On Generation of Silhouette of Moving Objects from Video

  • Soharab Hossain Shaikh
  • Sugam Kumar Bhunia
  • Nabendu Chaki
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 221)


Object classification from video is a well known topic of research in the context of computer vision. Video processing for the purpose of real time object classification and action recognition has great importance in building an intelligent surveillance system. This paper proposes a novel technique for extracting human silhouette from video in real time. Identification of the moving human objects is performed first using frame differencing technique followed by a number of steps for extraction of the human silhouette. The proposed method has been tested on a good number of videos having varying textured background with noise related to illumination change. The proposed method can also be applied for extraction of silhouettes of other types of animate and inanimate moving objects from a video with the view of object classification and recognition. The experimental results as documented in the paper establish the effectiveness of the proposed method.


Moving object detection Frame differencing Human silhouette extraction Online video processing Surveillance video 


  1. 1.
    Garrett AZ, Satio H (2009) Real-time online video object silhouette extraction using graph cuts on the GPU, In: Proceedings of the 15th international conference on image analysis and processing, Springer, Heidelberg, 985–994Google Scholar
  2. 2.
    Dedeoğlu Y, Töreyin UB, Güdükbay U, Çetin EA (2006) Silhouette-based method for object classification and human action recognition in video, HCI/ECCV, LNCS 3979, 64–77Google Scholar
  3. 3.
    Shaikh SH, Chaki N (2011) A low cost moving object detection method using boundary tracking, springer proceedings of the international conference on computer science engineering and applications (ICCSEA)Google Scholar
  4. 4.
    Shireen YE, Khaled ME, Sumaya HA (2008) Moving object detection in spatial domain using background removal techniques–state-of-art. Recent Patents Comput Sci 1:32–54CrossRefGoogle Scholar
  5. 5.
    Seki M, Fujiwara H, Sumi K (2000) A robust background subtraction method for changing background. In: proceedings IEEE workshop applications of computer vision, (2000) 207–213Google Scholar
  6. 6.
    DeCann B, Ross A (2010) Gait curves for human recognition, backpack detection and silhouette correction in a night time environment. In: Proceedings of SPIE conference on biometric technology for human identification 7, April, Orlando, USAGoogle Scholar
  7. 7.
    Barnich O, Jodogne S, Droogenbroeck VM (2006) Robust analysis of silhouettes by morphological size distributions, LNCS, vol 4179. Springer, Verlag, 734–745Google Scholar
  8. 8.
    Ekinci M, Gedikli E (2005) Silhouette based human motion detection and analysis for real-time automated video surveillance. Turk J Elec Engin 13(2):199–229Google Scholar
  9. 9.
    Wang L, Tan T, Ning H, Hu W (2003) Silhouette analysis-based gait recognition for human identification, vol 25(12). IEEE transactions on pattern analysis and machine intelligence, December, 1505–1518Google Scholar
  10. 10.
    Barnich O, Droogenbroeck VM (2009) Design of a morphological moving object signature and application to human identification, IEEE international conference on acoustics, speech and signal processing (ICASSP), 853–856Google Scholar
  11. 11.
    Gonzalez CR, Woods ER (1997) Digital image processing, second edition. Pearson Education North Asia Ltd and Publishing House of Electronics IndustryGoogle Scholar

Copyright information

© Springer India 2013

Authors and Affiliations

  • Soharab Hossain Shaikh
    • 1
  • Sugam Kumar Bhunia
    • 1
  • Nabendu Chaki
    • 2
  1. 1.A.K.Choudhury School of Information TechnologyUniversity of CalcuttaKolkataIndia
  2. 2.Department of Computer Science and EngineeringUniversity of CalcuttaKolkataIndia

Personalised recommendations