Using Harris Corner Detection and Background Modeling for InPainting Occluded Objects in a Video

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    In this papera proposed ofan efficient method for video inpainting which can be used to remove a single unwanted object that obscured another wanted object in a period of time in a video scene that captured for two occluded objects only. The proposed system based on statistical modified background modeling and interest point detection for the wanted object. Occlusion is the most important challenge in video inpainting and the proposed method can handle this challenge with a good result and less computational cost.The system consists of the following main steps. Firstly, input the original video then estimate the background of the video. After that detect the foreground objects by subtraction the background. Then applying segment and labeling stage each foreground object. Followed by tracking the selected two objects. Thenanalysis the occluded frames with computing interest point for the wanted object in the non-occluded frames basing on Harris corner detector. The final stage filling the unwanted object pixels by two choices either background model pixels or wanted object pixels.The proposed system focus on interruption cases that may be happened by the unwanted object and blocking another wanted and important object. By applying this methodology, the process of inpainting the unwanted object with the keeping of consistency of video.



  • Keywords

    Video inpainting, Background model, Remove object, Video editing, Video tracking, occlusion.

  • References

      [1] Criminisi, P. Perez and K. Toyama, "Region filling and object removal by exemplar-based Image inpainting", Transaction on image processing IEEE, Vol. 13, No. 9, (2004).

      [2] Kader A. Patwardhan, Guillermo Sapiro and Marcelo Bertalmio, "Video inpainting under constrained camera motion", IEEE transaction on image processing, Vol.16, No.2, (2006).

      [3] Anu Rachel Abraham, A. KethsyPrabhavathy, PhD. J. Devi Shree, "A Survey on Video Inpainting", International Journal of Computer Applications, Vol.55 No.9, (2012).

      [4] Ali Mosleh, Nizar Bouguila and A. Ben Hamza, "An Automatic inpainting scheme for video text detection and removal", Transaction on image processing IEEE, Vol.22, No.11 (2013).

      [5] SamehZarif, IbrahimaFaya and DayangRohaya, "Static object removal from video scene using local similarity", International colloquium on signal processing and its applications IEEE, (2013).

      [6] Narendra Bhatewara, Prashant Kumar and Anupam Agrawal, "Intelligent video inpainting system for texture reconstruction", 4th International Conference on Computer and Communication Technology (ICCCT), (2013).

      [7] St-Charles, P. and G. Bilodeau. "Improving background subtraction using Local Binary Similarity Patterns". in IEEE Winter Conference on Applications of Computer Vision,(2014).

      [8] MouniraEbdelli, Olivier Le Meur, Christine Guillemot, "Video inpainting with short-term windows: application to object removal and error concealment", IEEE Transaction on Image Processing, IEEE, Vol.24 No.10, pp.3034-47, (2015).

      [9] Madbouly, A., M. Wafy, and M.-S.M. Mostafa, "Performance Assessment of Feature Detector-Descriptor Combination".International Journal of Computer Science Issues (IJCSI), Vol.12 No.50, p.87(2015).

      [10] Sixue. Yang, Juntao. Xue and Yunri. Zong, "Caption detection and removal from videoimages with complicated background using intelligent inpainting scheme", world congress on intelligent control and automation IEEE, (2016).

      [11] Datey, L., "Object Detection and Tracking From Video Using Support Vector Machine". International Journal of Advanced Research in Electronics and Communication Engineering (IJARECE), Vol.5 No.12, (2016).

      [12] T.Saikumar, MamathaNalavapani, "Mean-Shift Tracking Algorithm for Salient Object Detection in videos", International Journal of Advances in Computer Science and Technology, Vol.5 No.8, (2016).

      [13] IsraaHadi Ali and Roa`a M. Al-Airaji , "Processing for Intelligent Movie Editor", Asian journal of Information technology, Vol.15 No.16, (2016).

      [14] Peng, W., et al., "Harris Scale Invariant Corner Detection Algorithm Based on the Significant Region". International Journal of Signal Processing, Image Processing and Pattern Recognition, Vol.9 , No.3,p. 413-420,(2016).

      [15] Hassaballah, M., A.A. Abdelmgeid, and H.A. Alshazly, "Image features detection, description and matching, in Image Feature Detectors and Descriptors", Springer. p. 11-45, (2016).

      [16] Shweta K. Talmale, N.J.J., "Object Tracking In Images And Videos. International Journal Of Engineering And Computer Science", Vol.5 No.1: p. 5. (2016).

      [17] DivyaM ,R.k.A.V., "Single Object Tracking System By Using Labview". International Journal on Recent and Innovation Trends in Computing and Communication,Vol.4 , No.5,p. 5.(2016).

      [18] Jignasha H. Patel and Prof. Jignasa N. Patel , "A Survey : Different techniques of video inpainting" , International journal for scientific research & development vol.4 , No.12 (2017).

      [19] A.GhanbariTalouki, M. Majdi and S. A. Edalatpanah, "Video Inpainting Using a Contour-based Method in Presence of More than One Moving Objects", International Journal of Advanced Engineering and Management, Vol. 2, No. 2, pp. 37-44, (2017).

      [20] Tawfiq A. Al-Asadi and Fanar Ali Joda, "A Survey: Background Modelling and Object Detection Using Local Texture Features", Journal of Engineering and Applied Sciences, Vol.12 No.11, (2017).

      [21] IsraaHadi Ali and Qasim Jaleel, "Determining the Best Method to Extract Interest Point for Video Hidden Object Recovery". Journal of Engineering and Applied Sciences, Vol.13 No.1, (2018).

      [22] IsraaHadi Ali and M. Mustafa Ehsan, "Video Inpainting Based on Background Modelling". Journal of Engineering and Applied Sciences, Vol.13 No.6, (2018).




Article ID: 27983
DOI: 10.14419/ijet.v7i4.19.27983

Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.