access icon free Greedy refinement of object proposals via boundary-aligned minimum bounding box search

© The Institution of Engineering and Technology
Received 11/04/2017, Accepted 19/11/2017, Revised 31/08/2017, Published 27/11/2017

Recently developed object detectors rely on automatically generated object proposals, instead of using a dense sliding window search scheme; generating good object proposals has therefore become crucial for improving the computational cost and accuracy of object detection performance. In particular, the shape and location errors of object proposals can be directly propagated to object detection unless some additional processes are adopted to refine the shape and location of bounding boxes. In this study, the authors demonstrate an object proposal refinement algorithm that improves the localisation accuracy and refines the shape of object proposals by searching a boundary-aligned minimum bounding box. They assume that an object consists of several image regions, and that the optimal object proposal is well aligned with image region boundaries. Based on this assumption, they design novel boundary-region alignment measures and then propose a greedy refinement method based on the proposed measures. Experiments on the PASCAL VOC 2007 dataset show that the proposed method produces highly well-localised object proposals and truly improves the quality of object proposals.

Inspec keywords: object detection; greedy algorithms; search problems

Other keywords: object detectors; object proposal refinement algorithm; image region boundaries; greedy refinement method; dense sliding window search scheme; boundary-aligned minimum bounding box search; PASCAL VOC 2007 dataset

Subjects: Optimisation techniques; Combinatorial mathematics; Optical, image and video signal processing; Optimisation techniques; Combinatorial mathematics; Computer vision and image processing techniques

References

    1. 1)
      • 2. Szegedy, C., Toshev, A., Erhan, D.: ‘Deep neural networks for object detection’. Proc. of Advances in Neural Information Processing Systems, 2013, pp. 2553–2561.
    2. 2)
      • 12. Zhang, Y., Sohn, K., Villegas, R., et al: ‘Improving object detection with deep convolutional networks via Bayesian optimization and structured prediction’. Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, 2015, pp. 249–258.
    3. 3)
      • 11. Arbelaez, P., Pont-Tuset, J., Barron, J., et al: ‘Multiscale combinatorial grouping’. Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, 2014, pp. 328–335.
    4. 4)
      • 17. Felzenszwalb, P.F., Huttenlocher, D.P.: ‘Efficient graph-based image segmentation’, Int. J. Comput. Vis., 2004, 59, (2), pp. 167–181.
    5. 5)
      • 10. Manen, S., Guillaumin, M., Van Gool, L.: ‘Prime object proposals with randomized Prim's algorithm’. Proc. of IEEE Int. Conf. on Computer Vision, 2013, pp. 2536–2543.
    6. 6)
      • 15. Alexe, B., Deselaers, T., Ferrari, V.: ‘What is an object?’. Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, 2010, pp. 73–80.
    7. 7)
      • 5. Alexe, B., Deselaers, T., Ferrari, V.: ‘Measuring the objectness of image windows’, IEEE Trans. Pattern Anal. Mach. Intell., 2012, 34, (11), pp. 2189–2202.
    8. 8)
      • 19. Girshick, R.: ‘Fast R-CNN’. Proc. of IEEE Int. Conf. on Computer Vision, 2015, pp. 1440–1448.
    9. 9)
      • 20. Vedaldi, A., Lenc, K.: ‘MatConvNet: convolutional neural networks for MATLAB’. Proc. of the ACM Int. Conf. on Multimedia, 2015.
    10. 10)
      • 9. Zitnick, C.L., Dollár, P.: ‘Edge boxes: locating object proposals from edges’. Proc. of European Conf. on Computer Vision, 2014, pp. 391–405.
    11. 11)
      • 3. Wang, X., Yang, M., Zhu, S., et al: ‘Regionlets for generic object detection’. Proc. of IEEE Int. Conf. on Computer Vision, 2013, pp. 17–24.
    12. 12)
      • 6. Uijlings, J.R.R., van de Sande, K.E.A., Gevers, T., et al: ‘Selective search for object recognition’, Int. J. Comput. Vis., 2013, 104, (2), pp. 154–171.
    13. 13)
      • 7. Cheng, M.-M., Zhang, Z., Lin, W.-Y., et al: ‘BING: binarized normed gradients for objectness estimation at 300 fps’. Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, 2014, pp. 3286–3293.
    14. 14)
      • 14. Liu, J., Ren, T., Wang, Y., et al: ‘Object proposal on RGB-D images via elastic edge boxes’, Neurocomputing, 2017, 236, pp. 134–146.
    15. 15)
      • 8. Krähenbühl, P., Koltun, V.: ‘Geodesic object proposals’. Proc. of European Conf. on Computer Vision, 2014, pp. 725–739.
    16. 16)
      • 18. Everingham, M., Van Gool, L., Williams, C.K.I., et al: ‘The PASCAL visual object classes challenge 2007 (VOC2007) results’, http://www.pascal-network.org/challenges/VOC/voc2007/workshop/index.html, accessed April 2017.
    17. 17)
      • 4. Girshick, R., Donahue, J., Darrell, T., et al: ‘Rich feature hierarchies for accurate object detection and semantic segmentation’. Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, 2014, pp. 580–587.
    18. 18)
      • 13. Chen, X., Ma, H., Wang, X., et al: ‘Improving object proposals with multi-thresholding straddling expansion’. Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, 2015, pp. 2587–2595.
    19. 19)
      • 16. Hou, X., Zhang, L.: ‘Saliency detection: a spectral residual approach’. Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, 2007, pp. 1–8.
    20. 20)
      • 1. Felzenszwalb, P.F., Girshick, R.B., McAllester, D., et al: ‘Object detection with discriminatively trained part-based models’, IEEE Trans. Pattern Anal. Mach. Intell., 2010, 32, (9), pp. 1627–1645.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2017.0208
Loading

Related content

content/journals/10.1049/iet-cvi.2017.0208
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading