Abstract
Class-level object detection is a fundamental task in computer vision and it is usually tackled with global or local image features. In contrast to these approaches, we propose semi-local features that exploit object segmentation as a pre-processing step for detection. The term semi-local features depicts that the proposed features are locally extracted from the image but globally extracted from the object. In particular, we investigate the impact of features generation approaches from differently transformed object regions. These transformations are, on the one hand, done with several object-background modifications and bounding-boxes. On the other hand, state-of-the-art texture and color features as well as different dissimilarity measures are compared against each other. We use the Pascal VOC 2010 dataset for evaluation with perfect and inaccurate object segments and to perform a case study with an automatic segmentation approach. The results indicate the high potential of semi-local features to assist object detection systems and show that a significant difference exists between different feature extraction methods.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Pantofaru, C., Schmid, C., Hebert, M.: Object Recognition by Integrating Multiple Image Segmentations. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 481–494. Springer, Heidelberg (2008)
Li, F., Carreira, J., Sminchisescu, C.: Object recognition as ranking holistic Figure-ground hypotheses. In: CVPR (2007)
Rabinovich, A., Vedaldi, A., Belongie, S.: Does image segmentation improve object categorization? Tech. Rep. CS2007-090 (2007)
Russell, B., Freeman, W., Efros, A., Sivic, J., Zisserman, A.: Using multiple segmentations to discover objects and their extent in image collections. In: CVPR (2006)
Everingham, M., Van Gool, L., Williams, C., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes (VOC) challenge. IJCV (2010)
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. PAMI (2005)
Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Van Gool, L.: A comparison of affine region detectors. IJCV (2005)
Van de Sande, K., Gevers, T., Snoek, C.: Evaluating color descriptors for object and scene recognition. PAMI (2010)
Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: CVPR (2006)
Lampert, C., Blaschko, M., Hofmann, T.: Beyond sliding windows: Object localization by efficient subwindow search. In: CVPR (2008)
Oliva, A., Torralba, A.: Building the GIST of a Scene: The Role of Global Image Features in Recognition. Visual Perception, Progress in Brain Research (2006)
Hoiem, D., Efros, A., Hebert, M.: Geometric context from a single image. In: ICCV (2005)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)
Leibe, B., Leonardis, A., Schiele, B.: Robust object detection with interleaved categorization and segmentation. IJCV (2008)
Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV (2004)
Toshev, A., Taskar, B., Daniilidis, K.: Object detection via boundary structure segmentation. In: CVPR (2010)
Shi, J., Malik, J.: Normalized cuts and image segmentation. In: CVPR (1997)
Carreira, J., Sminchisescu, C.: Constrained parametric min cuts for automatic object segmentation. In: CVPR (2010)
Comaniciu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. PAMI (2002)
Hoiem, D., Stein, A., Efros, A., Hebert, M.: Recovering occlusion boundaries. IJCV (2011)
Csurka, G., Perronnin, F.: An efficient approach to semantic segmentation. IJCV (2010)
Frigo, M., Johnson, S.: The design and implementation of FFTW3. In: Proc. Program Generation, Optimization, and Platform Adaptation (2005)
Manjunath, B., Ohm, J.-R., Vasudevan, V., Yamada, A.: Color and texture descriptors. Trans. on Circuits and Systems for Video Technology (2001)
Liu, H., Song, D., Rüger, S.M., Hu, R., Uren, V.S.: Comparing Dissimilarity Measures for Content-Based Image Retrieval. In: Li, H., Liu, T., Ma, W.-Y., Sakai, T., Wong, K.-F., Zhou, G. (eds.) AIRS 2008. LNCS, vol. 4993, pp. 44–50. Springer, Heidelberg (2008)
Sorschag, R.: CORI: A configurable object recognition infrastructure. In: International Conference on Signal and Image Processing Applications (2011)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. IJCV (2004)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sorschag, R. (2013). Object Detection with Semi-local Features. In: Latorre Carmona, P., Sánchez, J., Fred, A. (eds) Pattern Recognition - Applications and Methods. Advances in Intelligent Systems and Computing, vol 204. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-36530-0_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-36530-0_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-36529-4
Online ISBN: 978-3-642-36530-0
eBook Packages: EngineeringEngineering (R0)