AUTHORS: Marton Szemenyei, Ferenc Vajda

Download as PDF

ABSTRACT: Graphical object representation is fequently used for visual object recognition and detection methods. Since most machine learning methods requira vectorial input, significant research has been done on assigning feature vectors to graphs - a process known as graph embedding. However, when one wishes to detect objects in a larger scene, it is a more viable strategy to assign feature vectors to graph nodes, and classify them individually. In this paper, we present a graph node embedding algorithm for 3D object detection based on primitive shape graphs. Our embedding algorithm encodes the local context of the selected node into the feature vector, thus improving the classification accuracy of nodes. The method also imposes no restriction on the structure of the graphs or the weights on the nodes and edges. The method presented here will be used as part of an intelligent object pairing algorithm for Tangible Augmented Reality.

KEYWORDS: Artificial Intelligence, Shape Recognition, Graph Embedding, Object Detection, Augmented Reality

REFERENCES:

[1] L.-J. Li, R. Socher and L. Fei-Fei, “Towards Total Scene Understanding:Classification, Annotation and Segmentation in an Automatic Framework”, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2009.

[2] C. Wojek, S. Walk, S. Roth, K. Schindler and B. Schiele, “Monocular Visual Scene Understanding: Understanding Multi-Object Traffic Scenes”, IEEE Transactions on Pattern Analysis and Machine Intelligence 35(4), pp. 882-897 (2012).

[3] O. Pauly, B. Diotte, P. Fallavollita, S. Weidert, E. Euler and N. Navab, “Machine learning-based augmented reality for improved surgical scene understanding”, Computerized Medical Imaging and Graphics 41(1), pp. 55-60 (2015).

[4] M. Billinghurst, H. Kato and I. Poupyrev, “Tangible Augmented Reality”, in ACM SIGGRAPH ASIA, 2008.

[5] M. Billinghurst, H. Kato and S. Myojin, “Advanced Interaction Techniques for Augmented Reality Applications”, in Lecture Notes in Computer Science, Springer, 2009, pp. 13-22.

[6] G. A. Lee, M. Billinghurst and G. J. Kim, “Occlusion based Interaction Methods for Tangible Augmented Reality Environments”, Proceedings of the 2004 ACM SIGGRAPH international conference on Virtual Reality continuum and its applications in industry, 2004.

[7] W. Broll, E. Meier and T. Schardt, “The Virtual Round Table - a Collaborative Augmented Multi-User Environment”, Proceedings of the ACM Collaborative Virtual Environments, 2000.

[8] R. Schnabel, R. Wahl, R. Wessel and R. Klein, “Shape Recognition in 3D Point Clouds”, Proceedings of the 16-th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, 2008.

[9] R. Osada, T. Funkhouser, B. Chazelle and Dobkin David, “Matching 3D Models with Shape Distributions”, SMI 2001 International Conference on Shape Modeling and Applications, 2001.

[10] F. Tombari and L. Di Stefano, “Object recognition in 3D scenes with occlusions and clutter by Hough voting”, Fourth Pacific-Rim Symposium on Image and Video Technology, 2010.

[11] M. A. Fishler and R. C. Bolles, “Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography,”, Magazine Communications of the ACM, 24(6), pp. 381-395 (1981).

[12] R. Rusu, N. Blodow and M. Beetz, “Fast Point Feature Histograms (FPFH) for 3D Registration”, Proceedings of the IEEE International Conference on Robotics and Automation, Kobe, 2009.

[13] S. Lazebnik, C. Schmid and J. Ponce, “A sparse texture representation using local affine regions”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(1), pp. 1265-1278 (2005).

[14] A. Golonivskiy, V. G. Kim and T. Funkhouser, “Shape-based Recognition of 3D Point Clouds in Urban Environments”, IEEE 12th International Conference on Computer Vision, 2009.

[15] C. Szegedy, W. Liu and Y. Jia, “Going deeper with convolutions”, IEEE Conference on Computer Vision and Pattern Recognition, 2015.

[16] C. Wu, I. Lenz and A. Saxena, “Hierarchical Semantic Labeling for Task-Relevant RGB-D Perception”, Robotics: Science and Systems, 2014.

[17] M. Schwarz, H. Schulz and S. Behnke, “RGB-D Object Recognition and Pose Estimation based on Pre-trained Convolutional Neural Network Features”, Proceedings of the IEEE International Conference on Robotics and Automation, Seattle, 2015.

[18] Z. Wu, S. Song, A. Khosla, L. Z. F. Yu, X. Tang and J. Xiao, “3D ShapeNets: A Deep Representation for Volumetric Shape Modeling”, Proceedings of 28th IEEE Conference on Computer Vision and Pattern Recognition, 2015.

[19] S. Bai, X. Bai, Z. Zhou, Z. Zhang and L. J. Latecki, “GIFT: A Real-time and Scalable 3D Shape Search Engine”, Proceedings of 29th IEEE Conference on Computer Vision and Pattern Recognition, 2016.

[20] S. Gupta, R. Girshick, P. Arbelaez and J. Malik, “Learning Rich Features from RGB-D Images for Object Detection and Segmentation”, European Conference on Computer Vision, 2014.

[21] Y. Bengio, “Practical Recommendations for Gradient-Based Training of Deep Architectures”, Neural Networks: Tricks of the Trade, Springer, 2012, pp. 437-478.

[22] L. Bottou, “Stochastic Gradient Descent Tricks”, Neural Networks, Tricks of the Trade, Reloaded, Srpinger, 2012, p. 430445.

[23] R. Schnabel, R. Wahl and R. Klein, “Efficient RANSAC for Point-Cloud Shape Detection”, Computer Graphics Forum, 26(2), pp. 214-226 (2007).

[24] Roded Sharan and Trey Ideker, “Modeling cellular machinery through biological network comparison”, Nature Biotechnology, 24(4), pp. 427433 (2006)

[25] Ravi Kumar, Jasmine Novak, and Andrew Tomkins, “Structure and evolution of online social networks”, Proceedings of the Twelfth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2006

[26] R. C. Wilson, E. R. Hancock and B. Luo, “Pattern vectors from algebraic graph theory”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(7), pp. 11121124 (2005).

[27] S. V. N. Vishwanathan, N. N. Schraudolph, R. Kondor and K. M. Borgwardt, “Graph Kernels”, Journal of Machine Learning, 11(1), pp. 1201- 1242 (2010).

[28] F. Chung, Spectral graph theory, American Mathematical Society, 1997.

[29] M. Ferrer, F. Serratosa and A. Sanfeliu, “Synthesis of median spectral graph”, Lecture Notes in Computer Science, 3523(1), pp. 139146 (2005).

[30] D. White and R. C. Wilson, “Mixing Spectral Representations of Graphs”, Proceedings of the 18th International Conference on Pattern Recognition, 2006.

[31] P. Zhu and R. C. Wilson, “Stability of the Eigenvalues of Graphs”, 11th International Conference, CAIP 2005, 2005.

[32] M. F. Demirci, Y. Osmanlioglu, A. Shokoufandeh and S. Dickinson, “Efficient many-to-many feature matching under the l1 norm”, Journal of Computer Vision and Image Understanding, 115(7), pp. 976-983 (2011).

[33] P. Riba, J. Llados, A. Fornes and A. Dutta, “Large-scale Graph Indexing using Binary Embeddings of Node Contexts”, Proceedings of the 10th IAPR-TC-15 International Workshop, 2015.

[34] Changchang Wu, “Towards Linear-time Incremental Structure From Motion”, International Conference on 3DTV, 2013