AUTHORS: Artem Kruglov, Yuriy Chiryshev

Download as PDF

ABSTRACT: This paper is devoted to the investigation and development of the algorithm for the log pile photogrammetry measurement on the basis of abuts detection and calculation of their diameters. The algorithm of abuts contours detection and refinement relies on the modified radial symmetry object detection algorithm. The combination of the following methods is implemented at the further stages of the pile measurement algorithm: meanshift clustering, Delaunay triangulation, Boruvka's minimum spanning tree algorithm, watershed and Boykov-Kolmogorov graph cut algorithm. These methods were adapted to the specific of the given task. The testing of the resulting algorithm gives its TPR value at 96,2% which is much higher than other unsupervised training methods. The average error of the algorithm for the log pile photogrammetry measurement in comparison with manual measurement is less than 9.2%. It meets the requirements of the industry standards so the method of the log piles photogrammetry measurement using the developed algorithm can be successfully applied in the activity of forest enterprises.

KEYWORDS: Log pile, Photogrammetry, Abut detection, Radial symmetry, Meanshift clustering, Graph cut, Watershed, Volume measurement

REFERENCES:

[1] Nikolaev D.P., Kotov A.A., Usilin S.A., Postroenie ustoychivykh priznakov dlya algoritma Violy i Dzhonsa v zadache klassifikatsii transportnykh sredstv // Trudy 35- oy konferentsii molodykh uchenykh i spetsialistov «Informatsionnye tekhnologii i sistemy (ITiS’ 12)». Petrozavodsk, 2012. M.: IPPI RAN, 2012. pp. 383-388

[2] Buy TkhiTkhuChang, Fan Ngok Khoang, Spitsyn V. G., Raspoznavanie lits na osnove primeneniya metoda Violy-Dzhonsa, veyvletpreobrazovaniya i metoda glavnykh komponent // Izvestiya Tomskogo politekhnicheskogo universiteta

[Izvestiya TPU], 2012. T. 320, № 5: Upravlenie, vychislitel'naya tekhnika i informatika. pp. 54-59.

[3] Andreeva A.A., Ivanov A.L., Obnaruzhenie litsa na izobrazhenii v avtomatizirovannykh sistemakh gabitoskopicheskoy identifikatsii // Vestnik chuvashskogo universiteta, 2006, Cheboksary, № 2, pp. 316-322

[4] Murav'ev V.S., Murav'ev S.I. Adaptivnyy algoritm vydeleniya i obnaruzheniya vozdushnykh ob'ektov na izobrazheniyakh // Informatsionno-upravlyayushchie sistemy, 2011. SPb., № 5, s. 8-14

[5] Chochia P. A. Piramidal'nyy algoritm segmentatsii izobrazheniy // Informatsionnye protsessy. 2010. T. 10, № 1. S. 23–35

[6] Dasgupta S., Das S., Biswas A., Abraham A., Automatic circle detection on digital images with an adaptive bacterial foraging algorithm // Soft. Computing 14 (11), 2009, pp. 1151-1164

[7] Mishustin S.M., Issledovanie algoritma BFOA v ramkakh zadachi raspoznavaniya prostykh figur na izobrazhenii // Materialy IV mezhdunarodnoy nauchno-tekhnicheskoy konferentsii studentov, aspirantov i molodykh uchenykh, Donetsk, DonNTU, 2013

[8] Sadykov S.S., Terekhin A.V., Algoritm klassifikatsii vypuklykh figur s ispol'zovaniem diagonal'nykh priznakov formy // Vestnik KGU im. N.A. Nekrasova. 2013, №6, pp. 13-17.

[9] Minkina A., Grigor'ev A., Usilin S., Polevoy D., Nikolaev D.. Obobshchenie metoda Violy i Dzhonsa v vide reshayushchego dereva sil'nykh klassifikatorov dlya raspoznavaniya ob'ektov v videopotoke v rezhime real'nogo vremeni // Informatsionnye tekhnologii i sistemy. Sbornik trudov. 2014. pp. 303-307.

