Abstract
Object detection is a hot research topic in the field of computer vision. The existing algorithms do not take full account of the diversity of features of objects in the same class and the similarity between objects in different classes. To solve the above problems, a method for object detection based on exemplar object expression is proposed in this study. In the proposed algorithm, the concept of multi-feature tree is introduced. By employing the differences and similarities between some features of the objects, the objects in the training set are partitioned into different clusters. Thus, the leaf nodes of multi-feature tree constitute exemplar objects. At last, all the generated exemplar objects are adopted for the expression of object. The information of both the diversity of objects in the same class and the difference of objects in different classes is encoded for the object expression. Thus, the object detector has a satisfactory integration capability for objects in the same class, and a good distinguishing ability for objects in different classes. In this study, the proposed algorithm is compared with the existing object detection algorithms through the experiment on datasets of both PASCAL VOC 2010 and PASCAL VOC 2012. The validity of the proposed approach is proved according to the experimental results.
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
Preview
Unable to display preview. Download preview PDF.
References
Song, Z., Chen, Q., Huang, Z., Hua, Y., Yan, S.: Contextualizing object detection and classification. In: CVPR (2011)
Chen, Q., Song, Z., Hua, Y., Huang, Z., Yan, S.: Hierarchical matching with side information for image classification. In: CVPR (2012)
Russakovsky, O., Lin, Y., Yu, K., Fei-Fei, L.: Object-centric spatial pooling for image classification. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 1–15. Springer, Heidelberg (2012)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object Detection with Discriminatively Trained Part-Based Models. TPAMI (2010)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)
Dai, J., Yan, S., Tang, X., Kwok, J.T.: Locally adaptive classification piloted by uncertainty. In: ICML (2006)
Li, L., Su, H., Xing, E., Fei-Fei, L.: ObjectBank: a high-level image representation for scene classification & semantic feature sparsification. In: Proceedings of the Neural Information Processing Systems, Vancouver, Canada (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, Y., Wang, X., Du, J., Du, T. (2015). Object Detection Based on Exemplar Object Expression. In: Park, J., Chao, HC., Arabnia, H., Yen, N. (eds) Advanced Multimedia and Ubiquitous Engineering. Lecture Notes in Electrical Engineering, vol 352. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-47487-7_36
Download citation
DOI: https://doi.org/10.1007/978-3-662-47487-7_36
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-47486-0
Online ISBN: 978-3-662-47487-7
eBook Packages: EngineeringEngineering (R0)