© The Institution of Engineering and Technology
The authors describe their approach to segmenting moving road vehicles from the colour video data supplied by a stationary roadside closed-circuit television (CCTV) camera and classifying those vehicles in terms of type (car, van and heavy goods vehicle) and dominant colour. For the segmentation, the authors use a recursively updated Gaussian mixture model approach, with a multi-dimensional smoothing transform. The authors show that this transform improves the segmentation performance, particularly in adverse imaging conditions, such as when there is camera vibration. The authors then present a comprehensive comparative evaluation of shadow detection approaches, which is an essential component of background subtraction in outdoor scenes. For vehicle classification, a practical and systematic approach using a kernelised support vector machine is developed. The good recognition rates achieved in the authors’ experiments indicate that their approach is well suited for pragmatic vehicle classification applications.
References
-
-
1)
-
F. Melgani ,
L. Bruzzone
.
Classification of hyperspectral remote sensing images with support vector machines.
IEEE Trans. Geosci. Remote Sens.
,
8 ,
1778 -
1790
-
2)
-
9. Martel-Brisson, N., Zaccarin, A.: ‘Learning and removing cast shadows through a multidistribution approach’, IEEE Trans. Pattern Anal. Mach. Intell., 2007, 29, (7), pp. 1133–1146 (doi: 10.1109/TPAMI.2007.1039).
-
3)
-
29. Blanz, V., Scholkopf, B., Bulthoff, H., Burges, C., Vapnik, V., Vetter, T.: ‘Comparison of view-based object recognition algorithms using realistic 3d models’, in: Von der Malsburg, C., Von Seelen, W., Vorbrüggen, J.C., Sendhoff, B., editors. ‘Artificial Neural Networks – ICANN'96’, (Springer, 1996), 1112, pp. 251–256 (doi: 10.1007/3-540-61510-5_45).
-
4)
-
D. Comaniciu ,
P. Meer
.
Mean shift: a robust approach toward feature space analysis.
IEEE Trans. Pattern Anal. Mach. Intell.
,
5 ,
603 -
619
-
5)
-
V.N. Vapnik
.
An overview of statistical learning theory.
IEEE Trans. Neural Netw.
,
988 -
999
-
6)
-
A. Prati ,
I. Mikic ,
M. Trivedi ,
R. Cucchiara
.
Detecting moving shadows: algorithms and evaluation.
IEEE Trans. Pattern Anal. Mach. Intel.
,
7 ,
918 -
923
-
7)
-
D.G. Lowe
.
Distinctive image features from scale-invariant keypoints.
Int. J. Comput. Vis
,
2 ,
91 -
110
-
8)
-
11. Zang, W., Wu, Q.M.J., Yang, X., Fang, X.: ‘Multilevel framework to detect and handle vehicle occlusion’, IEEE Trans. Intell. Transp. Syst., 2008, 9, (1), pp. 161–174 (doi: 10.1109/TITS.2008.915647).
-
9)
-
R. Cucchiara ,
C. Grana ,
M. Piccardi ,
A. Prati
.
Detecting moving objects, ghosts, and shadows in video streams.
IEEE Trans. Pattern Anal. Mach. Intell.
,
10 ,
1337 -
1342
-
10)
-
10. Johansson, B., Wiklund, J., Forssen, P.E., Granlund, G.: ‘Combining shadow detection and simulation for estimation of vehicle size and position’, Pattern Recognit. Lett., 2009, 30, (8), pp. 751–759 (doi: 10.1016/j.patrec.2009.03.005).
-
11)
-
O. Chapelle ,
P. Haffner ,
V.N. Vapnik
.
Support vector machines for histogram-based image classification.
IEEE Trans. Neural Netw.
,
5 ,
1055 -
1064
-
12)
-
Z. Zivkovic ,
F. van der Heijden
.
Efficient adaptive density estimation per image pixel for the task of background subtraction.
Pattern Recognit. Lett.
-
13)
-
C. Stauffer ,
W. Grimson
.
Learning patterns of activity using real time tracking.
IEEE Trans. Pattern Anal. Mach. Intell.
,
8 ,
747 -
757
-
14)
-
2. Wang, Y., Malinovskiy, Y., Wu, Y.: ‘Occlusion robust and environment insensitive algorithm for vehicle detection and tracking using surveillance video cameras’. , 2008.
-
15)
-
D.-S. Lee
.
Effective Gaussian mixture learning for video background subtraction.
IEEE Trans. Pattern Anal. Mach. Intell.
