© The Institution of Engineering and Technology
Every year, backing-up crashes are responsible for hundreds of casualties in the world. In order to reduce this number, many automotive suppliers now provide ways for drivers to monitor the rear of their vehicle using sonar - or radar-based systems or wide angle cameras. Yet these systems still do not offer the performance required to consequently reduce the number of fatalities. To overcome the limitations of these systems, we have developed a real-time static obstacle detection system using a wide angle camera. We now propose to add moving obstacle detection and localisation to our camera-based system. Such system is the perfect candidate for next generation of automatic anti-collision systems. Our approach is based on camera movement compensation using inverse perspective mapping and probabilistic reasoning for movement detection. Using shape filtering, our approach can even limit detection to specific types of moving objects (pedestrians, cars etc.). We present the algorithms developed and the evaluation protocol used. We also show results of the system in typical urban situations, some in hard conditions (worst cases), and conclude on which future developments will bring performance improvements.
References
-
-
1)
-
U. Franke ,
S. Heinrich
.
Fast obstacle detection for urban traffic situation.
IEEE Trans. Intell. Transport. Syst.
,
3 ,
173 -
181
-
2)
-
Fablet, R., Black, M.J.: `Automatic detection and tracking of human motion with a view-based representation', Proc. of European Conf. on Computer Vision, 2002, p. 476–491.
-
3)
-
Bertozzi, M., Broggi, A., Fascioli, A., Lombardi, P.: `Vision-based pedestrian detection: will ants help?', Proc. of IEEE Intelligent Vehicles Symp, June 2002, Versailles.
-
4)
-
A. Broggi ,
A. Fascioli ,
M. Carletti ,
T. Meinecke
.
A multi-resolution approach for infrared vision-based pedestrian detection.
IEEE Intell. Vehicle Symp.
,
7 -
12
-
5)
-
H.A. Mallot ,
H.H. Bülthoff ,
J.J. Little ,
S. Bohrer
.
Inverse perspective mapping simplifies optical flow computation and obstacle detection.
Biol. Cybern.
,
177 -
85
-
6)
-
Masoud, O., Papanikolopoulos, N.P.: `A robust real-time multi-level model-based pedestrian tracking system', Proc. of the ITS America Seventh Annual Meeting, June 1997, Washington, DC.
-
7)
-
Fintzel, K., Bendahan, R., Vestri, C., Bougnoux, S., Kakinami, T.: `3D parking assistant system', 11thWorld Congress on Intelligent Transport Systems, 2004, Nagoya, Japan.
-
8)
-
Giebel, J., Gavrila, D.M.: `A Bayesian framework for Multi-cue 3D object tracking', Proc. of European Conf. on Computer Vision, 2004, Springer, p. 241–252.
-
9)
-
Abramson, Y., Steux, B.: `Hardware-friendly pedestrian detection and impact prediction', Proc. of IEEE Intelligent Vehicles Symp, June 2004.
-
10)
-
Sidenbladh, H.: `Detecting human motion with support vector machines', Proc. of IAPR Int. Conf. on Pattern Recognition, 2004, 2, Cambridge, UK, p. 188–191.
-
11)
-
Fuerstenberg, K.Ch., Dietmayer, K.C.J., Eisenlauer, S., Willhoeft, V.: `Multilayer laserscanner for robust object tracking and classification in urban traffic scenes', Proc. of ITS 2002, 9th World Congress on Intell. Transport Systems, October 2002, Chicago, ITS 2002, Paper 2054..
-
12)
-
AISIN SEIKI Parking Assist System, http://www.aisin.com/products/auto/info.html, accessed November 2006.
-
13)
-
R. Cutler ,
L.S. Davis
.
Robust real-time periodic motion detection, analysis and applications.
IEEE Trans. Pattern Anal. Machine Intell.
,
8 ,
781 -
796
-
14)
-
L. Zhao ,
C. Thorpe
.
Stereo- and neural network-based pedestrian detection.
IEEE Trans. Intell. Trans. Syst.
,
3 ,
148 -
154
-
15)
-
Takayama, M., Tanaka, Y., Kakinami, T., Iwata, Y.: `Driving assistance system using rear-view camera', 8thWorld Congress on Intelligent Transport Systems, October 2001, Sydney, Australia.
-
16)
-
Papageorgiou, C., Poggio, T.: `Trainable pedestrian detection', Proc. of Int. Conf. on Image Processing (ICIP'99), October 1999, Kobe, Japan.
-
17)
-
U. Franke ,
D.M. Gavrila ,
S. Gorzig ,
F. Lindner ,
F. Paetzold ,
C. Wohler
.
Autonomous driving goes downtown.
IEEE Intell. Syst.
,
6 ,
40 -
48
-
18)
-
Lee, L., Dalley, G., Tieu, K.: `Learning pedestrian models for silhouette refinement', Proc. of Int. Conf. on Computer Vision and Pattern Recognition, 2003.
-
19)
-
Broggi, A., Bertozzi, M., Fascoli, A., Sechi, M.: `Shape-based pedestrian detection', Proc. of IEEE Intelligent Vehicle Symp, 2000, Dearborn, U.S.A, p. 215–220.
-
20)
-
, : `Vehicle backover avoidance technology study', Report to Congress, November 2006.
-
21)
-
Shashua, A., Gdalyahu, Y., Hayon, G.: `Pedestrian detection for driving assistance systems: single-frame classification and system level performance', Proc. of the IEEE Intelligent Vehicles Symp, (IV2004), June 2004, Parma, Italy.
-
22)
-
Lipton, A., Fujiyoshi, H., Patil, R.: `Moving target classification and tracking from real-time video', Proc. of the 1998 DARPA Image Understanding Workshop (IUW'98), November 1998.
-
23)
-
Gavrila, D., Philomin, V.: `Real-time object detection for smart vehicles', Proc. of Int. Conf. on Computer Vision, 1999, p. 87–93.
-
24)
-
Lefaix, G., Marchand, E., Bouthemy, P.: `Motion-based obstacle detection and tracking for car driving assistance', Proc. of IAPR Int. Conf. on Pattern Recognition (ICPR'2002), August 2002, Québec, Canada, 4, p. 74–77.
-
25)
-
http://www.toyota.co.jp/en/tech/its/program/function/parking.html, accessed November 2006.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its_20060060
Related content
content/journals/10.1049/iet-its_20060060
pub_keyword,iet_inspecKeyword,pub_concept
6
6