Методы машинного обучения для построения трехмерных моделей антропогенных сцен
Диссертация
Согласно правилам перспективной проекции, проекции копланарных параллельных прямых пересекаются в одной точке на плоскости изображения, которая называется точкой схода. Точка схода задает направление прямых линий и соответствующих плоскостей в трехмерном пространстве. Если на изображении присутствуют несколько семейств параллельных линий, лежащих на разных плоскостях в трехмерном пространстве… Читать ещё >
Список литературы
- ВапникВ.Н. Восстановление зависимостей по эмпирическим данным М. Наука. 1979.
- Вапник В. Н., Червоненкис А. Я.: Теория распознавания образов. — М.: Наука, 1974.
- Воронцов К. В. Обзор современных исследований по проблеме качества обучения алгоритмов // Таврический вестник информатики и математики. — 2004.
- Воронцов К. В. Комбинаторные обоснования обучаемых алгоритмов // ЖВМиМФ. — 2004. — Т. 44, № 11. — С. 2099−2112.
- Воронцов К. В. Слабая вероятностная аксиоматика и надежность эмпирических предсказаний // Математические методы распознавания образов-13. — М.: МАКС Пресс, 2007. — С. 21−25.
- Воронцов К. В., ИнякинА. С., Лисица А. В. Система эмпирического измерения качества алгоритмов классификации // Математические методы распознавания образов-13.— М.: МАКС Пресс, 2007.— С. 577−580.
- Воронцов К.В. Оптимизационные методы линейной и монотонной коррекции в алгебраическом подходе к проблеме распознавания // ЖВМ и МФ. 2000. Т. 40, № 1.
- Воронцов, К. В. Комбинаторная теория надёжности обучения по прецедентам: Дис. док. физ.-мат. наук: 05−13−17.— Вычислительный центр РАН, 2010.
- Докукин А. А. Об одном методе построения оптимального алгоритма вычисления оценок // Журнал вычислительной математики и математической физики, 2006, № 4. С. 755−762.
- Журавлев Ю. И. Рудаков К.В. Об алгебраической коррекции процедур обработки (преобразования) информации // Проблемы прикладной математики и информатики. М. Наука, 1987. С. 187−198.
- И.Рудаков К. В. Полнота и универсальные ограничения в проблеме коррекции эвристических алгоритмов классификации // Кибернетика. 1987. № 3. с. 106- 109.
- Рудаков К.В., Воронцов К. В. О методах оптимизации и монотонной коррекции в алгебраическом подходе к проблеме распознавания // ДАН. 1999. Т. 367 № 3. С. 314−317
- Рязанов В.В. Комитетный синтез алгоритмов распознавания и классификации//ЖВМ и МФ. 1981. Т. 21, № 6 с. 1533−1543.
- Цюрмасто П. А., Воронцов К. В. Анализ сходства алгоритмов классификации в оценках обобщающей способности // Интеллектуализация обработки информации (ИОИ-2008): Тезисы докл. — Симферополь: КНЦ HAH Украины, 2008. — С. 232−234.
- Aguilera, D.G., Lahoz, J.G., Codes, J.F.: A new method for vanishing points detection in 3d reconstruction from a single view. // In: Proc. of ISPRS Commission V. (2005)
- Amit Y., Geman D., and Fan X. A coarse-to-fine strategy for multi-class shape detection. // In: TP AMI, 26(12):1606−1621, 2004.
- Andriluka M., Roth S., and Schiele В. People-tracking-by-detection and people-detection-by-tracking. // In: CVPR, 2008.
- Antone M.E., Teller S.J.: Automatic recovery of relative camera rotations for urban scenes. // In: CVPR. (2000) 2282−2289
- Almansa A., Desolneux A., Vamech S.: Vanishing point detection without any a priori information. // IEEE Trans. Pattern Anal. Mach. Intell. 25 (2003) 502−507
- Ballard D. H. Generalizing the hough transform to detect arbitrary shapes. // Pattern Recognition, 13(2):111−122, 1981.
