© The Institution of Engineering and Technology
A new approach for standing and walking pedestrian detection using pattern matching and exploiting both 2D image information and 3D dense stereo information is proposed. Because 3D information accuracy does not allow the direct classification of the 3D shape, a combined 3D–2D method is proposed. The 3D data are used in an innovative way for pedestrian hypotheses generation, scale and depth estimation and 2D models selection. Also the 3D hypotheses allow the corresponding 2D image region of interest selection and the 2D hypothesis generation. The 2D hypothesis consists of the object's external edges obtained by an edge extraction and a depth coherency-based filtering out process. The scaled models are matched against the selected hypothesis using an elastic high-speed matching based on the Chamfer distance. The method has been tested on synthetic and real-world scenarios.
References
-
-
1)
-
Kelly, P., Cooke, E., O'Connor, N.E., Smeaton, A.F.: `Pedestrian detection using stereo and biometric information', Int. Conf. Image Analysis and Recognition ICIAR (2), 2006, p. 802–813.
-
2)
-
S. Nedevschi ,
C. Vancea ,
T. Marita ,
T. Graf
.
On-line calibration method for stereovision systems used in far range detection vehicle applications.
IEEE Trans. Intell. Transp. Syst.
,
4 ,
651 -
660
-
3)
-
Gandhi, T., Trivedi, M.: `Pedestrian collision avoidance systems: a survey of computer vision based recent studies', Proc. IEEE Intelligent Transportation Systems Conf., IEEE ITSC, 2006, Toronto, Canada, p. 17–20.
-
4)
-
Rucklidge, W.: `Locating objects using the Hausdorff distance', Proc. Int. Conf. Computer Vision, 1995, p. 457–464.
-
5)
-
L. Zhao ,
C. Thorpe
.
Stereo and neural network-based pedestrian detection.
IEEE Trans. Intell. Transp. Syst.
,
3 ,
148 -
154
-
6)
-
M.A. Butt ,
P. Maragos
.
Optimum design of chamfer distance transform.
IEEE Trans. Image Process.
,
10 ,
1477 -
1484
-
7)
-
Gavrila, D.M.: `Pedestrian detection from a moving vehicle', Proc. European Conf. Computer Vision, 2000, Dublin, p. 37–49.
-
8)
-
Broggi, A., Fascioli, A., Grisleri, P., Graf, T., Meinecke, M.: `Model-based validation approaches and matching techniques for automotive vision based pedestrian detection', Proc. 2005 IEEE Computer Society Conf. Computer Vision and Pattern Recognition (CVPR'05) – Workshops, 2005, San Diego, 3, p. 1.
-
9)
-
Bertozzi, M., Binelli, E., Broggi, A., Rose, M.D.: `Stereo vision-based approaches for pedestrian detection', Proc. 2005 IEEE Computer Society Conf. Computer Vision and Pattern Recognition (CVPR'05) – Workshops, 2005, 3, p. 16.
-
10)
-
D.P. Huttenlocher ,
G.A. Klanderman ,
W.J. Rucklidge
.
Comparing images using the Hausdorff distance.
IEEE Trans. Pattern Anal. Mach. Intell.
,
9 ,
850 -
863
-
11)
-
Nedevschi, S., Danescu, R., Marita, T.: `A sensor for urban driving assistance systems based on dense stereovision', Proc. IEEE Intelligent Vehicles Symp. (IV 2007), 2007, Istanbul, Turkey.
-
12)
-
Gavrila, D., Giebel, J., Munder, S.: `Vision-based pedestrian detection: the PROTECTOR system', Proc. IEEE Intelligent Vehicles Symp, June 2004, p. 13–18.
-
13)
-
Gavrila, D.M., Philomin, V.: `Real-time object detection for smart vehicles', Proc. IEEE Int. Conf. Computer Vision, 1999, Kerkyra, Greece, p. 87–93.
-
14)
-
Huber, D., Kapuria, A., Donamukkala, R., Hebert, M.: `Parts-based 3D object classification', Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR 04), June 2004, p. 82–89.
-
15)
-
Osada, R., Funkhouser, T., Chazelle, B., Dobkin, D.: `Matching 3D models with shape distributions', Proc. Int. Conf. Shape Modeling and Applications, 2001, p. 154–166.
-
16)
-
D.M. Gavrila
.
Sensor-based pedestrain protection.
IEEE Intell. Syst.
,
5 ,
7 -
81
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its_20070038
Related content
content/journals/10.1049/iet-its_20070038
pub_keyword,iet_inspecKeyword,pub_concept
6
6