Abstract
Building recognition is an important and still challenging problem in computer vision and pattern recognition field. In this work, we propose a location-aware building recognition model by introducing blocklets, i.e., spatial adjacent blocks associated with their relative positions. First, by evenly partitioning each building image into blocks, we construct a spatial pyramid to describe the spatial relations of blocks. Second, we obtain blocklets by extracting spatial adjacent blocks. And we can cast the building recognition as matching between blocklets from different buildings. Third, towards an efficient matching, a hierarchical sparse coding method is proposed to represent each blocklet by a linear combination of basis blocklets. Furthermore, towards an effective matching, an LDA Jieping (In: Proceedings of ICML 1087–1093 2007)-like scheme is adopted to select the blocklets with high discrimination. Finally, we carry out the architecture recognition based on the selected highly discriminative blocklets. Experimental results on four datasets demonstrate our model is robust to occlusions and large change in backgrounds.
Similar content being viewed by others
Notes
The data set will be available online when the paper get accepted.
References
Jieping, Y.: Least squares linear discriminant analysis. In: Proceedings of ICML, pp 1087–1093 (2007)
Mao, J., Jain, A.K.: Texture classification and segmentation using multiresolution simultaneous autoregressive models. Pattern Recognit 25(2), 173–188 (1992)
Manjunath, B., Ma, W.Y.: Texture features for browsing and retrieval of image data. IEEE T-PAMI 18(8), 837–842 (1996)
Zhang, W., Kosecka, J.: Localization based on building recognition. IEEE Workshop on Computer Vision Applications for the Visually Impaired (2005)
Chung, Y.-C., Han, T. X., He, Z.: Building recognition using sketch-based representations and spectral graph. In: Proceedings of ICCV, pp 2014–2020 (2009)
Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of CVPR pp 2169–2178 (1006)
Yang, J., Yu, K., Gong, Y., Huang, T.: Linear spatial pyramid matching using sparse coding for image classification. In Proceedings of CVPR, pp 2169–2178 (2009)
Wang, J., Yang, J., Yu, K., Lv, F., Huang T., Gong, Y.: Locality-constrained linear coding for image classification. In: Proceedings of CVPR (2010)
Zhang, L., Bian, W., Song, M., Tao, D., Liu, X.: Integrating local features into discriminative graphlets for scene classification. Neural Information Processing (2011)
Yu, K., Lin Y., Lafferty, J.: Learning image representations from the pixel level via hierarchical sparse coding. In: Proceedings of CVPR (2011)
Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Object retrieval with large vocabularies and fast spatial matching. In: Proceedings of CVPR (2007)
Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Lost in quantization: improving particular object retrieval in large scale image databases. In: Proceedings of CVPR (2008)
Shao, H., Svoboda, T., Van Gool, L.: ZUBUD-Zurich buildings database for image based recognition. Technical report No. 260, Swiss Federal Institute of Technology (2003)
Harchaoui, Z., Bach, F.: Image classification with segmentation graph kernels. In: Proceedings of CVPR, pp 1–8 (2007)
Zhou, Xi., Cui, Na., Li, Zhen., Liang, Feng., Huang, Thomas S.: Hierarchical Gaussianization for image classification. In: Proceedings of ICCV, pp 1971–197 (2009)
Rehg, J.M., Wu, J.: Beyond the euclidean distance: creating effective visual codebooks using the histogram intersection kernel. In Proceedings IEEE ICCV, pp 630–637 (2009)
van Gemert, J. C., Geusebroek, J.-M., Veenman, C. J., Smeulders, A. W. M.: Kernel codebooks for scene categorization. In: Proceedings ECCV, pp 696–709 (2008)
Duda, R.O., Hart P.E., Stork, D.G.: Pattern classification. Wiley, (2000)
Honglak, L., Alexis, B., Rajat, R., Ng, A.Y.: Efficient sparse coding algorithms. In: Proceedings of NIPS, (2006)
Porway, J., Wang, K., Yao, B., Zhu, S.C.: Scale-invariant shape features for recognition of object categories. In: Proceedings of ICCV, (2004)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Li, Y., Zhang, S. & Zhang, L. Mining location-aware discriminative blocklets for recognizing landmark architectures. Multimedia Systems 22, 455–464 (2016). https://doi.org/10.1007/s00530-014-0409-6
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00530-014-0409-6