A Real-time Object Detection System Using Selected Principal Components

  • Jong-Ho Kim
  • Byoung-Doo Kang
  • Sang-Ho Ahn
  • Heung-Shik Kim
  • Sang-Kyoon Kim
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 240)


The detection of moving objects is a basic and necessary preprocessing step in many applications such as object recognition, context awareness, and intelligent visual surveillance. Among these applications, object detection for context awareness impacts the efficiency of the entire system and it requires rapid detection of accurate shape information, a challenge specially when a complicated background or a background change occurs. In this paper, we propose a method for detecting a moving object rapidly and accurately in real time when changes in the background and lighting occur. First, training data collected from a background image are linearly transformed using principal component analysis (PCA). Second, an eigen-background is organized from selected principal components with excellent ability to discriminate between object and background. Finally, an object is detected by convoluting the eigenvector organized in the previous step with an input image, the result of which is the input value used on an EM algorithm. An image sequence that includes various moving objects at the same time is organized and used as training data to realize a system that can adapt to changes in lighting and background. Test results show that the proposed method is robust to these changes, as well as to the partial movement of objects.


Object detection Principal Components Analysis (PCA) Eigen-background Mixture of Gaussian 


  1. 1.
    Yyilmaz A, Javed O, Shah M (2006) Object tracking: a survey. ACM J Comput Surv 38:1–45CrossRefGoogle Scholar
  2. 2.
    Stein AN, Herbert M (2009) Local detection of occlusion boundaries in video. Image Vis Comput 27:514–522CrossRefGoogle Scholar
  3. 3.
    Horn BKP, Schunck NG (1981) Determining optical flow. Artif Intell 17:185–203CrossRefGoogle Scholar
  4. 4.
    Itti L, Koch C, Niebur E (1998) A model of saliency-based visual attention for rapid scene analysis. IEEE Trans PAMI 20:1254–1259CrossRefGoogle Scholar
  5. 5.
    MCHugh JM, Konrad J, Saligrama V, Jodoin PM (2009) Foreground-adaptive background subtraction. IEEE Signal Process Lett 16:390–393Google Scholar
  6. 6.
    Rymel J, Renno J, Greenhill D, Orwell J, Jones GA (2004) Adaptive eigen-backgrounds for object detection. In: International conference on image processing, vol 3, pp 1847–1850Google Scholar
  7. 7.
    Zhang J, Zhuang Y (2007) Adaptive weight selection for incremental eigen-background modeling. In: International conference on multimedia and expo, pp 851–854Google Scholar
  8. 8.
    Turk MA, Pentland AP (1991) Face recognition using eigenfaces. In: IEEE conference on computer vision and pattern recognition. pp 586–591Google Scholar
  9. 9.
    Cheung SCS, Kamath C (2005) Robust techniques for background subtraction in urban traffic video. J Appl Signal Process 1:2330–340Google Scholar
  10. 10.
    Yang MS, Wu KL, Hsieh JN, Yu J (1999) Alpha-cut implemented fuzzy clustering algorithms and switching regressions. IEEE Trans Syst 18:1117–1128Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht(Outside the USA) 2013

Authors and Affiliations

  • Jong-Ho Kim
    • 1
  • Byoung-Doo Kang
    • 2
  • Sang-Ho Ahn
    • 3
  • Heung-Shik Kim
    • 1
  • Sang-Kyoon Kim
    • 1
  1. 1.Department of Computer EngineeringInje UniversityGimhaeRepublic of Korea
  2. 2.Researcher, STAR TeamKorea Electronics Technology InstituteBucheon-siRepublic of Korea
  3. 3.Department of Electronic EngineeringInje UniversityGimhaeRepublic of Korea

Personalised recommendations