Obstacle avoidance in person following for vision-based autonomous land vehicle guidance using vehicle location estimation and quadratic pattern classifier
Ch. Ku et Wh. Tsai, Obstacle avoidance in person following for vision-based autonomous land vehicle guidance using vehicle location estimation and quadratic pattern classifier, IEEE IND E, 48(1), 2001, pp. 205-215
An obstacle avoidance method for use in person following for vision-based a
utonomous land vehicle (ALV) guidance is proposed. This method is based on
the use of vehicle location estimation and a quadratic pattern classifier,
and aims to guide the ALV to follow a walking person in front by navigating
along a derived collision-free path. Before generating the collision-free
path, the person's location is obtained from extracted objects in the image
by a person detection method. The object closest to a predicted person loc
ation is regarded as the followed person and the remaining objects are rega
rded as obstacles. The collision-free navigation path is designed for ALV g
uidance in such a way that the ALV not only can keep following the person b
ut also can avoid collision with nearby obstacles. The navigation path resu
lts from a quadratic classifier that uses the vehicle and all of the object
s in the image as input patterns. A turn angle is then computed to drive th
e ALV to follow the navigation path. Successful navigation sessions confirm
the feasibility of the approach.