- Barinova O., Kuzmishkina A., Vezhnevets A., Vezhnevets V.: Learning class specific edges for vanishing point estimation. // In Proc. of Graphicon (2007) 162−165
- Barinova O., Lempitsky V., and Kohli P. On detection of multiple object instances using hough transforms. //In: CVPR. (2010)
- Barnard, S.: Interpreting perspective images. //Artificial Intelligence 21 (1983)435−462
- Beardsley, P., Murray, D.: Camera calibration using vanishing points. // In: BMVC. (1992) 416−425
- Besag J.: On the statistical analysis of dirty pictures. // Journal of the Royal Statistical Society B-48 (1986) 259−302
- Bourdev L. and Malik J. Poselets: Body part detectors trained using 3d human pose annotations. // In. ICCV, 2009.
- Boser B.- Guyon I.- Vapnik, V. A training algorithm for optimal margin classifiers. // Fifth Annual Workshop on Computational Learning Theory. ACM Press, Pittsburgh, (1992).
- Blake C. L., & Merz C. J.: UCI repository of machine learning databases (1998)
- Breiman L.: Bagging Predictors. // Machine Learning, 24, 2, (1996) 123 140
- Breiman Leo (2001). Random Forests. // Machine Learning 45 (1): 5−32
- Canny J.: A Computational Approach To Edge Detection. // PAMI 8 (1986)
- Caruana R., Niculescu-Mizil A.: An Empirical Comparison of Supervised Learning Algorithms // Proceedings of the 23rd International Conference on Machine Learning (ICML «06).
- Collins M., Schapire R. E. and Singer Y.: Logistic regression, AdaBoost and Bregman distances. I I Machine Learning (2001)
- Cipolla R., Drummond T., Robertson D.P.: Camera calibration from vanishing points in image of architectural scenes. // In: BMVC. (1999)
- Chum O., Matas J., Kittler J.: Locally Optimized RANSAC. // DAGM Symposium on Pattern Recognition 25 (2003) 236−243
- Comaniciu D., Meer P.: Mean shift: A robust approach toward feature space analysis. // IEEE Trans, on Pattern Analysis and Machine Intelligence (2002) 24,5.
- Collins R., Weiss R.: Vanishing point calculation as a statistical inference on the unit sphere. // In: ICCV. (1990) 400−403
- Coughlan J.M., Yuille A.L.: Manhattan world: Compass direction from a single image by bayesian inference. // In: ICCV. (1999) 941−947
- Criminisi A., Reid I., Zisserman A.: Single view metrology. // IJCV, 40 (2000)
- Desai C. F, Ramanan D. Discriminative models for multi-class object layout. ICCV, 2009.
- Delage E., Lee H., Ng A.: Automatic single-image 3d reconstructions of indoor manhattan world scenes. // In Proc. of ISRR (2005)
- Delage, E., Lee, H., Ng, A.: A dynamic bayesian network model for autonomous 3d reconstruction from a single indoor image. // In Proc. of CVPR (2006)
- Deutscher, J., Isard, M., MacCormick, J.: Automatic camera calibration from a single manhattan image. // In: ECCV (4). (2002) 175−205
- Denis, P., Elder, J.H., Estrada, F.J.: Efficient edge-based methods for estimating manhattan frames in urban imagery. // In: ECCV (2). (2008) 197 210
- Duric, Z., Rosenfeld, A.: Image sequence stabilization in real time. // RealTime Imaging 2 (1996) 271−284
- Dietterich, T., G.: An experimental comparison of three methods for constructing ensembles of decision trees: Bagging, boosting, and randomization. // Machine Learning, 40 (2) (1999)
- Domingos, P.: A Unified Bias-Variance Decomposition for Zero-One and Squared Loss. // In Proc. of the 17th National Conference on Artificial Intelligence. (2000).
- Domingo C., Watanabe O.: Madaboost: A modication of adaboost. // In 13th Annual Conference on Comp. Learning Theory, (2000)
- Freund Y., Schapire R., A decision-theoretic generalization of on-line learning and an application to boosting. // Journal of Computer and System Sciences, no. 55. 1997
- Friedman, J., Hastie, T., & Tibshirani, R.: Additive Logistic Regression: a Statistical View of Boosting. // The Annals of Statistics, 28, 2, (2000) 337 407
- Friedman, J.: Greedy function approximation: A gradient boosting machine. //Annals of Statistics, 29, 5. (2001)
- Frey B. J. and Dueck D. Clustering by passing messages between data points. // Science, 315:972−976, 2007.
