... 19 4 G. Unal et al.
Fig. 5 .15 . A walking person (Frames shown L-R-top-bottom) is tracked by the
polygonal tracker
18 0 G. Unal et al.
Fig. 5.5. Two rays-swimming video noisy ... prediction using optical flow
normal component
Fig. 5 .14 . A swimming fish in a rocky terrain in the sea (Frames 1, 10 , 20, 30, 40,
70, 11 0, 14 3 are shown left-right-top-bottom). Rows 1 and...
... pattern-windows follows them, as
shown in Fig. 1. 11. c, as equation (7) indicates. The pattern-windows will
38 M. Mata et al.
Fig. 1. 27. Landmark map of room 1. 3C13 and room sweep with detected land-
marks
Fig. ... 1 Learning Visual Landmarks for Mobile Robot Topological Navigation 33
Fig. 1. 22. RWI B- 21 test robot and laboratories and computer vision system
Wi...
... vol. 21, pp. 24 7-2 58.
18 Fahlman, S. E. (19 98) “An empirical study of learning speed in back-
propagation networks”. CMU-CS-8 8 -1 62.
19 Franz, Matthias O. (19 98) Learning view graphs for robot ... recognition [9, 10 , 11 ] and object tracking
[12 , 13 , 14 ], one usually needs a real-time coordination between sensory
perception and motor control [15 ]. A biological...
... Schwartz, “The local structure of space-
variant images”, Neural Network, vol. 10 (5), pp. 815 –8 31, 19 97.
3. On-line Model Learning for Mobile Manipulations 10 7
211
211
cossin
1
sincos
1
vvf
m
y
vvf
m
x
cc
c
c
cc
c
c
... pp. 411 –435, 19 80.
86. J.M. Foley, “Binocular distance perception: Egocentric visual task”,
Journal of experimental Psychology, vol. 11 , pp. 1...
... International
Conference on Robotics and Automation, pp. 11 24, 11 29, 20 01.
10 T. Mitchell, Machine Learning, McGraw Hill, 19 97.
11 L. P. Kaelbling, M. L. Littman, and A. W. Moore, “Reinforcement
learning: ... 15 02 15 08, November 19 98.
51 A.J. Smith, “Applications of the self-organizing map to
reinforcement learning , Neural Network, vol. 15 , no. 8-9 , pp.
11 07...
... combining these two sets of equations, and by setting
x
i
− ρx
i
=0,we
obtain
t
11
u
1
+ t
12
v
1
+ t
13
− t
41
u
1
x
1
− t
42
v
1
x
1
− t
43
x
1
=0
t
11
u
2
+ t
12
v
2
+ t
13
− t
41
u
2
x
2
− t
42
v
2
x
2
− ... 309–354, 19 84.
212 .75
212 .48
211 .98
1
1
1
339
340
3 41
100
200
Image
Row
Sequence of images
10 0th image 200th image
480
340
1
640
1...
... Range and Intensity Images 237
5
012 34
6789
10 11 12 13 14
(a)
(c) (d)
(b)
(e)
−0.8
+0 .15
−0.8
+0 .15
+0.45
+0.85
+0.3
+0.3
−0.65
−0.65
1. 5
1. 5
+0.45
+0.85
−0.3
−0.3
+0.7
+0.7
6.4.4 Projection Methods
The ... resulting model. The to-
tal number of points and triangles in the 40 range images were 1, 6 01, 563
and 3,053,907, respectively, and these were reduced to 14 8,...