A self-adaptive regression algorithm with noise density function difference and its application to artificial target extraction

doi:10.11947/j.AGCS.2021.20190509

Abstract

Abstract: Instruments, surrounding environment and human operation often cause a lot of noise in the LiDAR, resulting in low model regression accuracy. RANSAC algorithm is widely used to solve model regression problems by virtue of its simple implementation and robustness. However, for different scenarios, RANSAC algorithm needs to constantly adjust the parameters to estimate the optimal model solution. Considering the RANSAC algorithm and its family existing shortcomings, according to the difference of density distribution between inliers and noise. This paper firstly optimizes the initial hypothesis model by using density weighted guided sampling, and then proposes a spatial density function to evaluate the optimal model and to calculate the number of iterations by using the spatial density function. The whole process does not need any prior knowledge. The method proposed in this paper can solve the model regression problem where the inliers ratio is more than 10%. In addition, compared with the existing methods, the method proposed in this paper can achieve high accuracy and robustness without prior information.

Key words: random sample consensus (RANSAC), weighted sample, space density function, density difference, self-adaptive threshold

CLC Number:

P237

JIA Xiangyang, HUANG Xianfeng, NIU Wenyuan, ZHANG Fan, GAO Yunlong, YANG Chong. A self-adaptive regression algorithm with noise density function difference and its application to artificial target extraction[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(2): 226-234.