- Gall J. and Lempitsky V. Class-specific hough forests for object detection. // CVPR, 2009.
- Gu C., Lim J. J., Arbelaez P., and Malik J. Recognition using regions. // CVPR, 2009.
- Hoiem, D., Efros, A., Hebert, M.: Geometric context from a single image. // In Proc. oflCCV (2005)
- Hoiem, D., Sten, A.N., Efros A.A., Hebert, M.: Recovering Occlusion Boundaries from a Single Image. // In Proc. of ICCV (2007)
- Hoiem D., Rother C., and Winn J. M. 3d layoutcrf for multi-view object class recognition and segmentation. // CVPR, 2007.
- Hoiem, D., Efros, A.A., Hebert, M.: Automatic photo pop-up. // ACM Trans. Graph. 24 (2005) 577−584l.Hoiem, D., Efros, A.A., Hebert, M.: Putting objects in perspective. // International Journal of Computer Vision 80 (2008) 3−15
- Hough P. Machine analysis of bubble chamber pictures. // Int. Conf. High Energy Accelerators and Instrumentation, 1959.
- Hulse, J., Khoshgonaar, T., Napolitano, A.: Experimental perspectives on learning from imbalanced data. // In Proc. of ICML (2007) 935−942
- Kanevskiy D. Y., Vorontsov K. V. Cooperative revolutionary ensemble learning // Multiple Classifier Systems: 7th International Workshop, Prague, Czech Republic, May 23−25, 2007. — Lecture Notes in Computer Science. Springer-Verlag, 2007. — Pp. 469−478.
- Kang, H., Pyo, S., Anjyo, K., Shin, S.: Tour into the picture using a vanishing line and its extension to panoramic images. // In Proc. Eurographics (2001)132141.
- Kosecka, J., Zhang, W.: Video Compass. // In Proc. of ECCV 7 (2002) 476 491
- Kearns, M., Vazirani, U.: An Introduction to Computational Learning Theory. // MIT Press, 1994
- Kovesi P., Shapelets Correlated with Surface Normals Produce Surfaces. // 10th IEEE International Conference on Computer Vision. Beijing, pp 9 941 001.2005.
- Koutsourakis, P. Simon, L. Teboul, O. Tziritas, G. Paragios, N. Single view reconstruction using shape grammars for urban environments. // In. Proc. IEEE 12th International Conference on Computer Vision, 2009, pp. 1795 1802
- Langford J. and Blum A. Microchoice Bounds and Self Bounding learning algorithms. // COLT99, pages 209−214 (2002)
- Laferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. // In Proc. of ICML (2001)
- Lazic N., Givoni I., Frey B., and Aarabi P. Floss: Facility location for subspace segmentation. // ICCV, 2009.
- Leibe B., Leonardis A., and Schiele B. Robust object detection with interleaved categorization and segmentation. // IJCV, 77(l-3):259−289, 2008.
- Langford J., Seeger M., and Megiddo N. An Improved Predictive Accuracy Bound for Averaging Classifiers // In Proc ICML2001
- Langford J., Caruana R., (Not) Bounding the True Error // NIPS2001
- Langford J., Seeger M., Bounds for Averaging Classifiers // Technical report, Carnegie Mellon 2001
- Langford J. and McAllester D. Computable Shell Decomposition Bounds. // InJMLR
- Langford J. Combining Train Set and Test Set Bounds. // ICML2002
- McLean, G.F., Kotturi, D.: Vanishing point detection by line clustering. // IEEE Trans. Pattern Anal. Mach. Intell. 17 (1995) 1090−1095
- Mason L, Baxter J, Bartlett P, Frean M.: Boosting algorithms as gradient descent, // Neural Information Processing Systems 12, MIT Press, (2000) 512−518
- Nemhauser G. L. and Wolsey L. A. Best algorithms for approximating the maximum of a submodular set function. // Mathematics of operations research, 3(3): 177−188, 1978.
- Niculescu-Mizil, A., Caruana, R.: Obtaining Calibrated Probabilities from Boosting. // In Proc. of UAI (2005) 413−42 085.0kada. R. Discriminative generalized hough transform for object detection. //ICCV, 2009.
