Abstract
The objective of this paper is to use computer vision to detect and localize multiple object within an image in the presence of a cluttered background, substantial occlusion and significant scale changes. Our approach consists of first generating a set of hypotheses for each object using a generative model (pLSA) with a bag of visual words representing each image. Then, the discriminative part verifies each hypothesis using a multi-class SVM classifier with merging features that combines both spatial shape and color appearance of an object. In the post-processing stage, environmental context information is used to improve the performance of the system. A combination of features and context information are used to investigate the performance on our local database. The best performance is obtained using object-specific weighted merging features and the context information. Our approach overcomes the limitations of some state of the art methods.
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
Seemann, E., Leibe, B., Mikolajczyk, K., Schiele, B.: An evaluation of local shape-based features for pedestrain detection. In: Proc. of British Machine Vision Conference (BMVC 2005), Oxford, UK (2005)
Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: Proc. of European Conference on Computer Vision (ECCV 2004), Workshop on Statistical Learning in Computer Vision, Prague (2004)
Diplaros, A., Gevers, T., Patras, I.: Combining color and shape information for illumination-viewpoint invariant object recognition. IEEE Transactions on Image Processing 15, 1–11 (2006)
Stella, X., Ralph, G., Jianbo, S.: Concurrent object recognition and segmentation by graph partioning. In: Proc. of Neural Information Processing Systems (NIPS), Vancouver, Canada, pp. 1383–1390 (2002)
Leibe, B., Leonardis, A., Schiele, B.: Combined object categorization and segmentation with an implicit shape model. In: Proc. of ECCV 2004, Workshop on Statistical Learning in Computer Vision, Prague, pp. 17–32 (2004)
Guillaume, B., Bill, T.: Hierarchical part-based visual object categorization. In: Proc. of International Conference on Computer Vision and Pattern Recognition (CVPR(1)), San Diego, CA, USA, pp. 710–715 (2005)
Fergus, R., Perona, P., Zisserman, A.: Weakly supervised scale-invariant learning of model for visual recognition. International Journal of Computer Vision (IJCV) 71, 273–303 (2007)
Ferrari, V., Tinne, T., Luc, V.G.: Object detection by contour segmentation networks. In: Proc. of ECCV(3), Graz, Austria, pp. 14–28 (2006)
Jacobs, D.: Robust and efficient detection of salient convex groups. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) 18, 23–37 (1996)
Marcin, M., Cordelia, S.: Spatial weigthing for bag-of-features. In: Proc. of CVPR (2), New York, NY, pp. 2118–2125 (2006)
Bosch, A., Zisserman, A., Muñoz, X.: Representing shape with spatial pyramid kernel. In: ACM International Conference on Image and Video Retrieval (CIVR), Amsterdam, The Netherlands, pp. 401–408 (2007)
Ferrari, V., Fevrier, L., Jurie, F., Schmid, C.: Group of adjacent contour segment for object detection. PAMI 30, 30–51 (2008)
Josef, S., Bryan, R.C., Alexei, A., Zisserman, A., William, T.: Discovering objects and their location in images. In: Proc. of the IEEE International Conference on Computer Vision (ICCV), Beijing, China, pp. 370–377 (2005)
Stefan, Z., Manuela, M.: Detection and localization of multiple objects. In: Proc. of Humanoids, Genoa, Italy (2006)
Erik, M.C., Jochen, T.: Shared Features for Scalable Appearance-Based Object Recognition. In: Proc. of IEEE Workshop on Application of Computer Vision (WACV), Breckenridge, Colorado, pp. 16–21 (2005)
Bosch, A., Zisserman, A., Muñoz, X.: Scene classification using a hybrid generative/discriminative approach. PAMI 30, 712–727 (2008)
Fritz, M., Leibe, B., Caputo, B., Schiele, B.: Integrating representative and discriminative models for object category detection. In: Proc. of ICCV, Beijing, China, pp. 1363–1370 (2005)
Hofmann, T.: Unsupervised learning by probabilistic latent semantic analysis. Machine Learning 42, 177–196 (2001)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Das, D., Mansur, A., Kobayashi, Y., Kuno, Y. (2008). An Integrated Method for Multiple Object Detection and Localization. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2008. Lecture Notes in Computer Science, vol 5359. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-89646-3_14
Download citation
DOI: https://doi.org/10.1007/978-3-540-89646-3_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-89645-6
Online ISBN: 978-3-540-89646-3
eBook Packages: Computer ScienceComputer Science (R0)