Advertisement

Multimedia Tools and Applications

, Volume 73, Issue 1, pp 7–39 | Cite as

Distributed wide-area multi-object tracking with non-overlapping camera views

  • Youlu Wang
  • Senem VelipasalarEmail author
  • Mustafa Cenk Gursoy
Article

Abstract

We present a distributed system for wide-area multi-object tracking across disjoint camera views. Every camera in the system performs multi-object tracking, and keeps its own trackers and trajectories. The data from multiple features are exchanged between adjacent cameras for object matching. We employ a probabilistic Petri Net-based approach to account for the uncertainties of the vision algorithms (such as unreliable background subtraction, and tracking failure) and to incorporate the available domain knowledge. We combine appearance features of objects as well as the travel-time evidence for target matching and consistent labeling across disjoint camera views. 3D color histogram, histogram of oriented gradients, local binary patterns, object size and aspect ratio are used as the appearance features. The distribution of the travel time is modeled by a Gaussian mixture model. Multiple features are combined by the weights, which are assigned based on the reliability of the features. By incorporating the domain knowledge about the camera configurations and the information about the received packets from other cameras, certain transitions are fired in the probabilistic Petri net. The system is trained to learn different parameters of the matching process, and updated online. We first present wide-area tracking of vehicles, where we used three non-overlapping cameras. The first and the third cameras are approximately 150 m apart from each other with two intersections in the blind region. We also present an example of applying our method to a people-tracking scenario. The results show the success of the proposed method. A comparison between our work and related work is also presented.

Keywords

Video surveillance Object tracking Multi-camera tracking Non-overlapping camera views Probabilistic Petri-Nets 

