© The Institution of Engineering and Technology
A particle filter (PF) has been recently proposed to detect and track colour objects in video. This study presents an adaptation of the PF to track people in surveillance video. Detection is based on automated background modelling rather than a manually generated object colour model. Furthermore, a labelling method is proposed to create tracks of objects through the scene, rather than unconnected detections. A methodical comparison between the new PF tracking method and two other multi-object trackers is presented on the PETS 2004 benchmark data set. The PF tracker gives significantly fewer false alarms owing to explicit modelling of the object birth and death processes, while maintaining a good detection rate.
References
-
-
1)
-
A. Baumann ,
M. Boltz ,
J. Ebling
.
A review and comparison of measures for automatic video surveillance systems.
EURASIP J. Image Video Process.
,
30 -
59
-
2)
-
Jones, R., Ristic, B., Redding, N., Booth, D.: `Moving target indication and tracking from moving sensors', ‘Digital image computing techniques and applications, (IEEE Computer Society, Cairns, Australia, December 2005).
-
3)
-
Boers, Y., Driessen, H.: `The mixed labeling problem in multi target particle filtering', Tenth Int. Conf. on Information Fusion, July 2007, Quebec.
-
4)
-
M. Isard ,
A. Blake
.
Condensation-conditional density propagation for visual tracking.
Int. J. Comput. Vis.
,
1 ,
5 -
28
-
5)
-
Comaniciu, D., Ramesh, V., Meer, P.: `Real-time tracking of non-rigid objects using mean shift', IEEE Conf. on Computer Vision and Pattern Recognition, June 2000, p. 142–149, Hilton Head, SC.
-
6)
-
Fisher, R.: `PETS04 surveillance ground truth data set', Proc. Sixth IEEE Int. Workshop on Performance Evaluation of Tracking and Surveillance, May 2004, p. 1–5.
-
7)
-
B. Ristic ,
S. Arulampalam ,
N. Gordon
.
(2004)
Beyond the Kalman filter: particle filters for tracking applications.
-
8)
-
Shen, C., Brooks, M.J., van den Hengel, A.: `Fast global kernel density mode seeking with application to localization and tracking', IEEE Int. Conf. on Computer Vision, 2005, p. 1516–1523.
-
9)
-
Welch, G., Bishop, G.: `An introduction to the Kalman filter', 95-041, Technical report, , Department of Computer Science, University of North Carolina at Chapel Hill, 1995.
-
10)
-
C. Rasmussen ,
G. Hager
.
Probabilistic data association methods for tracking complex visual objects.
IEEE Trans. Pattern Anal. Mach. Intell.
,
6 ,
560 -
576
-
11)
-
E. Maggio ,
M. Taj ,
A. Cavallaro
.
Effcient multitarget visual tracking using random finite sets.
IEEE Trans. Circuits Syst. Video Technol.
,
8 ,
1016 -
1027
-
12)
-
K. Nummiaro ,
E. Koller-Meierb ,
L.V. Gool
.
An adaptive colour-based particle filter.
Image Vis. Comput.
,
99 -
110
-
13)
-
J. Czyz ,
B. Ristic ,
B. Macq
.
A particle filter for joint detection and tracking of colour objects.
Image Vis. Comput.
,
1271 -
1281
-
14)
-
G. Bradski ,
A. Kaehler
.
(2008)
Learning openCV: computer vision with the OpenCV library.
-
15)
-
S. Blackman ,
R. Popoli
.
(1999)
Design and analysis of modern tracking systems.
-
16)
-
A. Doucet ,
N. de Freitas ,
N. Gordon
.
(2001)
Sequential Monte Carlo methods in practice.
-
17)
-
Gabriel, P., Verly, J., Piater, J., Genon, A.: `The state of the art in multiple object tracking under occlusion in video sequences', Proc. Advanced Concepts for Intelligent Vision Systems, 2003, p. 166–173.
-
18)
-
I. Haritaoglu ,
D. Hartwood ,
L.S. Davis
.
Real-time surveillance of people and their activities.
IEEE Trans. Pattern Anal. Mach. Intell.
,
809 -
830
-
19)
-
J. Carpenter ,
P. Clifford ,
P. Fearnhead
.
Improved particle filter for nonlinear problems.
IEE Proc. Radar, Sonar Navig.
,
1 ,
2 -
7
-
20)
-
T. Kirubarajan ,
Y. Bar-Shalom ,
K.R. Pattipati
.
Multiassignment for tracking a large number of overlapping objects.
IEEE Trans. Aerosp. Electron. Syst.
,
1 ,
2 -
21
-
21)
-
D. Comaniciu ,
V. Ramesh ,
P. Meer
.
Kernel-based object tracking.
IEEE Trans. Pattern Anal. Mach. Intell.
,
564 -
577
-
22)
-
MacCormick, J., Blake, A.: `A probabilistic exclusion principle for tracking multiple objects', IEEE Int. Conf. on Computer Vision, September 1999, Corfu, Greece, 1, p. 572–578.
-
23)
-
Pérez, P., Hue, C., Varmaak, J., Gangnet, M.: `Color-based probabilistic tracking', Proc. European Conf. on Computer Vision (ECCV), 2002, p. 661–675, (LNCS, 2350).
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2010.0026
Related content
content/journals/10.1049/iet-cvi.2010.0026
pub_keyword,iet_inspecKeyword,pub_concept
6
6