Abstract
This paper proposes a novel object detection approach based on local shape information. Boundary edge fragments preserve some features like shape and position which properly describe the outline of an object. Extraction of object boundary fragments is a challenging task in object detection. In this paper, a sophisticated system is proposed to achieve this goal. We propose local shape descriptors and present a boundary fragment extraction method using Poisson equation properties, and then, we compute relation between boundary fragments using GMM to obtain exact boundaries and detect the object. To get more accurate detection of the object, we employ a False Positive elimination stage based on local orientation histogram matching. The proposed object detection system is applied on several datasets containing object classes in cluttered images in various forms of scale and translation. We compare our approach with other similar methods that use shape information for object detection. Experimental results show the power of our proposed method in detection and its robustness in face with scale and translation variations.
Similar content being viewed by others
References
Shotton J, Blake A, Cipolla R (2008) Multiscale categorical object recognition using contour fragments. IEEE Trans Pattern Anal Mach Intell 30(7):1270–1281
Felzenszwalb PF, Huttenlocher DP (2000) Efficient matching of pictorial structure. In: Proceedings of IEEE Conference on computer vision and pattern recognition (CVPR’00), vol 2, pp 66–73
Agarwal S, Atwan A, Roth D (2004) Learning to detect objects in images via a sparse, part-based representation. IEEE Trans Pattern Anal Mach Intell 26(11):1475–1490
Burl M, Weber M, Perona P (1998) A probabilistic approach to object recognition using local photometry and global geometry. In: Proceedings of European Conference on computer vision (ECCV’ 98), pp 628–641
Bouchard G, Triggs B (2005) A hierarchical part-based model for visual object categorization. In: Proceedings of IEEE Conference on computer vision and pattern recognition (CVPR’05), vol 1, pp 710–715
Leibe B, Leonardis A, Schiele B (2008) Robust object detection with interleaved categorization and segmentation. Int J Comput Vision 77(1–3):259–289
Ferrari V, Jurie F, Schmid C (2010) From images to shape models for object detection. Int J Comput Vision 87(3):284–303
Anvaripour M, Ebrahimnezhad H (2010) Object detection with novel shape representation using bounding edge fragments. In: Proceedings of International Symposium on telecommunication (IST’10), pp 846–851
Borenstein E, Malik J (2006) Shape guided object segmentation. In: Proceedings of the IEEE Conference on computer vision and pattern recognition (CVPR’06), vol 1, pp 969–976
Basri R, Costa L, Geiger D, Jacobs D (1998) Determining the similarity of deformable shapes. Vision Res 38:2365–2385
Garvilla D (2000) Pedestrian detection from a moving vehicle. In: Proceedings of European Conference on computer vision (ECCV’00), pp 37–49
Grauman K, Darrell T (2005) The Pyramid match kernels: discriminative classification with sets of image features. In: Proceedings of International Conference on computer vision (ICCV’05), vol 2, pp 1458–1465
Opelt A, Pinz A, Zisserman A (2006) A boundary-fragment model for object detection. In: Proceedings of European Conference on computer vision (ECCV’ 06), pp 575–588
Leibe B, Schiele B (2004) Scale-invariant object categorization using a scale-adaptive mean-shift search. In: Proceedings of DAGM’04 Pattern Recognition Symposium
Belongie S, Malik J (2002) Shape matching and object recognition using shape contexts. IEEE Trans Pattern Anal Mach Intell 24(4):509–522
Chui H, Rangarajan A (2003) A new point matching algorithm for non-rigid registration. Comput Vis Image Underst 89(2–3):114–141
Ommer B, Malik J (2009) Multi-scale object detection by clustering lines. In: Proceedings of International Conference on computer vision (ICCV’09), pp 484–491
Berg AC, Malik J (2001) Geometric blur for template matching. In: Proceedings of IEEE Conference on computer vision and pattern recognition, vol 1, pp 607–614
Geremy H, Gal E, Benjamin P, Daphne K (2009) Shape-based object localization for descriptive classification. Int J Comput Vision 84(1):40–62
Ferrari V, Jurie F, Schmid C (2006) Object detection with contour segment networks. In: Proceedings of European Conference on computer vision, pp 14–28
Ferrari V, Fevrier L, Jurie F, Schmid C (2007) Groups of adjacent contour segments for object detection. IEEE Trans Pattern Anal Mach Intell 30(1):36–51
Pham TV, Smeulders AWM (2005) Object recognition with uncertain geometry and uncertain part detection. Comput Vis Image Underst 99(2):241–258
Levin A, Weiss Y (2009) Learning to combine bottom-up and top-down segmentation. Int J Comput Vision 81(1):105–118
Sharon E, Galun M, Sharon D, Basri R, Brandt A (2006) Hierarchy and adaptivity in segmenting visual scenes. Nature 442:810–813
Gorelick L, Basri R (2009) Shape based detection and top–down delineation using image segments. Int J Comput Vision 83(3):211–232
Gorelick L, Galun M, Sharon E, Basri R, Brandt A (2006) Shape representation and classification using the Poisson equation. IEEE Trans Pattern Anal Mach Intell 28(12):1991–2005
Bergtholdt M, Kappes J, Schmidt S, Schnörr C (2010) A study of parts-based object class detection using complete graphs. Int J Comput Vision 87(1–2):93–117
Perronnin F (2008) Universal and adapted vocabularies for generic visual categorization. IEEE Trans Pattern Anal Mach Intell 30(7):1243–1256
ETHZ Database (2007) Ferrari V http://www.vision.ee.ethz.ch/datasets/downloads/ethz_shape_classes_v12.tgz. Accessed 2012
Adluru N, Latecki LJ (2009) Contour grouping based on contour-skeleton duality. Int J Comput Vision 83(1):12–29
Maji S, Malik J (2009) Object detection using max-margin Hough transform. In: Proceedings of IEEE Conference on computer vision and pattern recognition (CVPR’09), pp 1038–1045
Lu C, Adluru N, Ling H, Zhu G, Latecki LJ (2010) Contour based object detection using part bundles. Comput Vis Image Underst 114(7):827–834
Lear Data Sets and Images (2006-2013) LEAR-Learning and Recognition in Vision http://lear.inrialpes.fr/data. Accessed 2012
Weizmann Horse Database (2005) Borenstein E http://www.msri.org/people/members/eranb. Accessed 2012
Caltech101 Database (2006) Fei–Fei L, Fergus R, Perona P http://www.vision.caltech.edu/Image_Datasets/Caltech101/Caltech101.html. Accessed 2012
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Anvaripour, M., Ebrahimnezhad, H. Accurate object detection using local shape descriptors. Pattern Anal Applic 18, 277–295 (2015). https://doi.org/10.1007/s10044-013-0342-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-013-0342-x