Pattern Analysis and Applications

, Volume 10, Issue 4, pp 291–299 | Cite as

Salient human detection for robot vision

Theoretical Advances


In this paper, we propose a salient human detection method that uses pre-attentive features and a support vector machine (SVM) for robot vision. From three pre-attentive features (color, luminance and motion), we extracted three feature maps and combined them as a salience map. By using these features, we estimated a given object’s location without pre-assumptions or semi-automatic interaction. We were able to choose the most salient object even if multiple objects existed. We also used the SVM to decide whether a given object was human (among the candidate object regions). For the SVM, we used a new feature extraction method to reduce the feature dimensions and reflect the variations of local features to classifiers by using an edged-mosaic image. The main advantage of the proposed method is that our algorithm was able to detect salient humans regardless of the amount of movement, and also distinguish salient humans from non-salient humans. The proposed algorithm can be easily applied to human robot interfaces for human-like vision systems.


Salient human detection Pre-attentive features Support vector machine Color map Luminance map Motion map 



This research was supported by the Ministry of Information and Communication, Korea under the Information Technology Research Center support program supervised by the Institute of Information Technology Assessment, IITA-2005-(C1090-0501-0019).


  1. 1.
    Scassellati B (2002) Theory of mind for a humanoid robot. Auton Robots 12:13–24MATHCrossRefGoogle Scholar
  2. 2.
    Treisman A (1985) Preattentive processing in vision. Comp Vis Graph Image Process 31:156–177CrossRefGoogle Scholar
  3. 3.
    Zhao L, Charles CE (2000) Stereo and neural network-based pedestrian detection. IEEE Trans ITS 1:148–154Google Scholar
  4. 4.
    Haritaoglu I, Harwood D, Davis LS (2000) W4: real-time surveillance of people and their activities. IEEE Trans PAMI 22:809-830Google Scholar
  5. 5.
    Papageorgiou C, Oren M, Poggio T (1998) A general framework for object detection. In: International conference on computer vision, pp 555–562Google Scholar
  6. 6.
    Mohan A, Papageorgiou C, Poggio T (2001) Example-based object detection in images by components. IEEE Trans PAMI 23:349-361Google Scholar
  7. 7.
    Gavrila DM, Giebel J (2002) Shape-based pedestrian detection and tracking. Intelligent Vehicle Symp 1:8–14Google Scholar
  8. 8.
    Moghaddam B, Yang MH (2000) Gender classfication with support vector machines. In: IEEE international conference on automatic face and gesture recognition, pp 306-311Google Scholar
  9. 9.
    Itti L, Koch C, Niebur E (2000) A model of saliency based visual attention for rapid scene analysis. IEEE Trans PAMI 20:1254–1259Google Scholar
  10. 10.
    Jung B, Sukhatme GS (2004) Detecting moving objects suing a single camera on a mobile robot in an outdoor environment. In: International conference on intelligent automomous systems, pp 980–987Google Scholar
  11. 11.
    Viola P, Jones MJ, Snow D (2005) Detecting pedestrians using patterns of motion and appearance. Int J Comp Vis 63:153–161CrossRefGoogle Scholar
  12. 12.
    Oren M, Papageorgiou C, Sinha P, Osuna E, Poggio T (1997) Pedestrian detection using wavelet templates. In: International conference on computer vision and pattern recognition, pp 193–199Google Scholar
  13. 13.
    Wolfe JM (1994) A revised model of visual search. Psychon Bull Rev 1:202–238Google Scholar
  14. 14.
    Lucas B, Kanade T (1987) An iterative image registration technique with an application to stereo vision. In: Proceedings of 7th international joint conference on artificial intelligence, pp 674-679Google Scholar

Copyright information

© Springer-Verlag London Limited 2007

Authors and Affiliations

  1. 1.Department of Computer ScienceYonsei UniversitySeoulSouth Korea
  2. 2.Department of Computer EngineeringKeimyung UniversityDaeguSouth Korea

Personalised recommendations