Page 124 - Dynamic Vision for Perception and Control of Motion

3 Subjects and Subject Classes
108

sheep, goats, deer, dogs, cats, etc.; birds and poultry are two-legged animals, many
of which are able to fly.
Because of the eminent importance of humans and four-legged animals in any
kind of road traffic, autonomous vehicles should be able to understand the motion
capabilities of these living beings in the long run. This is out into the future right
now; the final section of this chapter shows an approach and first results developed
in the early 1990s for recognition of humans. This field has seen many activities
since the early work of Hogg (1984) in the meantime and has grown to a special
area in technical vision; two recent papers with application to road traffic are [Ber-
tozzi et al. 2004; Franke et al. 2005]

3.6.1 Simple Model of Human Body as Traffic Participant

Elaborate models for the motion ca-
Head 10
(with neck) (13 neck) pabilities of human bodies are avail-
able in different disciplines of physi-
0 1 0, 1
shoulders ology, sports, and computer
0, 1 upper
upper 0 1 animation [Alexander 1984; Bruderlin,
torso
arms 9 2, 3 Calvert 1989; Kroemer 1988]. Humans
2 3 elbows
12 as traffic participants with the behav-
2, 3 8 lower 12 waist
lower 2 3 ioral modes of walking, running, rid-
arms 6 7 6, 7 ing bicycles or motor bikes as well as
hips
4 5 modes for transmitting information
4, 5 4 5 4, 5
upper hands by waving their arms, possibly with
legs additional instruments, show a much
8 9 8, 9 knees
reduced set of stereotypical move-
6, 7 ments. Kinzel (1994a, b), therefore, se-
lower 6 7
legs lected the articulated body model
10, 11 shown in Figure 3.29 to represent
10 11
feet
humans in traffic activities in connec-
Body segments joints tion with the 4-D approach to dy-
namic vision. Visual recognition of
Figure 3.29. Simple generic model for hu- moving humans becomes especially
man shape with 22 degrees of freedom, af-
difficult due to the vast variety of
ter [Kinzel 1994]
clothing encountered and of objects
carried. For normal Western style
clothing the cyclic activities of extremities are characteristic of humans moving.
Motion of limbs should be separated from body motion since they behave in dif-
ferent modes and at different eigenfrequencies, usually.
Limbs tend to be used in typical cyclic motion, while the body moves more
steadily. The rotational movements of limbs may be in the same or in opposite di-
rection depending on the style and the phase of grasping or running.
Figure 3.30 shows early results achieved with the lower part of the body model
from Figure 3.29; cyclic motion of the upper leg (hip angle, amplitude § 60°, upper
graph) and the lower leg (knee angle, amplitude § 100°, bottom graph) has been
recognized roughly in a computer simulation with real-time image sequence