Abstract
Object detection and segmentation are indispensable for image scene understanding in augmented reality games. Object proposals delineate candidate objects in the image, and are widely used to speed up object searching in object detection and segmentation. This paper presents an approach for reducing the redundancy in object proposals. We compute contour support of object proposals, and construct contour support constraints using the characteristics of contour support distributions for foreground objects and image background. According to the constructed constraints, we propose the accepting and rejecting strategies to refine object proposals. Experiments demonstrate that our method reduces redundant object proposals and improves proposal accuracy for low proposal budgets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alexe, B., Deselaers, T., Ferrari, V.: Measuring the objectness of image windows. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2189–2202 (2012)
Carreira, J., Li, F., Sminchisescu, C.: Object recognition by sequential figure-ground ranking. Int. J. Comput. Vis. 98(3), 243–262 (2012)
Carreira, J., Sminchisescu, C.: CPMC: automatic object segmentation using constrained parametric min-cuts. IEEE Trans. Pattern Anal. Mach. Intell. 34(7), 1312–1328 (2012)
Cheng, M.M., Zhang, Z., Lin, W.Y., Torr, P.: Bing: binarized normed gradients for objectness estimation at 300fps. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3286–3293 (2014)
Dollár, P., Zitnick, C.L.: Structured forests for fast edge detection. In: IEEE International Conference on Computer Vision, pp. 1841–1848 (2013)
Estrada, F.J., Jepson, A.D.: Robust boundary detectionwith adaptive grouping. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop, p. 184 (2006)
Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The Pascal visual object classes (voc) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)
Hariharan, B., Arbeláez, P., Girshick, R., Malik, J.: Simultaneous detection and segmentation. In: European Conference on Computer Vision, pp. 297–312 (2014)
Hosang, J., Benenson, R., Schiele, B.: How good are detection proposals, really? In: British Machine Vision Conference, pp. 1–12 (2014)
Krahenbuhl, P., Koltun, V.: Learning to propose objects. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1574–1582 (2015)
Krähenbühl, P., Koltun, V.: Geodesic object proposals. In: European Conference on Computer Vision, pp. 725–739 (2014)
Levinshtein, A., Sminchisescu, C., Dickinson, S.: Optimal image and video closure by superpixel grouping. Int. J. Comput. Vis. 100(1), 99–119 (2012)
Lu, C., Liu, S., Jia, J., Tang, C.K.: Contour box: rejecting object proposals without explicit closed contours. In: IEEE International Conference on Computer Vision, pp. 2021–2029 (2015)
Van de Sande, K.E., Uijlings, J.R., Gevers, T., Smeulders, A.W.: Segmentation as selective search for object recognition. In: IEEE International Conference on Computer Vision, pp. 1879–1886 (2011)
Wang, S., Kubota, T., Siskind, J.M., Wang, J.: Salient closed boundary extraction with ratio contour. IEEE Trans. Pattern Anal. Mach. Intell. 27(4), 546–561 (2005)
Wang, X., Yang, M., Zhu, S., Lin, Y.: Regionlets for generic object detection. In: IEEE International Conference on Computer Vision, pp. 17–24 (2013)
Zitnick, C.L., Dollár, P.: Edge boxes: locating object proposals from edges. In: European Conference on Computer Vision, pp. 391–405 (2014)
Acknowledgements
This work is supported by National Natural Science Foundation of China under Grant No. 91520301.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Huang, X., Su, Y., Liu, Y. (2016). Object Proposal Refinement Based on Contour Support for Augmented Reality. In: El Rhalibi, A., Tian, F., Pan, Z., Liu, B. (eds) E-Learning and Games. Edutainment 2016. Lecture Notes in Computer Science(), vol 9654. Springer, Cham. https://doi.org/10.1007/978-3-319-40259-8_21
Download citation
DOI: https://doi.org/10.1007/978-3-319-40259-8_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-40258-1
Online ISBN: 978-3-319-40259-8
eBook Packages: Computer ScienceComputer Science (R0)