References

  1. 1.
    Albanese M, Chellappa R, Moscato V, Picariello A (2008) A constrained probabilistic petri net framework for human activity detection in video. IEEE Trans Multimedia 10(8):1429–1443CrossRefGoogle Scholar
  2. 2.
    Anjum N, Cavallaro A (2009) Trajectory association and fusion across partially overlapping cameras. In: Proc. of the IEEE int’l conf. on advanced video and signal based surveillanceGoogle Scholar
  3. 3.
    Baltieri D, Vezzani R, Cucchiara R (2011) 3DPes: 3D people dataset for surveillance and forensics. In: Proc. of the 1st int’l ACM workshop on multimedia access to 3D human objects, pp 59–64Google Scholar
  4. 4.
    Black J, Ellis T, Rosin P (2002) Multi view image surveillance and tracking. In: Proc. of workshop on motion and video computing, pp 169–174Google Scholar
  5. 5.
    Cai Y, Huang K, Tan T (2008) Human appearance matching across multiple non-overlapping cameras. In: Proc. of the int’l conf. on pattern recognitionGoogle Scholar
  6. 6.
    Calderara S, Prati A, Vezzani R, Cucchiara R (2005) Consistent labeling for multi-camera object tracking. Image Analysis and Processing 3617:1206–1214Google Scholar
  7. 7.
    Cao X, Wu C, Lan J, Yan P, Li X (2011) Vehicle detection and motion analysis in low-altitude airborne video under urban environment. IEEE Trans Circuits Syst Video Technol 21(10):1522–1533Google Scholar
  8. 8.
    Casares M, Velipasalar S, Pinto A (2010) Light-weight salient foreground detection for embedded smart cameras. Comput Vis Image Underst 114(11):1223–1237CrossRefGoogle Scholar
  9. 9.
    Cheng E, Madden C, Piccardi M (2006) Mitigating the effects of variable illumination for tracking across disjoint camera views. In: Proc. of IEEE int’l conf. on video and signal based surveillanceGoogle Scholar
  10. 10.
    Chilgunde A, Kumar P, Ranganath S, Huang W (2004) Multi-camera target tracking in blind regions of cameras with non-overlapping fields of view. In: Proc. of the British machine vision conferenceGoogle Scholar
  11. 11.
    Cohen I, Ma Y, Miller B (2008) Associating moving objects across non-overlapping cameras: a query-by-example approach. In: Proc. of IEEE conf. on technologies for homeland security, pp 566–571Google Scholar
  12. 12.
    Comaniciu D, Ramesh V, Meer P (2000) Real-time tracking of non-rigid objects using mean shift. In: Proc. of IEEE conf. on computer vision and pattern recognition, pp 142–149Google Scholar
  13. 13.
    Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proc. of IEEE Computer Society conf. on computer vision and pattern recognition, vol 1, pp 886–893Google Scholar
  14. 14.
    David R, Alla H (1994) Petri Nets for modeling of dynamic systems. Automatica 30(2):175–202MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    del-Blanco C, Mohedano R, Garcia N, Salgado L, Jaureguizar F (2008) Color-based 3D particle filtering for robust tracking in heterogeneous environments. In: Proc. of 2nd ACM/IEEE int’l conf. on distributed smart camerasGoogle Scholar
  16. 16.
    D’Orazio T, Mazzeo P, Spagnolo P (2009) Color brightness transfer function evaluation for non overlapping multi camera tracking. In: Proc. of ACM/IEEE int’l conf. on distributed smart camerasGoogle Scholar
  17. 17.
    Geismann P, Knoll A (2010) Speeding up hog and lbp features for pedestrian detection by multiresolution techniques. In: Proc. of the int’l conf. on advances in visual computing, pp 243–252Google Scholar
  18. 18.
    Huang T, Russell S (1998) Object identification: a Bayesian analysis with application to traffic surveillance. Artif Intell 103(1–2):77–93CrossRefzbMATHGoogle Scholar
  19. 19.
    Huang C, Chiu W, Wang S, Chuang J (2010) Probabilistic modeling of dynamic traffic flow across non-overlapping camera views. In: Proc. of the int’l conf. on pattern recognitionGoogle Scholar
  20. 20.
    Jacobs RA (2002) What determines visual cue reliability? Trends Cogn Sci 6(8):345–350CrossRefGoogle Scholar
  21. 21.
    Javed O, Rasheed Z, Shafique K, Shah M (2003) Tracking across multiple cameras with disjoint views. In: Proc. of IEEE int’l conf. on computer vision, vol 2, pp 952–957Google Scholar
  22. 22.
    Javed O, Shafique K, Shah M (2005) Appearance modeling for tracking in multiple non-overlapping cameras. In: Proc. of IEEE conf. on computer vision and pattern recognition, vol 2, pp 26–33Google Scholar
  23. 23.
    Jeong K, Jaynes C (2008) Object matching in disjoint cameras using a color transfer approach. Mach Vis Appl 19(5):443–455CrossRefzbMATHGoogle Scholar
  24. 24.
    Kang J, Cohan I, Medioni G (2005) Persistent objects tracking across multiple non overlapping cameras. In: Proc. of the IEEE workshop on motion and video computingGoogle Scholar
  25. 25.
    Khan S, Shah M (2003) Consistent labeling of tracked objects in multiple cameras with overlapping fields of view. IEEE Trans Pattern Anal Mach Intell 25(10):1355–1360CrossRefGoogle Scholar
  26. 26.
    Madden C, Piccardi M (2007) A framework for track matching across disjoint cameras using robust shape and appearance features. In: Proc. of IEEE conf. on advanced video and signal based surveillance, pp 188–193Google Scholar
  27. 27.
    Makris D, Ellis T, Black J (2004) Bridging the gaps between cameras. In: Proc. of IEEE Computer Society conf. on computer vision and pattern recognitionGoogle Scholar
  28. 28.
    Moller B, Plotz T, Fink G (2008) Calibration-free camera hand-over for fast and reliable person tracking in multi-camera setups. In: Proc. of the 19th int’l conf. on pattern recognitionGoogle Scholar
  29. 29.
    Monari E, Maerker J, Kroschel K (2009) A robust and efficient approach for human tracking in multi-camera systems. In: Proc. of the IEEE int’l conf. on advanced video and signal based surveillance, pp 134–139Google Scholar
  30. 30.
    Murata T (1989) Petri Nets: properties, analysis and applications. Proc IEEE 77(4):541–580CrossRefGoogle Scholar
  31. 31.
    Niu C, Grimson E (2006) Recovering non-overlapping network topology using far-field vehicle tracking data. In: Proc. of the int’l conf. on pattern recognitionGoogle Scholar
  32. 32.
    Ojala T, Pietikainen M, Harwood D (1996) A comparative study of texture measures with classification based on feature distributions. Pattern Recogn 29(1):51–59CrossRefGoogle Scholar
  33. 33.
    Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24(7):971–987CrossRefGoogle Scholar
  34. 34.
    Pflugfelder R, Bischof H (2008) Tracking across non-overlapping views via geometry. In; Proc. of the int’l conf. on pattern recognitionGoogle Scholar
  35. 35.
    Porikli F (2003) Inter-camera color calibration by correlation model function. In: Proc. of IEEE int’l conf. on image processingGoogle Scholar
  36. 36.
    Prosser B, Gong S, Xiang T (2008) Multi-camera matching using bi-directional cumulative brightness transfer functions. In: British machine vision conferenceGoogle Scholar
  37. 37.
    Rahimi A, Dunagan B, Darrell T (2004) Simultaneous calibration and tracking with a network of non-overlapping sensors. In: Proc. of IEEE Computer Society conf. on computer vision and pattern recognition, vol 1, pp I-187–I-194Google Scholar
  38. 38.
    Triesch J, von der Malsburg C (2001) Democratic integration: self-organized integration of adaptive cues. Neural Comput 13(9):2049–2074CrossRefzbMATHGoogle Scholar
  39. 39.
    Velipasalar S, Schlessman J, Chen C, Wolf W, Singh J (2008) A scalable clustered camera system for multiple object tracking. EURASIP J Image Video Process 542808Google Scholar
  40. 40.
    Wang X, Han T, Yan S (2009) An HOG-LBP human detector with partial occlusion handling. In: Proc. of int’l conf. on computer vision, pp 32–38Google Scholar
  41. 41.
    Wang Y, Velipasalar S, Gursoy M (2010) Wide-area multi-object tracking with non-overlapping camera views. In: Proc. of IEEE int’l conf. on multimedia and expoGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2012

Authors and Affiliations

  • Youlu Wang
    • 1
  • Senem Velipasalar
    • 2
    Email author
  • Mustafa Cenk Gursoy
    • 2
  1. 1.Dept. of Electrical EngineeringUniversity of Nebraska-LincolnLincolnUSA
  2. 2.Electrical Engineering and Computer Science DepartmentSyracuse UniversitySyracuseUSA

Personalised recommendations