Systems, Man & Cybernetics - April 2016 - 38

points in the patch, respectively. The computational
details are omitted for simplicity.

Range Data Acquisition
Plane Segmentation
LLF Extraction
BF Extraction
HLF Extraction
HLF-1

...

BF

HLF-6

Training
GMM1

. . . GMM6

GMM7

GMM8

Passed Results
Ok -Plane, K = 1,2,3,4

Others

Recursive Plane Clustering
Object Recognition Results
Figure 5. a diagram of the proposed object

recognition method.

patch. In this article, we define three classes of features-basic feature (BF), low-level feature (LLF), and
high-level feature (HLF).
Basic Features
Basic features are local features that describe a patch's
intrinsic attributes. They serve as the identity of the patch.
Similar to [19], three BFs-orientation (O), area (A), and
height (H)-are defined for a planar patch. They are computed as the angle between the patch's normal and Z axes,
size of the patch, and the maximum Z coordinate of the

d

A

d

B

nB

(a)

(d)

A
d

B

(b)
A

A
B

nA

A

C

d1
B
d2
(e)

B

(c)
nA

A
d

nB
B
(f)

Figure 6. the definition of HLFs. (a) HLF-1: coplanar

with distance d; (b) HLF-2: parallel and face-to-face
with distance d; (c) HLF-3: step shape with distance
d; (d) HLF-4: parallelepiped shape; (e) HLF-5: sideabove with distance d1 and d2: d1 is the A's projection
distance, while d2 is the minimum distance between
A's projection points on B and B's points; and (f) HLF-6:
above-with-distance d. A, B, and C represent any
three patches out of the N planar patches.
38

IEEE SyStEmS, man, & CybErnEtICS magazInE A pri l 2016

Low-Level Features
To classify a patch into a constituent element of a model
object, the patch's IPR must be considered in addition to its
BFs. The following nine IPRs are defined for patch Pi with
reference to patch P j :
1) plane-distance is a value representing the minimum distance between the points of Pi and the points of P j
2) plane-angle represents the angle between Pi and P j
3) parallel-distance, denoted l ij, represents the distance
between two parallel planes, Pi and Pi, and is computed
as the mean of the distance from the centroid of Pi to patch
P j ; and the distance from the centroid of Pi to patch Pi
4) projection-overlap rate is a value representing to what
extent Pi overlaps P j , and it is calculated as the area
ratio of the projected Pi (onto P j) to P j
5) projection distance is the minimum distance from the
points of Pi to plane P j
6) is parallel describes if Pi is parallel to P j (1 = parallel,
0 = not parallel)
7) is perpendicular describes if Pi is perpendicular to P j
(1 = perpendicular, 0 = not perpendicular)
8) is coplanar describes if Pi is coplanar with P j (1 =
coplanar, 0 = not coplanar)
9) is adjacent describes if Pi is adjacent to P j (1 = adjacent, 0 = not adjacent).
Due to the SR4000's noise, threshold values are used in
computing the above LLFs. The details are omitted. Since
there are N patches, an N # N matrix is formed to record
each of the nine IPRs among the N patches. Each matrix is
called an LLF. In an LLF matrix, an element at (i, j)
describes the IPR of Pi with reference to P j . For example,
is parallel (i, j) = 1 indicates that Pi is parallel to P j .
High-Level Features and Feature Vectors
In this work, each planar patch is classified as a plane
belonging to one of the eight objects (models). To this end,
we define six mutually exclusive HLFs as shown in
Figure 6. Each HLF represents a set of particular IPRs that
exists in an object model. The HLF extraction is a process
to identify the HLF for each of the N planar patches and
assign each patch an HLF vector. The BFs extracted earlier
are used in constructing the HFL vector. We first construct
a BF vector [O, A, H] for a planar patch. Each BF is then
extended based on the patch's HLF. For a patch with HLF-1,
HLF-2, HLF-3, or HLF-6, we add parameter d into its BF
vector to form a HLF vector [O, A, H, d]. For a patch with
HLF-5, we add parameter d1 and d2 to form a HLF vector
[O, A, H, d1, d2]. For a patch with HLF-4, we simply use the
BF vector as the HLF vector. A plane is treated as an object
if it is a wall/ground. Such a plane does not have an IPR. We
therefore simply use its BF vector as the HLF vector. A
plane with an HLF as depicted in Figure 6 is called a complex plane, while a wall/ground plane an elementary plane.



