Dimension-wise spatial layout importance selection: an alternative way to handle object deformation
View Patent ↗Systems and methods are disclosed for object detection by receiving an image; segmenting the image; extracting features from the image; and performing a dimension-wise spatial layout selection to pick up dimensions inside a discriminative spatial region for classification.
1. A method for object detection, comprising:
receiving an image;
segmenting the image;
extracting features from the image; and
performing a dimension-wise spatial layout selection to pick up dimensions inside a discriminative spatial region for classification,
wherein comprising for each boosting classifier, the learning process obtains a set of weak classifiers H for separating the positive samples from negative ones:
H
(
Q
)
=
∑
t
=
1
T
β
t
h
t
(
T
(
R
i
t
′
(
Q
)
)
)
=
∑
t
=
1
T
β
t
h
t
(
∑
j
=
1
N
i
t
α
i
t
,
j
T
(
r
i
t
,
j
′
(
Q
)
)
)
,
where Q represents a candidate bounding box, i t is an index of the region selected in a t th round of training, N i t is a total number of regionlets in region R i t , and β t is a weight of a selected weak classifier, T is a feature representation for respective region R or regionlet prototype r′, subscript j th refers to a feature extracted from the j th regionlet r j in R, α j is a binary variable, R′ is a feature region protype.
2. The method of claim 1 , comprising counting features appearing in candidate sub-regions.
3. The method of claim 1 , comprising:
forming at least an object bounding box for a location; and
applying a cascaded boosting classifier to each object bounding box, with each weak classifier taking a feature response of a region inside the bounding box as its input and then the region is in turn represented by a group of small sub-regions (regionlets).
4. The method of claim 1 , comprising selecting sets of regionlets from a pool of candidate regionlet groups by boosting.
5. The method of claim 1 , comprising using a regionlet representation to model fine-grained spatial appearance layouts.
6. The method of claim 1 , comprising aggregating feature responses of regionlets within one group to a one dimensional feature robust to local deformation.
7. The method of claim 1 , comprising determining a permutation invariant feature operation on features extracted from regionlets as
T
(
R
)
=
∑
j
=
1
N
R
α
j
T
(
r
j
)
,
subject
to
α
j
∈
{
0
,
1
}
,
∑
j
=
1
N
R
α
j
=
1
,
where T(R) as a feature representation for region R, T(r j ) as a feature extracted from the j th regionlet r j in R, N R is a total number of regionlets in region R, α j is a binary variable, either 0 or 1.
8. The method of claim 1 , comprising applying max-pooling over regionlet features as:
T
(
R
)
=
max
j
T
(
r
j
)
.
9. The method of claim 1 , comprising normalizing regionlets using detection windows.
10. The method of claim 1 , comprising normalizing regionlets by using relative positions and sizes of the regionlets and their groups to an object bounding box.
11. The method of claim 1 , comprising training with boosting regionlet features.
12. The method of claim 1 , comprising using RealBoost to train cascaded classifiers for object detection.
13. A system for object detection, comprising:
a camera;
a processor coupled to the camera;
code for receiving an image;
code for segmenting the image;
code for extracting features from the image; and
code for performing a dimension-wise spatial layout selection to pick up dimensions inside a discriminative spatial region for classification
wherein comprising for each boosting classifier, the learning process obtains a set of weak classifiers H for separating the positive samples from negative ones:
H
(
Q
)
=
∑
t
=
1
T
β
t
h
t
(
T
(
R
i
t
′
(
Q
)
)
)
=
∑
t
=
1
T
β
t
h
t
(
∑
j
=
1
N
i
t
α
i
t
,
j
T
(
r
i
t
,
j
′
(
Q
)
)
)
,
where Q represents a candidate bounding box, i t is an index of the region selected in a t th round of training, N i t is a total number of regionlets in region R i t , and β t is a weight of a selected weak classifier, T is a feature representation for respective region R or regionlet prototype r′, subscript j th refers to a feature extracted from the j th regionlet r j in R, α j is a binary variable, R′ is a feature region protype.
14. The system of claim 13 , comprising code for counting features appearing in candidate sub-regions.
15. The system of claim 13 , comprising code for:
forming at least an object bounding box for a location; and
applying a cascaded boosting classifier to each object bounding box, with each weak classifier taking a feature response of a region inside the bounding box as its input and then the region is in turn represented by a group of small sub-regions (regionlets).
16. The system of claim 13 , comprising code for learning a combination of different spatial layouts to detect a target object.
17. The system of claim 13 , comprising code for randomly generating a plurality of sub-regions in a candidate region with different sizes and aspect ratios.
18. The system of claim 13 , comprising code for selecting specific feature dimensions in a specific spatial layout for efficient classification.