Abstract
We propose an approach for view-invariant object detection directly in 3D with following properties: (i) The detection is based on matching of 3D contours to 3D object models. (ii) The matching is constrained with qualitative spatial relations such as above/below, left/right, and front/back. (iii) In order to ensure that any matching solution satisfies these constraints, we formulate the matching problem as finding maximum weight subgraphs with hard constraints, and utilize a novel inference framework to solve this problem. Given a single view of an RGB-D camera, we obtain 3D contours by ”back projecting” 2D contours extracted in the depth map. As our experimental results demonstrate, the proposed approach significantly outperforms the state-of-the-art 2D approaches, in particular, latent SVM object detector, as well as recently proposed approaches for object detection in RGB-D data.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Barrow, H., Tenenbaum, J.: Interpreting line drawings as three-dimensional surfaces. Artificial Intelligence 17, 75–116 (1981)
Lowe, D.G.: Three-dimensional object recognition from single two-dimensional images. Artificial Intelligence 31(3), 355–395 (1987)
Ferrari, V., Jurie, F., Schmid, C.: From images to shape models for object detection. International Journal of Computer Vision 87, 284–303 (2010)
Shotton, J., Blake, A., Cipolla, R.: Multiscale categorical object recognition using contour fragments. IEEE Trans. Pattern Anal. Mach. Intell. 30, 1270–1281 (2008)
Opelt, A., Pinz, A., Zisserman, A.: Learning an alphabet of shape and appearance for multi-class object detection. International Journal of Computer Vision 80, 16–44 (2008)
Bo, L., Lai, K., Ren, X., Fox, D.: Object recognition with hierarchical kernel descriptors. In: CVPR, pp. 1729–1736 (2011)
Stiene, S., Lingemann, K., Nuchter, A., Hertzberg, J.: Contour-based object detection in range image. In: Third International Symposium on 3D Data Processing, Visualization and Transmission (2006)
Drost, B., Ulrich, M., Navab, N., Ilic, S.: Model globally, match locally: Efficient and robust 3d object recognition. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 998–1005 (2010)
Hinterstoisser, S., Holzer, S., Cagniart, C., Ilic, S., Konolige, K., Navab, N., Lepetit, V.: Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes. In: IEEE International Conference on Computer Vision, pp. 858–865 (2011)
Ponce, J., Lazebnik, S., Rothganger, F., Schmid, C.: Toward true 3d object recognition. In: Congres de Reconnaissance des Formes et Intelligence Artificielle (2004)
Ferrari, V., Tuytelaars, T., Van Gool, L.J.: Integrating multiple model views for object recognition. In: CVPR, pp. 105–112 (2004)
Thomas, A., Ferrari, V., Leibe, B., Tuytelaars, T., Schiele, B., Van Gool, L.J.: Towards multi-view object class detection. In: CVPR, pp. 1589–1596 (2006)
Leibe, B., Leonardis, A., Schiele, B.: An Implicit Shape Model for Combined Object Categorization and Segmentation. In: Ponce, J., Hebert, M., Schmid, C., Zisserman, A. (eds.) Toward Category-Level Object Recognition. LNCS, vol. 4170, pp. 508–524. Springer, Heidelberg (2006)
Savarese, S., Li, F.F.: 3d generic object categorization, localization and pose estimation. In: ICCV, pp. 1–8 (2007)
Sun, M., Su, H., Savarese, S., Li, F.F.: A multi-view probabilistic model for 3d object classes. In: CVPR, pp. 1247–1254 (2009)
Liebelt, J., Schmid, C.: Multi-view object class detection with a 3d geometric model. In: CVPR, pp. 1688–1695 (2010)
Yan, P., Khan, S.M., Shah, M.: 3d model based object class detection in an arbitrary view. In: ICCV, pp. 1–6 (2007)
Arie-Nachimson, M., Basri, R.: Constructing implicit 3d shape models for pose estimation. In: ICCV, pp. 1341–1348 (2009)
Payet, N., Todorovic, S.: From contours to 3d object detection and pose estimation. In: ICCV, pp. 983–990 (2011)
Janoch, A., Karayev, S., Jia, Y., Barron, J.T., Fritz, M., Saenko, K., Darrell, T.: A category-level 3-d object dataset: Putting the kinect to work. In: ICCV Workshops, pp. 1168–1174 (2011)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Transactions on Pattern Analysis and Machine Intelligence 32, 1627–1645 (2010)
Savarese, S., Tuytelaars, T., Van Gool, L.J.: Special issue on 3d representation for object and scene recognition. Computer Vision and Image Understanding 113, 1181–1182 (2009)
Liebelt, J., Schmid, C., Schertler, K.: Viewpoint-independent object class detection using 3d feature maps. In: CVPR (2008)
Berg, A.C., Berg, T.L., Malik, J.: Shape matching and object recognition using low distortion correspondences. In: CVPR, pp. 26–33 (2005)
Asahiro, Y., Hassin, R., Iwama, K.: Complexity of finding dense subgraphs. Discrete Applied Mathematics (2002)
Ma, T., Latecki, L.J.: Maximum weight cliques with mutex constraints for video object segmentation. In: CVPR (2012)
Grabner, H., Gall, J., Van Gool, L.J.: What makes a chair a chair? In: CVPR, pp. 1529–1536 (2011)
Everingham, M., Van Gool, L.J., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. International Journal of Computer Vision 88, 303–338 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ma, T., Yi, M., Latecki, L.J. (2013). View-Invariant Object Detection by Matching 3D Contours. In: Park, JI., Kim, J. (eds) Computer Vision - ACCV 2012 Workshops. ACCV 2012. Lecture Notes in Computer Science, vol 7729. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37484-5_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-37484-5_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37483-8
Online ISBN: 978-3-642-37484-5
eBook Packages: Computer ScienceComputer Science (R0)