,
5 ,
827 -
832
-
16)
-
37. Canu, S., Grandvalet, Y., Guigue, V., Rakotomamonjy, A.: ‘Svm and kernel methods matlab toolbox’, .
-
17)
-
19. Ma, X., Grimson, W.: ‘Edge-based rich representation for vehicle classification’. Int. Conf. Computer Vision, 2005, pp. 1185–1192.
-
18)
-
34. Comaniciu, D., Meer, P.: ‘Mean shift: A robust approach toward feature space analysis’, IEEE Trans. Pattern Anal. Mach. Intell., 2002, 24, (5), pp. 603–619 (doi: 10.1109/34.1000236).
-
19)
-
3. Buch, N., Velastin, S., Orwell, J.: ‘A review of computer vision techniques for the analysis of urban traffic’, IEEE Trans. Intell. Transp. Syst., 2011, 99, pp. 1–20.
-
20)
-
12. Wang, J., Ma, Y., Li, C., Wang, H., Liu, J.: ‘An efficient multi-object tracking method using multiple particle filters’. WRI World Congress on Computer science and Information Engineering, 2009, pp. 568–572.
-
21)
-
7. Power, P., Schoonees, J.: ‘Understanding background mixture models for foreground segmentation’. Proc. Image and Vision Computing, New Zealand, 2002.
-
22)
-
29. Blanz, V., Scholkopf, B., Bulthoff, H., Burges, C., Vapnik, V., Vetter, T.: ‘Comparison of view-based object recognition algorithms using realistic 3d models’, in: Von der Malsburg, C., Von Seelen, W., Vorbrüggen, J.C., Sendhoff, B., editors. ‘Artificial Neural Networks – ICANN'96’, (Springer, 1996), 1112, pp. 251–256 (doi: 10.1007/3-540-61510-5_45).
-
23)
-
25. Vapnik, V.: ‘Estimation of dependences based on empirical data’ (Springer, Berlin, 1982).
-
24)
-
35. Horprasert, T., Harwood, D., Davis, L.: ‘A statistical approach for real-time robust background subtraction and shadow detection’. Proc. IEEE ICCV'99 Frame rate workshop, 1999.
-
25)
-
17. Baek, N., Park, S., Kim, K., Park, S.: ‘Vehicle color classification based on the support vector machine method’, ICIC, CCIS 2, 2007, 2, pp. 1133–1139.
-
26)
-
11. Zang, W., Wu, Q.M.J., Yang, X., Fang, X.: ‘Multilevel framework to detect and handle vehicle occlusion’, IEEE Trans. Intell. Transp. Syst., 2008, 9, (1), pp. 161–174 (doi: 10.1109/TITS.2008.915647).
-
27)
-
13. Prati, A., Mikic, I., Trivedi, M., Cucchiara, R.: ‘Detecting moving shadows: algorithms and evaluation’, IEEE Trans. Pattern Anal. Mach. Intell., 2003, 25, (7), pp. 918–923 (doi: 10.1109/TPAMI.2003.1206520).
-
28)
-
4. Nieto, M., Unzueta, L., Cortes, A., Barandiaran, J., Otaegui, O., Sanchez, P.: ‘Real-time 3d modeling of vehicles in low-cost monocamera systems’. Proc. Int. Conf. Computer Vision Theory and Applications VISAPP2011, 2011, pp. 459–464.
-
29)
-
26. Vapnik, V.: ‘The nature of statistical learning theory’ (Springer, New York, 1995).
-
30)
-
21. Zhang, C., Chen, X., Chen, W.: ‘A pca-based vehicle classification framework’. Int. Conf. Data Engineering Workshops (ICDEW'06), 2006.
-
31)
-
33. Chen, Z., Husz, Z., Wallace, I., Wallace, A.: ‘Video object tracking based on a chamfer distance transform’. IEEE Int. Conf. Image Processing, San Antonio, Texas, USA, 2007, pp. 357–360.
-
32)
-
24. Ortes, C., Vapnik, V.: ‘Support vector network’, Mach. Learn., 1995, 20, pp. 1–25.
-
33)
-
31. Scholkopf, B., Burges, C., Vapnik, V.: ‘Extracting support data for a given task’. Proc. First Int. Conf. Knowledge Discovering and data Mining, 1995, pp. 252–257.
-
34)
-
10. Johansson, B., Wiklund, J., Forssen, P.E., Granlund, G.: ‘Combining shadow detection and simulation for estimation of vehicle size and position’, Pattern Recognit. Lett., 2009, 30, (8), pp. 751–759 (doi: 10.1016/j.patrec.2009.03.005).
