A.3.6.7 Detection and recognition of a ditch

In several applications, driving cross-country at speeds up to ~ 20 km/h is desirable. Usually, the ground is not completely flat so that perturbations in pitch and bank (roll) are considerably higher than on roads. In addition, the effects even of low vegetation on visibility of ditches are important.

In the figure above, self-occlusion of a negative obstacle is sketched; the ground on the near side of the ditch occludes most of the area of the slope on the far side. It turned out in experiments with VaMoRs that for picking up first indications of a ditch at larger distances,

• looking for area- or edge-based features in the tele image was more reliable than trying to derive these indications from stereo images; (full frames at full video rate have been available with the ACADIA-board from PVT, Sarnoff-approach).
• When closing in, correlation-based stereo interpretation with its formidable computing power provided better results than feature-based EMS-vision.
• Saccadic ditch perception has been developed and is treated in [Pellkofer et al. 2003; Hofmann 2004]

video 26 Detect ditch, Stop VaMoRs 2000

video 33

EMS On-Off-Road Mission Performance 2003

References

Baten S, Lützeler M, Dickmanns ED, Mandelbaum R, Burt P (1998).  Techniques for Autonomous, Off-Road Navigation. IEEE Intelligent Systems, Vol. 13, No. 6, pp 57-65

Gregor R, Lützeler M, Dickmanns ED (2001).  EMS-Vision: Combining on- and off-road driving. Proc. SPIE Conf. on Unmanned Ground Vehicle Technology III, AeroSense ‘01, Orlando (FL). Abstract (and part of Introd.)

Gregor R, Lützeler M, Pellkofer M, Siedersberger K-H, Dickmanns ED (2001).   A Vision System for Autonomous Ground Vehicles with a Wide Range of Maneuvering Capabilities. Proc. ICVS, Vancouver

Pellkofer M, Lützeler M, Dickmanns ED (2001). Interaction of Perception and Gaze Control in Autonomous Vehicles. Proc. SPIE: Intelligent Robots and Computer Vision XX; Newton, USA, pp 1-12. Abstract

Pellkofer M, Lützeler M, Dickmanns ED (2001). Vertebrate-type perception and gaze control for road vehicles. Proc. Int. Symp. on Robotics Research, Lorne, Australia. pdf

Siedersberger K-H, Pellkofer M, Lützeler M, Dickmanns ED, Rieder A, Mandelbaum R, Bogoni I (2001). Combining EMS-Vision and Horopter Stereo for Obstacle Avoidance of Autonomous Vehicles. Proc. ICVS, Vancouver

Gregor R, Lützeler M, Pellkofer M, Siedersberger KH, Dickmanns ED (2002). EMS-Vision: A Perceptual System for Autonomous Vehicles. IEEE Trans. on Intelligent Transportation Systems, Vol.3, No.1, pp. 48 – 59

Pellkofer M, Hofmann U, Dickmanns ED (2003). Autonomous cross-country driving using active vision. SPIE Conf. 5267, Intelligent Robots and Computer Vision XXI: Algorithms, Techniques, and Active Vision. Photonics East, Providence, Rhode Island

Pellkofer M (2003).  Verhaltensentscheidung für autonome Fahrzeuge mit Blickrichtungssteuerung. Dissertation, UniBwM, LRT. Kurzfassung

Hofmann U (2004). Zur visuellen Umfeldwahrnehmung autonomer Fahrzeuge. Dissertation, UniBwM, LRT. Kurzfassung

Dickmanns ED (2007). Dynamic Vision for Perception and Control of Motion. Springer-Verlag, (Section 14.6.6) Content