A Hybrid Approach for Object Proposal Generation

  • Muhammd Aamir
  • Yi-Fei Pu
  • Waheed Ahmed Abro
  • Hamad Naeem
  • Ziaur Rahman
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 506)


Object detection in natural images is evolving, with enormous commercial achievements, becoming relatively common in every industry. Modern research in this area is progressing in many directions, with numerous different techniques being proposed to achieve state-of-the-art detection performance. Recent object detection methods use two steps to detect high-quality objects: first, it generates a set of object proposals as accurate as possible, and then these proposals are passed to object classifier for post-classification. This paper presents an efficient new hybrid object proposal method, which gets the initial proposal by computing multiple hierarchical segmentations using super pixels and then ranks the proposal according to region score – which is defined as number of contours wholly enclosed in the proposed region, passing only the top object proposal for the post-classification. Passing few object proposals in the object detection pipeline for post-classification speeds up the object detection process. This paper demonstrates that our method results in high-quality class-independent object locations, with mean average best overlap of 0.833 at 1500 locations, resulting in a superior detection rate in object detection tasks at relatively fast speeds – as compared to object detection methods using selective search – and greatly reduces the false-positive rate.


Object detection Object proposal Image segmentation 



This work was supported by the National Natural Science Foundation of China under grants 61571312, Academic and Technical Leaders Support Foundation of Sichuan province under grants (2016)183-5, and National Key Research and Development Program Foundation of China under grants 2017YFB0802300. The authors would like to thank Ms. Siobhan Kathryn He for the constructive criticism of the manuscript.


  1. 1.
    Uijlings JRR, van de Sande KEA, Gevers T, Smeulders AWM (2013) Selective search for object recognition. Inter J Comp Vision 104(2):154–171CrossRefGoogle Scholar
  2. 2.
    Zitnick CL, Dollár P (2014) Edge boxes: locating object proposals from edges. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer vision – ECCV 2014. Lecture notes in computer science, vol 8693. Springer, ChamGoogle Scholar
  3. 3.
    Girshick RB, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE conference on computer vision and pattern recognition, pp 580–587CrossRefGoogle Scholar
  4. 4.
    Felzenszwalb PF, Huttenlocher DP (2004) Efficient graph-based image segmentation. Inter J Comp Vision 59(2):167–181CrossRefGoogle Scholar
  5. 5.
    Carreira J, Sminchisescu C (2012) Cpmc: automatic object segmentation using constrained parametric min-cuts. PAMI 34(7):1312CrossRefGoogle Scholar
  6. 6.
    Endres I, Hoiem D (2014) Category-independent object proposals with diverse ranking. PAMI 36:222CrossRefGoogle Scholar
  7. 7.
    Rantalankila P, Kannala J, Rahtu E (2014) Generating object segmentation proposals using global and local search. In: Computer vision and pattern recognition (CVPR), 2014 IEEE conference on. IEEE, pp 2417–2424Google Scholar
  8. 8.
    Alexe B, Deselaers T, Ferrari V (2012) Measuring the objectness of image windows. PAMI 34(11):2189CrossRefGoogle Scholar
  9. 9.
    Rahtu E, Kannala J, Blaschko M (2011) Learning a category independent object detection cascade. In: Computer vision (ICCV), 2011 IEEE international conference on. IEEE, pp 1052–1059Google Scholar
  10. 10.
    Cheng M-M, Zhang Z, Lin W-Y, Torr P (2014) BING: Binarized normed gradients for objectness estimation at 300fps. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3286–3293Google Scholar
  11. 11.
    Dollar P, Zitnick CL (2014) Fast edge detection using structured forests. CoRR abs/1406.5549Google Scholar
  12. 12.
    Everingham M, Ali Eslami SM, Van Gool L, Williams CKI, Winn J, Zisserman A (2015) The pascal visual object classes challenge: a retrospective. Inter J Comp Vision 111(1):98–136CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  • Muhammd Aamir
    • 1
  • Yi-Fei Pu
    • 1
  • Waheed Ahmed Abro
    • 2
  • Hamad Naeem
    • 1
  • Ziaur Rahman
    • 1
  1. 1.College of Computer Science Sichuan UniversityChengduChina
  2. 2.School of Computer Science and EngineeringSoutheast UniversityNanjingChina

Personalised recommendations