[10] Turker M., Koc-San D., Building extraction from high-resolution optical spaceborne images using the integration of support vector machine (SVM) classification, Hough transformation and perceptual grouping. // Int. J. Applied Earth Observation and Geoinformation Vol. 34, pp. 58-69, 2015

[11] Kotov A., Nikolaev D., Proslezhivanie v videopotoke ob'ektov, soderzhashchikh mnozhestvo kontsentricheskikh dug URL: http://itas2012.iitp.ru/pdf/1569605095.pdf (access date 21.02.2017)

[12] Hahn K-S., Jung S., Han Y., Hahn H., A new algorithm for ellipse detection by curve segments // Pattern Recognition Letters vol. 29(13): pp. 1836-1841, 2008

[13] F. Mai, Y. S. Hung, H. Zhong, W. F. Sze, A hierarchical approach for fast and robust ellipse extraction, Pattern Recognition, vol. 41, no. 8, pp. 2512–2524, 2008

[14] De Marco T., Cazzato, D., Marco L., Cosimo D., Randomized circle detection with isophotes curvature analysis // Pattern Recognition, vol. 48 (2), pp.411-421, 2015

[15] Rad A.A., Faez K., Qaragozlou N., Fast circle detection using gradient pair vectors // In Proceedings of the Seventh International Conference on DICTA, pp. 10-12, 2003

[16] Yin P., Chen L., New method for ellipse detection by means for symmetry // Journal of Electronic Imaging. vol. 3(1), pp. 20-29, 1994

[17] Cheng H.D., Guo Y., Zhang Y., A novel Hough transform based on eliminating particle swarm optimization and its applications // Pattern Recognition, vol. 42 (9), pp. 1959- 1969, 2009

[18] Cauchie J., Fiolet V., Villers D., Optimization of an Hough transform algorithm for the search of a center // Pattern Recognition vol. 41(2): pp. 567-574, 2008

[19] Mochizuki Y., Torii A., Imiya A., N-Point Hough transform for line detection. // J. Visual Communication and Image Representation, vol. 20(4): pp. 242-253, 2009

[20] Fornaciari M., Prati A., Cucchiara R., A fast and effective ellipse detector for embedded vision applications // Pattern Recognition vol. 47(11) pp. 3693–3708, 2014

[21] Pan L., Chu W.S., SaragihJ.M., De la Torre F., Xie M., Fast and Robust Circular Object Detection with Probabilistic Pairwise Voting (PPV) // IEEE Signal Processing Letters, vol. 18, no. 11, pp. 639-642, 2011

[22] Šukilović T., Curvature based shape detection // Computational Geometry, vol. 48 (3), pp. 180-188, 2015

[23] Ioannou D., Huda W., LaineA.F., Circle recognition through a 2D Hough Transform and radius histogramming // Image and Vision Computing 17 (1), pp. 15-26, 1999

[24] HassaneinA.S., Mohammad S., Sameer M., Ragab M.E., A Survey on Hough Transform, Theory, Techniques and Applications. CoRR abs, pp. 1-18, 2015

[25] Prasad D.K., Leung M.K.H., Cho S.Y., Edge curvature and convexity based ellipse detection method // Pattern Recognition, vol. 45(9):pp. 3204-3221, 2012

[26] Lebedev S.A., Ososkov G.A., Bystrye algoritmy raspoznavaniya kolets i identifikatsii elektronov v detektore RICH eksperimenta SVM // Pis'ma v EChAYa. 2009. T. 6, № 2(151). pp. 260-284.

[27] Marin D., Gegundez-Arias M.E., Suero A., Bravo J.M., Obtaining optic disc center and pixel region by automatic thresholding methods on morphologically processed fundus images // Proceedings Of Computer Methods And Programs In Biomedicine, Elsevier, Vol.118, No.2, Page No.173-185, 2014.

[28] Lu W., Tan J., Detection of incomplete ellipse in images with strong noise by iterative randomized hough transform (IRHT) // Pattern Recognition, vol. 41, no. 4, pp. 1268 – 1279, 2008

[29] Kierkegaard P., A method for detection of circular arcs based on the Hough transform // Machine Vision and Applications, vol. 5 (4), pp. 249-263, 1992

[30] Marr D. Zrenie: Informatsionnyy podkhod k izucheniyu predstavleniya i obrabotki zritel'nykh obrazov. M., «Radio i svyaz'». 1987

[31] Damien Rj., The mean shift clustering algorithm // EFAVDB, URL: http://efavdb.com/mean-shift/#Tech (датаобращения 21.02.2017)

[32] Loy, G., Zelinsky, A., Fast radial symmetry for detecting points of interest // IEEE Transactions on PAMI, vol. 25, no. 8, 2003, pp. 959-973

[33] Comaniciu D., Meer P., Mean Shift: A Robust Approach Toward Feature Space Analysis // In IEEE Transactions on PAMI, vol. 24 No 5, pp. 603-619, 2002

[34] Mandel' I.D., Klasternyy analiz. M.: Finansy i Statistika, 1988, 186 p.

[35] Skvortsov A.V. Triangulyatsiya Delone i ee primenenie // Tomsk: Izd-vo Tom. un-ta, 2002. – 128 p.

[36] Skvortsov A.V., Mirza N.S., Algoritmy postroeniya i analiza triangulyatsii. – Tomsk: Izd- vo Tom.un-ta, 2006. – 168 p.

[37] Erzin A. I., Kochetov Yu. A., Zadachi marshrutizatsii : ucheb. posobie / Novosib. gos. un-t. – Novosibirsk :RITsNGU, 2014. – 95 p.

[38] Shapiro L., Stokman Dzh., Komp'yuternoe zrenie // M.: BINOM. Laboratoriya znaniy 2006, 752 p.

[39] Gonsales R., Vuds R., Tsifrovaya obrabotka izobrazheniy // M: Tekhnosfera, 2005, 1072 p.

[40] Forsayt D., Pons Zh., Komp'yuternoe zrenie. Sovremennyy podkhod // M.: Izdatel'skiy dom «Vil'yams», 2004, 928 p.

[41] Chen H., Introduction to Min-Cut/Max-Flow Algorithms // UCLA CIVS, URL: http://perso.telecomparistech.fr/~tupin/cours/matim/articles/theorie _gra.pdf (датаобращения 21.02.2017)

[42] Algoritmy minimizatsii energii na osnove razrezov grafov // URL: http://www.machinelearning.ru/wiki/images/9/ 9e/GM_graphCuts.pdf (access date: 21.02.2017)

[43] RoerdinkJ.B.T.M., Meijster A., The Watershed Transform: Definitions, Algorithms and Parallelization Strategies // FundamentaInformaticae, vol. 41, IOS Press, pp. 187–228, 2001

[44] Boykov Y., Kolmogorov V., An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision // In IEEE Transactions on PAMI, vol. 26, No. 9, pp. 1124-1137, 2004

[45] Breiman L. Random forests // Machine Learning, 45(1): 5–32, 2001.

[46] Dalal N., Triggs B. Histograms of oriented gradients for human detection // IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), San Diego, CA, USA, 2005, pp. 886-893 vol. 1.

[47] Déniz O., Bueno G., Salido J., De la Torre F. Face recognition using Histograms of Oriented Gradients // Pattern Recogn. Lett. 32, 12 (September 2011), 1598-1603.

[48] Galsgaard B., Lundtoft D.H., Nikolov I., Nasrollahi K., Moeslund T.B. Circular Hough Transform and Local Circularity Measure for Weight Estimation of a Graph-Cut Based Wood Stack Measurement // IEEE Winter Conference on Applications of Computer Vision, Waikoloa, HI, 2015, pp. 686-693.

[49] Gutzeit E., Voskamp J. Automatic segmentation of wood logs by combining detection and segmentation // International Symposium on Visual Computing. pp. 252–261 (2012).

[50] Herbon C., Tönnies K., Stock B. Detection and segmentation of clustered objects by using iterative classification, segmentation, and Gaussian mixture models and application to wood log detection // Pattern Recognition. Springer International Publishing, (2014), pp. 354-364.

[51] Herbon С. The HAWKwood Database // CoRR abs/1410.4393 (2014): n. pag.

[52] Knyaz V.A., Maksimov A.A. Photogrammetric Technique for Timber Stack Volume Contol // International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. XL-3, 157-162, 2014.

[53] Knyaz V.A., Vizilter Yu.V., Zheltov S.Yu. Photogrammetric techniques for measurements in woodworking industry // International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences Proceedings, Vol. XXXIII, part B5/2, pp. 42- 47, 2004.

[54] Misra A., Takashi A., Okatani T., Deguchi K. Hand Gesture Recognition Using Histogram of Oriented Gradients and Partial Least Squares Regression // MVA2011, IAPR Conference on Machine Vision Applications; 2011; Nara, Japan.

[55] Mullin M., Sukthankar R. Complete CrossValidation for Nearest Neighbor Classifiers // Proceedings of International Conference on Machine Learning. 2000. pp. 1137-1145.

[56] Ojala T., Pietikainen M., Harwood D. Performance evaluation of texture measures with classification based on Kullback discrimination of distributions // Proceedings of the 12th IAPR International Conference on Pattern Recognition, 1994, vol. 1 - Conference A: Computer Vision & Image Processing, vol. 1, pp. 582–585, Oct 1994.

[57] Viola P., Jones M. Rapid object detection using a boosted cascade of simple features // Proc. Int. Conf. on Computer Vision and Pattern Recognition. 2001. № 1. P. 511−518.

[58] Wang X., Doretto G., Sebastian T.B., Rittscher J., Tu P.H. Shape and Appearance Context Modeling // Proceedings of IEEE International Conference on Computer Vision (ICCV) 2007.