Table of Contents for the Digital Edition of Systems, Man & Cybernetics - April 2016

Systems, Man & Cybernetics - April 2016 - Cover1
Systems, Man & Cybernetics - April 2016 - Cover2
Systems, Man & Cybernetics - April 2016 - 1
Systems, Man & Cybernetics - April 2016 - 2
Systems, Man & Cybernetics - April 2016 - 3
Systems, Man & Cybernetics - April 2016 - 4
Systems, Man & Cybernetics - April 2016 - 5
Systems, Man & Cybernetics - April 2016 - 6
Systems, Man & Cybernetics - April 2016 - 7
Systems, Man & Cybernetics - April 2016 - 8
Systems, Man & Cybernetics - April 2016 - 9
Systems, Man & Cybernetics - April 2016 - 10
Systems, Man & Cybernetics - April 2016 - 11
Systems, Man & Cybernetics - April 2016 - 12
Systems, Man & Cybernetics - April 2016 - 13
Systems, Man & Cybernetics - April 2016 - 14
Systems, Man & Cybernetics - April 2016 - 15
Systems, Man & Cybernetics - April 2016 - 16
Systems, Man & Cybernetics - April 2016 - 17
Systems, Man & Cybernetics - April 2016 - 18
Systems, Man & Cybernetics - April 2016 - 19
Systems, Man & Cybernetics - April 2016 - 20
Systems, Man & Cybernetics - April 2016 - 21
Systems, Man & Cybernetics - April 2016 - 22
Systems, Man & Cybernetics - April 2016 - 23
Systems, Man & Cybernetics - April 2016 - 24
Systems, Man & Cybernetics - April 2016 - 25
Systems, Man & Cybernetics - April 2016 - 26
Systems, Man & Cybernetics - April 2016 - 27
Systems, Man & Cybernetics - April 2016 - 28
Systems, Man & Cybernetics - April 2016 - 29
Systems, Man & Cybernetics - April 2016 - 30
Systems, Man & Cybernetics - April 2016 - 31
Systems, Man & Cybernetics - April 2016 - 32
Systems, Man & Cybernetics - April 2016 - 33
Systems, Man & Cybernetics - April 2016 - 34
Systems, Man & Cybernetics - April 2016 - 35
Systems, Man & Cybernetics - April 2016 - 36
Systems, Man & Cybernetics - April 2016 - 37
Systems, Man & Cybernetics - April 2016 - 38
Systems, Man & Cybernetics - April 2016 - 39
Systems, Man & Cybernetics - April 2016 - 40
Systems, Man & Cybernetics - April 2016 - 41
Systems, Man & Cybernetics - April 2016 - 42
Systems, Man & Cybernetics - April 2016 - 43
Systems, Man & Cybernetics - April 2016 - 44
Systems, Man & Cybernetics - April 2016 - 45
Systems, Man & Cybernetics - April 2016 - 46
Systems, Man & Cybernetics - April 2016 - 47
Systems, Man & Cybernetics - April 2016 - 48
Systems, Man & Cybernetics - April 2016 - 49
Systems, Man & Cybernetics - April 2016 - 50
Systems, Man & Cybernetics - April 2016 - 51
Systems, Man & Cybernetics - April 2016 - 52
Systems, Man & Cybernetics - April 2016 - 53
Systems, Man & Cybernetics - April 2016 - 54
Systems, Man & Cybernetics - April 2016 - 55
Systems, Man & Cybernetics - April 2016 - 56
Systems, Man & Cybernetics - April 2016 - Cover3
Systems, Man & Cybernetics - April 2016 - Cover4
https://www.nxtbook.com/nxtbooks/ieee/smc_202110
https://www.nxtbook.com/nxtbooks/ieee/smc_202107
https://www.nxtbook.com/nxtbooks/ieee/smc_202104
https://www.nxtbook.com/nxtbooks/ieee/smc_202101
https://www.nxtbook.com/nxtbooks/ieee/smc_202010
https://www.nxtbook.com/nxtbooks/ieee/smc_202007
https://www.nxtbook.com/nxtbooks/ieee/smc_202004
https://www.nxtbook.com/nxtbooks/ieee/smc_202001
https://www.nxtbook.com/nxtbooks/ieee/smc_201910
https://www.nxtbook.com/nxtbooks/ieee/smc_201907
https://www.nxtbook.com/nxtbooks/ieee/smc_201904
https://www.nxtbook.com/nxtbooks/ieee/smc_201901
https://www.nxtbook.com/nxtbooks/ieee/smc_201810
https://www.nxtbook.com/nxtbooks/ieee/smc_201807
https://www.nxtbook.com/nxtbooks/ieee/smc_201804
https://www.nxtbook.com/nxtbooks/ieee/smc_201801
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_1017
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0717
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0417
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0117
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_1016
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0716
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0416
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0116
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_1015
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0715
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0415
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0115
https://www.nxtbookmedia.com