- Pearl. J. Probabilistic Reasoning in Intelligent Systems. // Morgan Kaufmann, Palo Alto, 1988.
- Perrone M.: Improving regression estimation: Averaging methods for Variance reduction with extension to General Convex Measure Optimization, // Ph.D. Thesis, Brown University, (1993)
- Ratsch. G.: Robust Boosting and Convex Optimization. // Doctoral dissertation, University of Potsdam, (2001)
- Reyzin, L., & Schapire, R.: How boosting the margin can also boost classifier complexity. // In Proceedings of the 23rd International Conference on Machine Learning (2006)
- Rosset S.: Robust Boosting and Its Relation to Bagging. // KDD-05 (2005)
- Rother, C.: A new approach for vanishing point detection in architectural environments. // In: BMVC. (2000)
- Robert E. Schapire, Marie Rochery, Mazin Rahim and Narendra Gupta. Incorporating prior knowledge into boosting. // In Machine Learning: Proceedings of the Nineteenth International Conference, 2002.
- Saxena, A., Sun, M., Ng, A.: Learning 3-D Scene Structure from a Single Still Image. // In Proc. of ICCV workshop on 3D representation for Recognition (2007)
- Saxena, A., Chung, S., Ng, A.: Depth Reconstruction from a Single Still Image. // IJCV (2007)
- Saxena, A., Chung, S., Ng, A.: Learning Depth from Single Monocular Images. //In Proc. of NIPS 18 (2005)
- Schindler, G., Dellaert, F.: Atlanta world: An expectation maximization framework for simultaneous low-level edge grouping and camera calibration in complex man-made environments. // In: CVPR (1). (2004) 203−209
- Sutton, C., McCallum, A.: Piecewise training of undirected models. // In Proc. of UAI 21 (2005)
- Sheikh Y., Khan E. A., and Kanade T. Mode-seeking by medoid-shifts. // ICCV, 2007.
- Shotton, J., Winn, J., Rother, C., Criminisi, A.: TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context. IJCV (2007)
- Schapire, R., Freund, Y., Bartlett, P., and Wee Sun Lee.: Boosting the margin: A new explanation for the effectiveness of voting methods. // In Machine Learning: Proceedings of the Fourteenth International Conference (1997)
- Schapire, R. and Singer, Y.: Improved Boosting Algorithms Using Confidence-rated Predictions, // In Machine Learning, 37(3):297−336, 1999
- Schapire R, Rochery M, Rahim M., Gupta N. Incorporating prior knowledge into boosting, // In Machine Learning, 2002
- Taniguchi M, Tresp V.: Averaging Regularized Estimators, // In Neural Computation (1997)
- Tardif, J.P.: Non-iterative approach for fast and accurate vanishing point detection. // In: ICCV. (2009)
- A. Torralba and A. Oliva. Depth estimation from image structure. // IEEE Trans Pattern Analysis and Machine Intelligence (PAMI), 24(9): 1−13, 2002.
- Tuytelaars, T., Gool, L.J.V., Proesmans, M., Moons, T.: A cascaded hough transform as an aid in aerial image interpretation. // In: ICCV. (1998) 67−72
- Tu, Z., Chen, X., Yuille, A.L., Zhu, S.C.: Image parsing: Unifying segmentation, detection, and recognition. // International Journal of Computer Vision 63 (2005) 113−140
- Vezhnevets, V., Konushin, A., Ignatenko, A.: Interactive image-based urban modeling. // In Proc. of PIA (2007) 63−68
- Viola, P., Jones, M.: Robust Real-time Object Detection. // IJCV (2001)
- Vezhnevets A, Barinova O.: Avoiding boosting overfitting by removing confusing samples, // In Proc. Of European Conference on Machine Learning (2007)
- Vorontsov K. V. Combinatorial probability and the tightness of generalization bounds // Pattern Recognition and Image Analysis. — 2008. — Vol. 18, no. 2. — Pp. 243−259.
- Wasserman, L.: All of Nonparametric Statistics. // Springer, 2006.
- Winn J. M. and Shotton J. The layout consistent random field for recognizing and segmenting partially occluded objects. // CVPR (1), pp. 3744, 2006.