-
35)
-
22. Vapnik, V., Chervonenkis, A.: ‘A note on one class of perceptrons’, Autom. Remote Control, 1964, 25, pp. 821–837.
-
36)
-
20. Lowe, D.: ‘Distinctive image features from scale invariant keypoints’, Int. J. Comput. Vis., 2004, 60, (2), pp. 91–110 (doi: 10.1023/B:VISI.0000029664.99615.94).
-
37)
-
16. Cucchiara, R., Piccardi, M., Prati, A.: ‘Detecting moving objects, ghosts and shadows in video streams’, IEEE Trans. Pattern Anal. Mach. Intell., 2003, 25, (10), pp. 1337–1342 (doi: 10.1109/TPAMI.2003.1233909).
-
38)
-
30. Melgani, F., Bruzzone, L.: ‘Classification of hyperspectral remote sensing images with support vector machines’, IEEE Trans. Geosci. Remote Sens., 2004, 42, (8), pp. 1778–1790 (doi: 10.1109/TGRS.2004.831865).
-
39)
-
9. Martel-Brisson, N., Zaccarin, A.: ‘Learning and removing cast shadows through a multidistribution approach’, IEEE Trans. Pattern Anal. Mach. Intell., 2007, 29, (7), pp. 1133–1146 (doi: 10.1109/TPAMI.2007.1039).
-
40)
-
37. Canu, S., Grandvalet, Y., Guigue, V., Rakotomamonjy, A.: ‘Svm and kernel methods matlab toolbox’, .
-
41)
-
32. Jain, R., Kasturi, R., Schunck, B.: ‘Machine vision. McGraw-Hill series in Computer Science’ (McGraw-Hill, Inc., New York, NY, 1995).
-
42)
-
27. Vapnik, V.: ‘An overview of statistical learning theory’, IEEE Trans. Neural Netw., 1999, 10, (5), pp. 988–999 (doi: 10.1109/72.788640).
-
43)
-
28. Chapelle, O., Haffner, P., Vapnik, V.: ‘Support vector machines for histogram-based image classification’, IEEE Trans. Neural Netw., 1999, 10, (5), pp. 1055–1064 (doi: 10.1109/72.788646).
-
44)
-
2. Wang, Y., Malinovskiy, Y., Wu, Y.: ‘Occlusion robust and environment insensitive algorithm for vehicle detection and tracking using surveillance video cameras’. , 2008.
-
45)
-
1. Zivkovic, Z., Heijden, F.: ‘Efficient adaptive density estimation per image pixel for the task of background subtraction’, Pattern Recognit. Lett., 2006, 27, (7), pp. 773–780 (doi: 10.1016/j.patrec.2005.11.005).
-
46)
-
36. Joachims, T.: ‘Training linear svms in linear time’. Proc. 12th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (KDD'06), Philadelphia, Pennsylvania, USA, 2006, pp. 217–226.
-
47)
-
6. Stauffer, C., Grimson, W.: ‘Learning patterns of activity using real-time tracking’, IEEE Trans. Pattern Anal. Mach. Intell., 2000, 22, (8), pp. 747–757 (doi: 10.1109/34.868677).
-
48)
-
23. Vapnik, V., Lerner, A.: ‘Pattern recognition using generalized portrait method’, Autom. Remote Control, 1963, 24, pp. 774–780.
-
49)
-
18. Ambardekar, A., Nicolescu, M., Bebis, G.: ‘Efficient vehicle tracking and classification for an automated traffic surveillance system’, Proc. Signal Image Process., 2008.
-
50)
-
15. Finlayson, G., Hordley, S., Drew, M.: ‘Removing shadows from images’. European Conf. Computer Vision, 2002 (LNCS, 2353), no (4), pp. 823–836.
-
51)
-
14. Elgammal, A., Harwood, A., Davis, L.: ‘Non-parametric model for background subtraction’. Proc. Sixth European Conf. Computer Vision-Part II 1843, 2000 (LNCS), pp. 751–767.
-
52)
-
8. Lee, D.-S.: ‘Effective gaussian mixture learning for video background subtraction’, IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, (5), pp. 827–832 (doi: 10.1109/TPAMI.2005.102).
-
53)
-
5. Friedman, N., Russell, S.: ‘Image segmentation in video sequences: A probabilistic approach’. Proc 13th Conf. Uncertainty in Artificial Intelligence, 1997, pp. 175–181.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2012.0104
Related content
content/journals/10.1049/iet-its.2012.0104
pub_keyword,iet_inspecKeyword,pub_concept
6
6