Abstract
Motivated by the rising performances of object detection algorithms, we investigate how to further precisely segment out objects within the output bounding boxes. The task is formulated as a unified optimization problem, pursuing a unique latent object mask in non-parametric manner. For a given test image, the objects are first detected by detectors. Then for each detected bounding box, the objects of the same category along with their object masks are extracted from the training set. The latent mask of the object within the bounding box is inferred based on three objectives: 1) the latent mask should be coherent, subject to sparse errors caused by within-category diversities, with the global bounding-box-level mask inferred by sparse representation over the bounding boxes of the same category within the training set; 2) the latent mask should be coherent with local patch-level mask inferred by sparse representation of the individual patch over all spatially nearby (handling local deformations) patches of the same category in the training set; and 3) mask property within each sufficiently small super-pixel should be consistent. All these three objectives are integrated into a unified optimization problem, and finally the sparse representation coefficients and the latent mask are alternately optimized based on Lasso optimization and smooth approximation followed by Accelerated Proximal Gradient method, respectively. Extensive experiments on the Pascal VOC object segmentation datasets, VOC2007 and VOC2010, show that our proposed algorithm achieves competitive results with the state-of-the-art learning based algorithms, and is superior over other detection based object segmentation algorithms.
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
Gonfaus, J., Bosch, X., Weijer, J., Bagdanov, A., Gual, J.: Harmony potentials for joint classification and segmentation. In: CVPR (2010)
Li, F., Carreira, J., Sminchisescu, C.: Object recognition as ranking holistic figure-ground hypotheses. In: CVPR (2010)
Brox, T., Bourdev, L., Maji, S., Malik, J.: Object segmentation by alignment of poselet activations to image contours. In: CVPR (2011)
Yang, Y., Hallman, S., Ramanan, D., Fowlkes, C.: Layered object detection for multi-class segmentation. In: CVPR (2010)
Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. TPAMI 32 (2010)
Vedaldi, A., Gulshan, V., Varma, M., Zisserman, A.: Multiple kernels for object detection. In: ICCV (2009)
Kumar, M., Torr, P., Zisserman, A.: OBJ CUT. In: CVPR (2005)
Ladicky, L., Sturgess, P., Alahari, K., Russell, C., Torr, P.: What, Where and How Many? Combining Object Detectors and CRFs. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 424–437. Springer, Heidelberg (2010)
Ladicky, L., Russell, C., Kohli, P., Torr, P.: Associative hierarchical CRFs for object class image segmentation. In: ICCV (2009)
Ladicky, L., Russell, C., Kohli, P., Torr, P.: 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)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge, VOC 2007 (2007) (results)
Yuan, X., Yan, S.: Visual classification with multi-task joint sparse representation. In: CVPR (2010)
Mori, G., Ren, X., Efros, A., Malik, J.: Recovering human body configurations: Combining segmentation and recognition. In: CVPR (2004)
Martin, D., Fowlkes, C., Malik, J.: Learning to detect natural image boundaries using brightness and texture. In: NIPS (2002)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge, VOC 2010 (2010) (results)
Malisiewic, T., Gupta, A., Efros, A.: Ensemble of exemplar-svms for object detection and beyond. In: ICCV (2011)
Wright, J., Yang, A., Ganesh, A., Sastry, S., Ma, Y.: Robust face recognition via sparse representation. TPAMI 31 (2009)
Yang, J., Yu, K., Gong, Y., Huang, T.: Linear spatial pyramid matching using sparse coding for image classification. In: CVPR (2009)
Liu, X., Feng, J., Yan, S., Jin, H.: Image segmentation with patch-pair density priors. In: ACM Multimedia (2010)
Rao, S., Tron, R., Vidal, R., Ma, Y.: Motion segmentation via robust subspace separation in the presence of outlying, incomplete, or corrupted trajectories. In: CVPR (2008)
Elhamifar, E., Vidal, R.: Sparse subspace clustering. In: CVPR (2009)
Zhu, L., Chen, Y., Yuille, A., Freeman, W.: Latent hierarchical structural learning for object detection. In: CVPR (2010)
Chen, Y., Zhu, L., Yuille, A.: Active Mask Hierarchies for Object Detection. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 43–56. Springer, Heidelberg (2010)
Emmanuel Candes, J.R.: L1-magic: Recovery of sparse signals via convex programming (2005)
Nesterov, Y.: Smooth minimization of non-smooth functions. Math. Program. (2005)
Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., Gong, Y.: Locality-constrained linear coding for image classification. In: CVPR (2010)
Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: CVPR (2006)
Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV 60 (2004)
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
Xia, W., Song, Z., Feng, J., Cheong, LF., Yan, S. (2012). Segmentation over Detection by Coupled Global and Local Sparse Representations. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7576. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33715-4_48
Download citation
DOI: https://doi.org/10.1007/978-3-642-33715-4_48
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33714-7
Online ISBN: 978-3-642-33715-4
eBook Packages: Computer ScienceComputer Science (R0)