISETTI G, STRASDAT H, et al. g2o: A general framework for graph optimization［C］∥IEEE International Conference on Robotics and Automation. Shanghai, China: IEEE, 2011: 3607-3613.

[1]	BAI Xiongfei, GONG Shuicheng, LI Xuesong, XU Bo, YANG Xiaoli, WANG Mingyan. Defect Classification of Weld Metallographic Structure Based on Data Augmentation of Poisson Fusion [J]. Journal of Shanghai Jiao Tong University, 2023, 57(10): 1316-1328.
[2]	WANG Jiajing1,2,ZHANG Zhusheng1,HE Weiping1. Identification of Tools with Failure Barcode Based on Multi-Information Fusion [J]. Journal of Shanghai Jiaotong University, 2014, 48(12): 1675-1680.
[3]	ZHAO Hongwei,XIE Yongfang,CAO Binfang,JIANG Zhaohui. Extraction and Application of Froth Texture Feature Based on Gabor Wavelets and LPP in Flotation Process [J]. Journal of Shanghai Jiaotong University, 2014, 48(07): 942-947.
[4]	WANG Jiajing1,2,ZHANG Shusheng1,HE Weiping1. 2D Bar Code Recovery in Highlight Area of Metal Parts [J]. Journal of Shanghai Jiaotong University, 2013, 47(12): 1836-1841.
[5]	WANG Xiaoduan1,LIU Shuxin2,LIU Manhua1. Fingerprint Singular-point Detection Based on Mathematical Model Analysis [J]. Journal of Shanghai Jiaotong University, 2013, 47(08): 1222-1226.
[6]	LI Bin, YE Hao. Robust Image Registration Method Based on Affine Geometric Invariant [J]. Journal of Shanghai Jiaotong University, 2012, 46(12): 1881-1884.
[7]	WU Yi-Quan-1, 2 , ZHANG Xiao-Jie-1, WU Shi-Hua-1, ZHANG Guo-Hua-2, ZHANG Sheng-Wei-2, YU Su-Fen-2. Image Thresholding Based on 2-D Histogram θ-Division and Minimum Error [J]. Journal of Shanghai Jiaotong University, 2012, 46(06): 892-899.
[8]	QIN Hong-Xing-1, YANG Jie-2. Point-Based Surface Filtering Based on Meshless Local Petrov-Galerkin Method [J]. Journal of Shanghai Jiaotong University, 2012, 46(04): 584-590.
[9]	QIN Hong-xing,YANG Jie,GUO Lü, TANG Wei. A Hard Accelerated Algorithm for EWA Splatting Based on Modern GPU [J]. Journal of Shanghai Jiaotong University, 2008, 42(12): 1943-1946.
[10]	TANG Wei, YAO Li-xiu, YANG Jie, QIN Hong-xing. An Adaptive Sampling Algorithm Based on Vector Field for Medical Volume Rendering [J]. Journal of Shanghai Jiaotong University, 2008, 42(10): 1650-1654.
[11]	SU Fu. Region of Interest Based Texture Image Retrieval Using Curvelet Correlogram [J]. Journal of Shanghai Jiaotong University, 2014, 48(05): 653-657.
[12]	LI Xiaoxu1,DAI Bin1,CAO Jie1,2. An Improved UPF Object Tracking Algorithm Based on Multi-Feature Fusion [J]. Journal of Shanghai Jiaotong University, 2014, 48(10): 1473-1478.
[13]	CAO Jiea,b，LI Yuqina，WU Dib. A High Precision Particle Filter Based on Improved Differential Evolution [J]. Journal of Shanghai Jiaotong University, 2014, 48(12): 1714-1720.
[14]	GUO Gaifang,HE Weiping,LI Xiashuang,WANG Jian,WU Zhenfang. Accurate Localization of 2D Barcode Marked in Mental Parts Under Complex Background Based on Edge and LevelSet [J]. Journal of Shanghai Jiao Tong University, 2017, 51(1): 90-.
[15]	XUE Mengxia,LIU Shirong,WANG Jian. Dynamic MultiTarget Recognition Based on Machine Vision [J]. Journal of Shanghai Jiao Tong University, 2017, 51(6): 727-733.