Abstract
Object detection, recognition and pose estimation in 3D images have gained momentum due to availability of 3D sensors (RGB-D) and increase of large scale 3D data, such as city maps. The most popular approach is to extract and match 3D shape descriptors that encode local scene structure, but omits visual appearance. Visual appearance can be problematic due to imaging distortions, but the assumption that local shape structures are sufficient to recognise objects and scenes is largely invalid in practise since objects may have similar shape, but different texture (e.g., grocery packages). In this work, we propose an alternative appearance-driven approach which first extracts 2D primitives justified by Marr’s primal sketch, which are “accumulated” over multiple views and the most stable ones are “promoted” to 3D visual primitives. The 3D promoted primitives represent both structure and appearance. For recognition, we propose a fast and effective correspondence matching using random sampling. For quantitative evaluation we construct a semi-synthetic benchmark dataset using a public 3D model dataset of 119 kitchen objects and another benchmark of challenging street-view images from 4 different cities. In the experiments, our method utilises only a stereo view for training. As the result, with the kitchen objects dataset our method achieved almost perfect recognition rate for \(\pm 10^\circ \) camera view point change and nearly 80 % for \(\pm 20^\circ \), and for the street-view benchmarks it achieved 75 % accuracy for 160 street-view images pairs, 80 % for 96 street-view images pairs, and 92 % for 48 street-view image pairs.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Object retrieval with large vocabularies and fast spatial matching. In: CVPR (2007)
Chum, O., Matas, J.: Unsupervised discovery of co-occurrence in sparse high dimensional data. In: CVPR (2010)
Rodola, E., Albarelli, A., Bergamasco, F., Torsello, A.: A scale independent selection process for 3d object recognition in cluttered scenes. Int. J. Comput. Vis. 102, 129–145 (2013)
As’ari, M., Supriyanto, U.S.E.: 3d shape descriptor for object recognition based on kinect-like depth image. Image Vis. Comput. 32, 260–269 (2014)
Buch, A., Yang, Y., Krüger, N., Petersen, H.: In search of inliers: 3d correspondence by local and global voting. In: CVPR (2014)
Marr, D.: Vision. A Computational Investigation into the Human Representation and Processing of Visual Information. W.H. Freeman and Company, New York (1982)
Kalkan, S., Wörgötter, F., Krüger, N.: Statistical analysis of local 3d structure in 2d images. In: CVPR (2006)
Glasner, D., Galun, M., Alpert, S., Basri, R., Shakhnarovich, G.: Viewpoint-aware object detection and pose estimation. In: ICCV (2011)
Sattler, T., Leibe, B., Kobbelt, L.: Fast image-based localization using direct 2d-to-3d matching. In: ICCV (2011)
Zia, M., Stark, M., Schiele, B., Schindler, K.: Detailed 3d representations for object recognition and modeling. IEEE PAMI 35, 2608–2623 (2013)
Dorai, C., Jain, A.: Shape spectrum based view grouping and matching of 3D free-form objects. T-PAMI 19, 1139–1145 (1997)
Fayad, J., Russell, C., Agapito, L.: Automated articulated structure and 3D shape recovery from point correspondences. In: ICCV (2011)
Sharma, A., Horaud, R., Cech, J., Boyer, E.: Topologically-robust 3D shape matching based on diffusion geometry and seed growing. In: CVPR (2011)
Bronstein, A., Bronstein, M., Kimmel, R.: Three-dimensional face recognition. Int. J. Comput. Vis. 64, 5–30 (2005)
Gökberg, B., Irfanoglu, M., Akarun, L.: 3D shape-based face representation and feature extraction for face recognition. Image Vis. Comput. 24, 857–869 (2006)
Papazov, C., Burschka, D.: An efficient RANSAC for 3D object recognition in noisy and occluded scenes. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010, Part I. LNCS, vol. 6492, pp. 135–148. Springer, Heidelberg (2011)
Drost, B., Ulrich, M., Navab, N., Ilic, S.: Model globally, match locally: Efficient and robust 3D object recognition. In: CVPR (2010)
Detry, R., Pugeault, N., Piater, J.: A probabilistic framework for 3D visual object representation. T-PAMI 31, 1790–1803 (2009)
Baseski, E., Pugeault, N., Kalkan, S., Kraft, D., Wörgötter, F., Krüger, N.: A scene representation based on multi-modal 2d and 3d features. In: ICCV Workshop on 3D Representation for Recognition (2007)
