© The Institution of Engineering and Technology
Pedestrians are the most vulnerable urban traffic participants. In order to better protect them in pre-crash scenarios, it is necessary to detect them. Unfortunately, pedestrian detection is very difficult in highly cluttered urban scenarios, using cameras mounted on moving vehicle. A novel approach to walking pedestrian detection, using dense stereo vision systems, is presented. Multiple features combined into a Bayesian framework are used to yield a high rate of pedestrian detection. The feature set includes simple features such as width, height, lateral and longitudinal speed. It also includes complex motion features, such as the variance of the motion field caused by the pedestrians' legs and arms moving during walking and the periodicity of the pedestrians' walking pattern.
References
-
-
1)
-
Havasi, L., Szlvik, Z., Szirnyi, T.: `Pedestrian detection using derived third-order symmetry of legs', Proc. Int. Conf. Computer Vision and Graphics, 2004.
-
2)
-
Lucas, B., Kanade, T.: `An iterative image registration technique with an application to stereo vision', Proc. 7th Int. Joint Conf. Artificial Intelligence (IJCAI), 1981, p. 674–679.
-
3)
-
B.K.P. Horn ,
B.G. Schunck
.
Determining optical flow.
Artif. Intell.
,
185 -
203
-
4)
-
J.-Y. Bouguet
.
(2000)
Pyramidal implementation of the Lucas–Kanade feature tracker.
-
5)
-
P.D. Welch
.
The use of fast Fourier transform for the estimation of power spectra: a method based on time averaging over short, modified periodograms.
IEEE Trans. Audio Electroacoust.
,
70 -
73
-
6)
-
D.M. Gavrila
.
A Bayesian exemplar-based approach to hierarchical shape matching.
IEEE Trans. Pattern Anal. Mach. Intell.
,
8
-
7)
-
Gavrila, D.M., Giebel, J., Munder, S.: `Vision-based pedestrian detection: the PROTECTOR system', Intelligent Vehicles Symp., June 2004, p. 13–18, available at: www.gavrila.net/iv04protector.pdf.
-
8)
-
Mählisch, M., Oberländer, M., Lählein, O., Gavrila, D., Ritter, W.: `A multiple detector approach to low-resolution pedestrian recognition', Proc. IEEE Intelligent Vehicles Symp., 2005, Las Vegas, USA, available at: www.gavrila.net/Publications/iv05.pdf.
-
9)
-
D.M. Gavrila
.
The visual analysis of human movement: a survey.
Comput. Vis. Image Underst.
,
1 ,
82 -
98
-
10)
-
Shashua, A., Gdalyahu, Y., Hayun, G.: `Pedestrian detection for driving assistance systems: single-frame classification and system level performance', IEEE Intelligent Vehicle Symp., June 2004, p. 1–6.
-
11)
-
Loy, G., Fletcher, L., Apostoloff, N., Zelinsky, A.: `An adaptive fusion architecture for target tracking', Proc. 5th International Conf. Automatic Face and Gesture Recognition, 2002, p. 261–266.
-
12)
-
Viola, P., Jones, M.J., Snow, D.: `Detecting pedestrians using patterns of motion and appearance', Proc. Ninth IEEE Int. Conf. Computer Vision, 2003, 2, available at: www.merl.com/papers/docs/TR2003-90.pdf.
-
13)
-
Woodfill, J.I., Gordon, G., Buck, R.: `Tyzx deepsea high speed stereo vision system', Proc. IEEE Computer Society Workshop on Real Time 3-D Sensors and Their Use, Conf. Computer Vision and Pattern Recognition, June 2004, available at: www.tyzx.com/pubs/CVPR3DWorkshop2004.pdf.
-
14)
-
Harville, M., Rahimi, A., Darrell, T., Gordon, G., Woodfill, J.: `3D pose tracking with linear depth and brightness constraints', Proc. IEEE Int. Conf. Computer Vision, 1999, 1, p. 206–213, available at: http://www.tyzx.com/pubs/ICCV99.pdf.
-
15)
-
Leibe, B., Seemann, E., Schiele, B.: `Pedestrian detection in crowded scenes', Proc. 2005 IEEE Computer Society Conf. Computer Vision and Pattern Recognition, 2005, 1, available at: www.mis.informatik.tu-darmstadt.de/Publications/leibe-crowdedscenes-cvpr05.pdf.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its_20070039
Related content
content/journals/10.1049/iet-its_20070039
pub_keyword,iet_inspecKeyword,pub_concept
6
6