Moving Object Detection from Mobile Platforms Using Stereo Data Registration - Computational Intelligence Paradigms in Advanced Pattern Classification - page 30

50 50

100
150

100
150

200
250

200
250

300
350

300
350

400
450

400
450

100 200 300 400 500 600 100 200 300 400 500 600

Frame ( n ) Frame ( n + 1 )

Frame ( n ) Frame ( n + 1 )

Fig. 1 Feature points detected and tracked through consecutive frames: ( top ) using Harris
corner detector; ( bottom ) using SIFT detector and descriptor

n+1

n

P 1(x,y,z)

P 1(x,y,z)

Z

Z

X

X

n+1

P 2(x,y,z)

n

[ R | t ]

P 2(x,y,z)

Y

Y

n

n+1

P 3(x,y,z) P 3(x,y,z)

Fig. 2 Illustration of feature points represented in the 3D space, together with three couples
of points used for computing the 3D rigid displacement: [ R | t ] —RANSAC-like technique