Defocus Map-Based Segmentation of Automotive Vehicles

  • Senthil Kumar ThangavelEmail author
  • Nirmala Rajendran
  • Karthikeyan Vaiapury
Conference paper
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 30)


Defocus estimation plays a vital role in segmentation and computer vision applications. Most of the existing work uses defocus map for segmentation, matting, decolorization and salient region detection. In this paper, we propose to use both defocus map and grabcut using wavelet for reliable segmentation of the image. The result shows the comparative analysis between the bi-orthogonal and Haar function using wavelet, grabcut and defocus map. Experimental results show promising results, and hence, this algorithm can be used to obtain the defocus map of the scene.


Defocus map Segmentation Wavelet Grabcut 



This work is performed as a part of internship with TCS Innovation Lab.


  1. 1.
    Chen D-J, Chen H-T, Chang L-W (2016) Fast defocus map estimation. In: 2016 IEEE international conference on image processing (ICIP). IEEEGoogle Scholar
  2. 2.
    Jiang P, Ling H, Yu J, Peng J (2013) Salient region detection by UFO: uniqueness, focusness and objectness. In: IEEE international conference on computer vision, ICCV 2013, Sydney, Australia, 1–8 Dec 2013, pp 1976–1983Google Scholar
  3. 3.
    Lin HT, Tai Y, Brown MS (2011) Motion regularization for matting motion blurred objects. IEEE Trans Pattern Anal Mach Intell 33(11):2329–2336CrossRefGoogle Scholar
  4. 4.
    Namboodiri VP, Chaudhuri S (2008) Recovery of relative depth from a single observation using an uncalibrated (real-aperture) camera. In: 2008 IEEE computer society conference on computer vision and pattern recognition (CVPR 2008), 24–26 June 2008, Anchorage, Alaska, USAGoogle Scholar
  5. 5.
    Peng Y, Zhao X, Cosman PC (2015) Single underwater image enhancement using depth estimation based on blurriness. In: 2015 IEEE international conference on image processing, ICIP 2015, Quebec City, QC, Canada, 27–30 Sept 2015, pp 4952–4956Google Scholar
  6. 6.
    Ashutosh S, Chung SH, Ng AY (2005) Learning depth from single monocular images. NIPS 18:1–8Google Scholar
  7. 7.
    Zhuo S, Sim T (2011) Defocus map estimation from a single image. Pattern Recogn 44(9):1852–1858CrossRefGoogle Scholar
  8. 8.
    Petrova J, Hostalkova E (2011) Edge detection in medical image using the wavelet transform. Report of research, Department of Computing and Control Engineering, Czech PublicGoogle Scholar
  9. 9.
    Brannock, E, Weeks M (2006) Edge detection using wavelets. In: Proceedings of the 44th annual Southeast regional conference, pp 649–654. ACMGoogle Scholar
  10. 10.
    Moreno-Noguer F, Belhumeur PN, Nayar SK (2007) Active refocusing of images and videos. ACM Trans Graph 26(3):67–75CrossRefGoogle Scholar
  11. 11.
    Levin A, Fergus R, Durand F, Freeman WT (2007) Image and depth from a conventional camera with a coded aperture. ACM Trans Graph 26(3):70–78CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Senthil Kumar Thangavel
    • 1
    Email author
  • Nirmala Rajendran
    • 2
  • Karthikeyan Vaiapury
    • 2
  1. 1.Department of Computer Science and EngineeringAmrita School of Engineering, Amrita Vishwa VidyapeethamCoimbatoreIndia
  2. 2.TCS Research and Innovation, Tata Consultancy ServicesChennaiIndia

Personalised recommendations