Abstract
Contextual modeling is a critical issue in scene understanding. Object detection accuracy can be improved by exploiting tendencies that are common among object configurations. However, conventional contextual models only exploit the tendencies of normal objects; abnormal objects that do not follow the same tendencies are hard to detect through contextual model. This paper proposes a novel generative model that detects abnormal objects by meeting four proposed criteria of success. This model generates normal as well as abnormal objects, each following their respective tendencies. Moreover, this generation is controlled by a latent scene variable. All latent variables of the proposed model are predicted through optimization via population-based Markov Chain Monte Carlo, which has a relatively short convergence time. We present a new abnormal dataset classified into three categories to thoroughly measure the accuracy of the proposed model for each category; the results demonstrate the superiority of our proposed approach over existing methods.
Chapter PDF
Similar content being viewed by others
References
Choi, M., Lim, J., Torralba, A., Willsky, A.: Exploiting hierarchical context on a large database of object categories. In: Proc. of IEEE Conf. on CVPR (2010)
Murphy, K., Torralba, A., Freeman, W.: Using the forest to see the trees: a graphical model relating features, objects and scenes. In: NIPS (2003)
Torralba, A., Murphy, K., Freeman, W.: Contextual models for object detection using boosted random fields. In: NIPS (2005)
Desai, C., Ramanan, D., Fowlkes, C.: Discriminative models for multi-class object layout. In: Proc. of ICCV (2009)
Choi, M., Torralba, A., Willsky, A.: Context models and out-of-context objects. Pattern Recognition Letters 33, 853–862 (2012)
Heitz, G., Koller, D.: Learning Spatial Context: Using Stuff to Find Things. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 30–43. Springer, Heidelberg (2008)
Galleguillos, C., Rabinovich, A., Belongie, S.: Object categorization using co-occurrence, location and appearance. In: Proc. of IEEE Conf. on CVPR (2008)
Jasra, A., Stephens, D., Holmes, C.: On population-based simulation for static inference. Statistics and Computing 17, 263–279 (2007)
Rabinovich, A., Vedaldi, A., Galleguillos, C., Wiewiora, E., Belongie, S.: Objects in context. In: Proc. of ICCV (2007)
Li, L., Socher, R., Fei-Fei, L.: Towards total scene understanding: Classification, annotation and segmentation in an automatic framework. In: Proc. of IEEE Conf. on CVPR (2009)
Ladicky, L., Russell, C., Kohli, P., Torr, P.H.S.: Graph Cut Based Inference with Co-occurrence Statistics. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 239–253. Springer, Heidelberg (2010)
Galleguillos, C., Belongie, S.: Context based object categorization: A critical survey. Computer Vision and Image Understanding 114, 712–722 (2010)
Russell, B., Torralba, A., Liu, C., Fergus, R., Freeman, W.: Object recognition by scene alignment. In: NIPS (2007)
Torralba, A.: Contextual priming for object detection. IJCV 53, 169–191 (2003)
Li, L., Su, H., Xing, E., Fei-Fei, L.: Object bank: A high-level image representation for scene classification and semantic feature sparsification. In: NIPS (2010)
Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. on PAMI 32, 1627–1645 (2010)
Hoiem, D., Efros, A., Hebert, M.: Putting objects in perspective. In: Proc. of IEEE Conf. on CVPR (2006)
Alexe, B., Deselaers, T., Ferrari, V.: What is an object? In: Proc. of IEEE Conf. on CVPR (2010)
Olson, C.: Maximum-likelihood image matching. IEEE Trans. on PAMI 24, 853–857 (2002)
Xiao, J., Hays, J., Ehinger, K., Oliva, A., Torralba, A.: Sun database: Large-scale scene recognition from abbey to zoo. In: Proc. of IEEE Conf. on CVPR (2010)
Russell, B., Torralba, A., Murphy, K., Freeman, W.: Labelme: a database and web-based tool for image annotation. IJCV 77, 157–173 (2008)
Van Hulse, J., Khoshgoftaar, T., Napolitano, A.: Experimental perspectives on learning from imbalanced data. In: ICML (2007)
Kim, W., Park, J., Lee, K.: Stereo matching using population-based mcmc. IJCV 83, 195–209 (2009)
Wei, L. (2012), http://www.liweiart.com
Everingham, M., Gool, L., Williams, C., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. IJCV 88, 303–338 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Park, S., Kim, W., Lee, K.M. (2012). Abnormal Object Detection by Canonical Scene-Based Contextual Model. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7574. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33712-3_47
Download citation
DOI: https://doi.org/10.1007/978-3-642-33712-3_47
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33711-6
Online ISBN: 978-3-642-33712-3
eBook Packages: Computer ScienceComputer Science (R0)