Abstract
Object detection is widely employed in a large number of areas, such as human detection, medical image processing, etc. However, it is insufficient to use only a learning algorithm to detect objects and more techniques or models, such as a probability based approach, a part model, a segmentation model, are combined with the learning algorithm to accomplish the detection task. To this end, a fusion approach is required to balance the decisions making by multiple models. This paper proposes an optimization methodology that fuses a set of confidence outputs estimated by multiple models. Various experiments are executed and demonstrate that the proposed fusion method has a relative better performance than that of the system constituted by a single model.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The UIUC Image Database for Car Detection is available at http://cogcomp.cs.illinois.edu/Data/Car/.
- 2.
The Caltech Airplanes dataset is available at http://www.vision.caltech.edu/html-files/archive.html.
References
Opelt, A., Pinz, A., Zisserman, A.: Incremental learning of object detectors using a visual shape alphabet. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 3–10 (2006)
Leibe, B., Leonardis, A., Schiele, B.: Robust Object Detection with Interleaved Categorization and Segmentation. Int J Comput Vis 77, 259–289 (2008). doi:10.1007/s11263-007-0095-3
Scholkopf, B., Smola, A.J.: Learning with Kernels, Support Vector Machines, Regularization, Optimization, and Beyond (Adaptive Computation and Machine Learning). The MIT Press, Cambridge (2002)
Alexe, B., Deselaers, T., Ferrari, V.: What is an object? In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2010)
Lang, C., Liu, G., Yu, J., Yan, S.: Saliency detection by multitask sparsity pursuit. IEEE Trans. Image Process. 21(3), 1327–1338 (2012)
Laptev, I.: Improving object detection with boosted histograms. Image Vis. Comput. 27, 535–544 (2009)
Nelder, J.A., Mead, R.: A simplex method for function minimization. Comput. J. 7, 308–313 (1965). doi:10.1093/comjnl/7.4.308
Lagarias, J.C., Reeds, J.A., Wright, M.H., Wright, P.E.: Convergence properties of the Nelder-Mead simplex method in low dimensions. SIAM J. Optim. 9(1), 112–147 (1998)
Wu, J., Shen, H., Li, Y.-D., Xiao, Z.-B., Ming-Yu, L., Wang, C.-L.: Learning a hybrid similarity measure for image retrieval. Pattern Recogn. 46(11), 2927–2939 (2013)
Domke, J.: Learning graphical model parameters with approximate marginal inference. PAMI, 35(10), pp. 2454–2467 (2013) (to appear)
Zhu, L., Chen, Y., Yuille, A., Freeman, W.: Latent hierarchical structural learning for object detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2010)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes (VOC) challenge. Int. J. Comput. Vis. 88, 303–338 (2010). doi:10.1007/s11263-009-0275-4
Fischler, M.A., Elschlager, R.A.: The representation and matching of pictorial structures. IEEE Trans. Comput. c-22(1), 67–92 (1973)
Burl, M.C., Weber, M., Perona, P.: A probabilistic approach to object recognition using local photometry and global geometry. In: Proceedings of European Conference on Computer Vision, pp. 628–641 (1998)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627–1645 (2010)
Zhu, S.-C., Mumford, D.: A stochastic grammar of images. Found. Trends Comput. Graph. Vis. 2(4), 259–362 (2006). doi:10.1561/0600000018
Wang, T., Dai, G., Ni, B., Xu, D., Siewe, F.: A distance measure between labeled combinatorial maps. Comput. Vis. Image Underst. 116(2012), 1168–1177 (2012)
Wang, Y., Georgescu, B., Chen, T., Wen, W., Wang, P., Xiaoguang, L., Lonasec, R., Zheng, Y., Comaniciu, D.: Learning-based detection and tracking in medical imaging: a probabilistic approach. Lect. Notes Comput. Vis. Biomech. 7, 209–235 (2013)
Li, Y., Shen, H.: On identity disclosure control for hypergraph-based data publishing. IEEE Trans. Inf. Forensics Secur. 8(8), 1384–1396 (2013)
Song, Z., Chen, Q., Huang, Z., Hua, Y., Yan, S.: Contextualizing object detection and classification. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2011)
Teng, Z., Zhang, B., Kim, O., Kang, D.-J.: Regional SVM classifiers with a spatial model for object detection. In: International Conference on Computer Vision Theory and Applications, Lisbon, Portugal (2014)
Acknowledgements
This work was supported by the Fundamental Research Funds for the Central Universities with grant number 2014JBM040 and Natural Science Foundation of China (61370070).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Teng, Z., Zhang, B. (2014). An Optimization Method of Fusing Multiple Decisions in Object Detection. In: Peng, WC., et al. Trends and Applications in Knowledge Discovery and Data Mining. PAKDD 2014. Lecture Notes in Computer Science(), vol 8643. Springer, Cham. https://doi.org/10.1007/978-3-319-13186-3_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-13186-3_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-13185-6
Online ISBN: 978-3-319-13186-3
eBook Packages: Computer ScienceComputer Science (R0)