References

[1] FISCHLER M A, BOLLES R C. Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981, 24(6):381-395.
[2] 陈敏, 朱庆, 何海清, 等. 面向城区宽基线立体像对视角变化的结构自适应特征点匹配[J]. 测绘学报, 2019, 48(9):1129-1140. DOI:10.11947/j.AGCS.2019.20180266. CHEN Min, ZHU Qing, HE Haiqing, et al. Structureadaptive feature point matching for urban area wide-baseline images with viewpoint variation[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(9):1129-1140. DOI:10.11947/j.AGCS.2019.20180266.
[3] 姚国标, 张力, 杜全叶, 等. 核线驱动与自适应窗口相结合的建筑物角点稳健匹配算法[J]. 测绘学报, 2015, 44(S1):160-165. DOI:10.11947/j.AGCS.2015.F019. YAO Guobiao, ZHANG Li, DU Quanye, et al. A robust matching algorithm for corner points of building based on epipolar driving and self-adaptive window[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(S1):160-165. DOI:10.11947/j.AGCS.2015.F019.
[4] 姚吉利, 马宁, 贾象阳, 等. 球形标靶的固定式扫描大点云自动定向方法[J]. 测绘学报, 2015, 44(4):431-437. DOI:10.11947/j.AGCS.2015.20130357. YAO Jili, MA Ning, JIA Xiangyang, et al. An approach for automatic orientation of big point clouds from the stationary scanners based on the spherical targets[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(4):431-437. DOI:10.11947/j.AGCS.2015.20130357.
[5] 姚吉利, 贾象阳, 马宁, 等. 地面激光扫描多站点云整体定向平差模型[J]. 测绘学报, 2014, 43(8):835-841. DOI:10.13485/j.cnki.11-2089.2014.0123. YAO Jili, JIA Xiangyang, MA Ning, et al. Overall orientation adjustment model of terrestrial laser scanning multi-station point clouds[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(8):835-841. DOI:10.13485/j.cnki.11-2089.2014.0123.
[6] 张帆, 黄印, 黄先锋, 等. 非直视区域的普通平面镜辅助地面三维激光扫描方法[J]. 测绘学报, 2017, 46(12):1950-1958. DOI:10.11947/j.AGCS.2017.20170052. ZHANG Fan, HUANG Yin, HUANG Xianfeng, et al. 3D laser scanning assisted by ordinary plane mirror for non-direct viewing area[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(12):1950-1958. DOI:10.11947/j.AGCS.2017.20170052.
[7] LAFARGE F, KERIVEN R, BRÉDIF M. Insertion of 3-d-primitives in mesh-based representations:towards compact models preserving the details[J]. IEEE Transactions on Image Processing, 2010, 19(7):1683-1694.
[8] 贾松敏, 郑泽玲, 张国梁, 等. 基于混合特征的机器人定位与地图创建[J]. 仪器仪表学报, 2018, 39(12):198-206. JIA Songmin, ZHENG Zeling, ZHANG Guoliang, et al. Robot localization and map building based on hybrid features[J]. Chinese Journal of Scientific Instrument, 2018, 39(12):198-206.
[9] CHUM O, MATAS J, KITTLER J. Locally optimized RANSAC[C]//25th DAGM Symposium on Pattern Recognition. Magdeburg:Springer, 2003:236-243.
[10] CHUM O, MATAS J. Matching with PROSAC-progressive sample consensus[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). San Diego, CA:IEEE, 2005:220-226.
[11] MYATT D R, TORR P H S, NASUTO S J, et al. NAPSAC:high noise, high dimensional robust estimation-it's in the bag[C]//Proceedings of the British Machine Vision Conference 2002. Cardiff, UK:DBLP, 2002:1-10.
[12] TORR P H S, ZISSERMAN A. MLESAC:a new robust estimator with application to estimating image geometry[J]. Computer Vision and Image Understanding, 2000, 78(1):138-156.
[13] HAST A, NYSJÖ J, MARCHETTI A. Optimal RANSAC-towards a repeatable algorithm for finding the optimal set[J]. Journal of WSCG, 2013, 21(1):21-30.
[14] CHUM O, MATAS J. Optimal randomized RANSAC[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(8):1472-1482.
[15] RAGURAM R, FRAHM J M, POLLEFEYS M. Exploiting uncertainty in random sample consensus[C]//2009 IEEE 12th International Conference on Computer Vision. Kyoto:IEEE, 2009:2074-2081.
[16] Michaelsen Eckart, Hansen Wolfgang V, Kirchhof Michael, et al. Estimating the essential matrix:Goodsac versus RANSAC[C]. Symposium Photogrammetric Computer Vision (PCV), Berlin:ISPRS,2006:161-166.
[17] SATTLER T, LEIBE B, KOBBELT L. SCRAMSAC:improving RANSAC's efficiency with a spatial consistency filter[C]//2009 IEEE 12th International Conference on Computer Vision. Kyoto:IEEE, 2009:2090-2097.
[18] TORR P H S. Bayesian model estimation and selection for epipolar geometry and generic manifold fitting[J]. International Journal of Computer Vision, 2002, 50(1):35-61.
[19] FENG C L, HUNG Y S. A robust method for estimating the fundamental matrix[C]//Digital Image Computing:Techniques and Applications. Sydney:DBLP, 2003:633-642.
[20] KONOUCHINE A, GAGANOV V, VEZNEVETS V. AMLESAC:a new maximum likelihood robust estimator[C]//Proceedings of the International Conference on Computer Graphics and Vision (Grapicon). Novosibirsk Akademgorodok:[s.n.], 2005:93-100.
[21] CHOI S, KIM J H. Robust regression to varying data distribution and its application to landmark-based localization[C]//2008 IEEE International Conference on Systems, Man and Cybernetics. Singapore:IEEE, 2008:3465-3470.
[22] ZHANG Yunliang, TIAN Hengyuan, DENG Yanzi, et al. Improving RANSAC for efficient and precise model fitting with statistical analysis[J]. European Journal of Electrical Engineering and Computer Science, 2019, 3(5):1-7.
[23] MOISAN L, MOULON P, MONASSE P. Automatic homographic registration of a pair of images, with a contrario elimination of outliers[J]. Image Processing On Line, 2012, 2:56-73.
[24] CHOI J, MEDIONI G. StaRSaC:stable random sample consensus for parameter estimation[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL:IEEE, 2009:675-682.
[25] LEMMENS M. Terrestrial laser scanning[M]//Geo-information. Geotechnologies and the Environment. Dordrecht:Springer, 2011:101-121.
[26] CASULA G, MORA P, BIANCHI M G. Detection of terrain morphologic features using GPS, TLS, and Land Surveys:"Tana Della Volpe" blind valley case study[J]. Journal of Surveying Engineering, 2010, 136(3):132-138.
[27] 姚吉利, 马宁, 贾象阳, 等. 光束法区域网平差的地面激光扫描多站点云自动定向方法[J]. 测绘学报, 2014, 43(7):711-716, 723. DOI:10.13485/j.cnki.11-2089.2014.0099. YAO Jili, MA Ning, JIA Xiangyang, et al. Auto-registration for terrestrial laser scanning multi-stations point clouds with bundle block adjustment method[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(7):711-716, 723. DOI:10.13485/j.cnki.11-2089.2014.0099.