Advertisement

Dense Flow-Based Video Object Segmentation in Dynamic Scenario

  • Arati Kushwaha
  • Om Prakash
  • Rajneesh Kumar Srivastava
  • Ashish Khare
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 524)

Abstract

Segmenting object from a moving camera is a challenging task due to varying background. When camera and object both are moving, then object segmentation becomes more difficult and challenging in video segmentation. In this paper, we introduce an efficient approach to segment object in moving camera scenario. In this work, first step is to stabilize the consecutive frame changes by the global camera motion and then to model the background, non-panoramic background modeling technique is used. For moving pixel identification of object, a motion-based approach is used to resolve the problem of wrong classification of motionless background pixel as foreground pixel. Motion vector has been constructed using dense flow to detect moving pixels. The quantitative performance of the proposed method has been calculated and compared with the other state-of-the-art methods using four measures, such as average difference (AD), structural content (SC), Jaccard coefficients (JC), and mean squared error (MSE).

Keywords

Object segmentation Moving camera Dense flow Non-panoramic model Background modeling 

References

  1. 1.
    Vrigks, M., Nikou, C. & Kakadiaries, L. A. (2015). A review of human activity recognition methods. Frontiers in Robotics and AI, 2(28).Google Scholar
  2. 2.
    Ke, S.-R., Uyen Thuc, H.-L, Lee, Y.-L., Hwang, J.-N., Yoo, J.-H., & Choi, K.-H. (2013). A review on video-based human activity recognition. Computers, 2, 88–131.CrossRefGoogle Scholar
  3. 3.
    Ko, T., Soatto, S., & Estrin, D. (2010). Warping background subtraction. In 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1331–1338).Google Scholar
  4. 4.
    Stauffer, C., & Grimson, W. (1999). Adaptive background mixture models for real-time tracking. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Vol. 2, pp. 246–252).Google Scholar
  5. 5.
    Tavakkoli, A., Nicolescu, M., Bebis, G., & Nicolescu, M. (2009). Nonparametric statistical background modeling for efficient forackground modelling from n detection. Machine Vision Applications, 20, 395–409.CrossRefGoogle Scholar
  6. 6.
    Bouwmans, T., El Baf, F., & Vachon, B. (2008). Background modeling using mixture of gaussians for foreground detection—a survey. Recent Patents on Computer Science, 1(3), 219–237.CrossRefGoogle Scholar
  7. 7.
    Cho, S. H., & Hang, B. K. (2011). Panoramic background generation using mean-shift in moving camera environment. In Proceedings of the International Conference on Image Processing, Computer Vision, and Pattern Recognition.Google Scholar
  8. 8.
    Guillot, C., Taron M., Sayd, P., Pha, Q. C., Tilmant, C., & Lavest, J. M. (2010). Background subtraction adapted to pan tilt zoom cameras by key point density estimation. In Computer Vision–ACCV Workshops (pp. 33–42), Springer: Berlin Heidelberg.Google Scholar
  9. 9.
    Xue, K., Liu, Y., Ogunmakin, G., Chen, J., & Zhang, J. (2013). Panoramic Gaussian Mixture Model and large-scale range background substraction method for PTZ camera-based surveillance systems. Machine Vision and Applications, 24(3), 477–492.CrossRefGoogle Scholar
  10. 10.
    Robinault, L., Bres, S., & Miguet, S. (2009). Real time foreground object detection using pan tilt zoom camera. VISSAPP, 1, 609–614.Google Scholar
  11. 11.
    Murray, D., & Basu, A. (1994). Motion tracking with an active camera. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16, 449–459.CrossRefGoogle Scholar
  12. 12.
    Xue, K., Liu, Y., Ogunmakin, G., Chen, J., & Zhang, J (2013). Panoramic Gaussian Mixture Model and large-scale range background substraction method for PTZ camera-based surveillance systems. Machine Vision and Applications, 24, 477–492.CrossRefGoogle Scholar
  13. 13.
    Viswanath, A., Kumari Beherab, R., Senthamilarasub, V., & Kutty, K. (2015). Background modelling from a moving camera. Procedia Computer Science, 58, 289–296.CrossRefGoogle Scholar
  14. 14.
    Kim, S. K., Yun. K., Yi, K. M., Kim, S. J., & Choi, H. Y. (2013). Detection of moving objects with a moving camera using non-panoramic background model. Machine Vision and Applications, 24, 1015–1028.CrossRefGoogle Scholar
  15. 15.
    Yi, K., Yun, K., Kim, S., Chang, H., & Choi, J. (2013). Detection of moving objects with non-stationary cameras in 5.8 ms: Bringing motion detection to your mobile device. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (pp. 27–34).Google Scholar
  16. 16.
    Kurnianggoro, L., Shahbaz, A., & Jo, K.-H. (2016). Dense optical flow in stabilized scenes for moving object detection from a moving camera. In 16th International Conference on Control, Automation and Systems (ICCAS 2016), October 16–19. HICO, Gyeongju, Korea.Google Scholar
  17. 17.
    Kadim, Z., Daud, M. M, Radzi, S. S. M., Samudin, N., & Woon, H. H. (2013). Method to detect and track moving object in non-static PTZ camera. In Proceedings of the International MultiConference of Engineers and Computer Scientists, 3 (Vol. I) IMECS 2013, March 13–15, Hong Kong.Google Scholar
  18. 18.
    Hu, W.-C., Chen, C.-H., Chen,T.-Y., & Huang, D.-Y., & Wu, Z.-C. (2015). Moving object detection and tracking from video captured by moving camera. Journal of Visual Communication and Image Representation, 30, 164–180.CrossRefGoogle Scholar
  19. 19.
    Lucas, B. D., & Kanade, T. (1981). An iterative image registration technique with an application to stereo vision. In International Joint Conference on Artificial Intelligence (pp. 674–679).Google Scholar
  20. 20.
    Khare, M., & Srivastava, R. K. (2012). Level set method for segmentation of medical images without reinitialization. Journal of Medical Imaging and Health Informatics, 2(2), 158–167.CrossRefGoogle Scholar
  21. 21.
    Rosin, P., & Ioannidis, E. (2003). Evaluation of global image thresholding for change detection. Pattern Recognition Letters, 24(14), 2345–2356.CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Arati Kushwaha
    • 1
  • Om Prakash
    • 2
  • Rajneesh Kumar Srivastava
    • 1
  • Ashish Khare
    • 1
  1. 1.Department of Electronics and CommunicationUniversity of AllahabadAllahabadIndia
  2. 2.Department of Computer Science and EngineeringNirma UniversityAhmedabadIndia

Personalised recommendations