Knopp, J., Prasad, M., Willems, G., Timofte, R., Van Gool, L.: Hough transform and 3D SURF for robust three dimensional classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part VI. LNCS, vol. 6316, pp. 589–602. Springer, Heidelberg (2010)
Tombari, F., Salti, S., Di Stefano, L.: Unique signatures of histograms for local surface description. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part III. LNCS, vol. 6313, pp. 356–369. Springer, Heidelberg (2010)
Pham, M.T., Woodford, O., Perbert, F., Maki, A., Stenger, B., Cipolla, R.: A new distance for scale-invariant 3D shape recognition and registration. In: ICCV (2011)
Zaharescu, A., Boyer, E., Horaud, R.: Keypoints and local descriptors of scalar functions on 2d manifolds. Int. J. Comput. Vis. 100, 78–98 (2012)
Bo, L., Lai, K., Ren, X., Fox, D.: Object recognition with hierarchical kernel descriptors. In: CVPR (2011)
Sun, J., Ovsjanikov, M., Guibas, L.: A concise and provably informative multi-scale signature based on heat diffusion. In: Eurographics Symposium on Geometry Processing (2009)
Bronstein, A., Bronstein, M., Guibas, L., Ovsjanikov, M.: Shape google: geometric words and expressions for invariant shape retrieval. ACM Trans. Graph. 30, 1–20 (2011)
Ahmed, N., Theobalt, C., Rössl, C., Thrun, S., Seidel, H.P.: Dense correspondence finding for parameterization-free animation reconstruction from video. In: CVPR (2008)
Mian, A., Bennamoun, M., Owens, R.: On the repeatability and quality of keypoints for local feature-based 3D object retrieval from cluttered scenes. Int. J. Comput. Vis. 89, 348–361 (2010)
Lee, S., Lu, Z., Kim, H.: Probabilistic 3D object recognition with both positive and negative evidences. In: ICCV (2011)
Hu, W., Zhu, S.C.: Learning a probabilistic model mixing 3d and 2d primitives for view invariant object recognition. In: CVPR (2010)
Kang, H., Hebert, M., Kanade, T.: Discovering object instances from scenes of daily living. In: ICCV (2011)
Krüger, N., Janssen, P., Kalkan, S., Lappe, M., Leonardis, A., Piater, J., Rodriguez-Sanchez, A., Wiskott, L.: Deep hierarchies in the primate visual cortex: what can we learn for computer vision? IEEE PAMI 35, 1847–1871 (2013)
Fidler, S., Boben, M., Leonardis, A.: Similarity-based cross-layered hierarchical representation for object categorization. In: CVPR (2008)
Mutch, J., Lowe, D.: Object class recognition and localization using sparse features with limited receptive fields. Int. J. Comput. Vis. 80, 45–57 (2008)
Pugeault, N., Wörgötter, F., Krüger, N.: Accumulated visual representation for cognitive vision. In: BMVC (2008)
Chaudhuri, B., Sarkar, N.: Texture segmentation using fractal dimension. T-PAMI 17, 72–76 (1995)
Felsberg, M., Sommer, G.: Image features based on a new approach to 2D rotation invariant quadrature filters. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part I. LNCS, vol. 2350, pp. 369–383. Springer, Heidelberg (2002)
Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2003)
Chum, O., Matas, J.: Optimal randomized RANSAC. T-PAMI 30, 1472–1482 (2008)
Umeyama, S.: Least-squares estimation of transformation parameters between two point patterns. T-PAMI 13, 376–380 (1991)
Xue, Z., Kasper, A., Zoellner, J., Dillmann, R.: An automatic grasp planning system for service robots. In: ICAR (2009)
Frome, A., Huber, D., Kolluri, R., Bülow, T., Malik, J.: Recognizing objects in range data using regional point descriptors. In: Pajdla, T., Matas, J.G. (eds.) ECCV 2004. LNCS, vol. 3023, pp. 224–237. Springer, Heidelberg (2004)
Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape context. T-PAMI 24, 509–522 (2002)
Acknowledgement
The authors would like to give thanks to Dr. Lixin Fan for the valuable discussions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Fu, J., Kämäräinen, JK., Buch, A.G., Krüger, N. (2015). Indoor Objects and Outdoor Urban Scenes Recognition by 3D Visual Primitives. In: Jawahar, C., Shan, S. (eds) Computer Vision - ACCV 2014 Workshops. ACCV 2014. Lecture Notes in Computer Science(), vol 9008. Springer, Cham. https://doi.org/10.1007/978-3-319-16628-5_20
Download citation
DOI: https://doi.org/10.1007/978-3-319-16628-5_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16627-8
Online ISBN: 978-3-319-16628-5
eBook Packages: Computer ScienceComputer Science (R0)