没有合适的资源?快使用搜索试试~ 我知道了~
通过自适应信息进行高光谱目标检测-具有局部约束的理论度量学习
0 下载量 196 浏览量
2021-03-12
16:40:14
上传
评论
收藏 2.87MB PDF 举报
温馨提示
试读
16页
通过自适应信息进行高光谱目标检测-具有局部约束的理论度量学习
资源详情
资源评论
资源推荐
remote sensing
Article
Hyperspectral Target Detection via Adaptive
Information—Theoretic Metric Learning with
Local Constraints
Yanni Dong
1
, Bo Du
2,
*, Liangpei Zhang
3
and Xiangyun Hu
1
1
Hubei Subsurface Multi–Scale Imaging Key Laboratory, Institute of Geophysics and Geomatics, China
University of Geosciences, Wuhan 430074, China; dongyanni@cug.edu.cn (Y.D.); xyhu@cug.edu.cn (X.H.)
2
School of Computer, Wuhan University, Wuhan 430079, China
3
State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan
University, Wuhan 430079, China; zlp62@whu.edu.cn
* Correspondence: gunspace@163.com; Tel.: +86-138-7146-1059
Received: 18 July 2018; Accepted: 3 September 2018; Published: 6 September 2018
Abstract:
By using the high spectral resolution, hyperspectral images (HSIs) provide significant
information for target detection, which is of great interest in HSI processing. However, most classical
target detection methods may only perform well based on certain assumptions. Simultaneously,
using limited numbers of target samples and preserving the discriminative information is also a
challenging problem in hyperspectral target detection. To overcome these shortcomings, this paper
proposes a novel adaptive information-theoretic metric learning with local constraints (ITML-ALC)
for hyperspectral target detection. The proposed method firstly uses the information-theoretic metric
learning (ITML) method as the objective function for learning a Mahalanobis distance to separate
similar and dissimilar point-pairs without certain assumptions, needing fewer adjusted parameters.
Then, adaptively local constraints are applied to shrink the distances between samples of similar pairs
and expand the distances between samples of dissimilar pairs. Finally, target detection decision can
be made by considering both the threshold and the changes between the distances before and after
metric learning. Experimental results demonstrate that the proposed method can obviously separate
target samples from background ones and outperform both the state-of-the-art target detection
algorithms and the other classical metric learning methods.
Keywords: hyperspectral image; target detection; metric learning; local constraints
1. Introduction
A hyperspectral image (HSI) obtained by remote sensing systems can provide significant
information. Each pixel of HSI contains a continuous spectrum with hundreds or even thousands of
spectral bands, of which the width of each band is about 5–10 nm, to detect and characterize target of
interest in the scene [
1
,
2
]. Target detection is one of the most wide applications of hyperspectral image
processing, and it plays an important role in the real world, such as detecting humanmade objects
in reconnaissance applications, searching rare minerals in geology, and researching environmental
pollution [
3
–
5
]. Based on specific spectral signatures (prior information), the purpose of target detection
is to decide whether a target of interest is present or not present (background) in a pixel-under-test,
which can be viewed as a binary classifier [6,7].
A number of classical target detection algorithms have been proposed in HSI analysis. Most of
them are based on the linear models and statistical hypothesis tests, which can maximize the detection
probability for fixed false alarm probability, such as orthogonal subspace projection (OSP) and adaptive
cosine/coherence estimator (ACE). The former OSP method proposed by Harsanyi et al. [
8
] suppresses
Remote Sens. 2018, 10, 1415; doi:10.3390/rs10091415 www.mdpi.com/journal/remotesensing
Remote Sens. 2018, 10, 1415 2 of 16
the background signatures by projecting each pixel’s spectrum onto a subspace, which is orthogonal
to the background signatures. The well-known ACE method proposed by Kraut et al. [
9
] assumes
that the additive noise has been included in background, which is an unstructured background
detector. However, most classical algorithms depend on the specific statistical hypothesis tests, and
may only perform well under certain conditions, e.g., the ACE detector assumes that the background
is homogeneous, which is unrealistic in the real world.
In recent years, the machine learning techniques have been introduced into HSI target detection,
which has been paid great attention [
10
,
11
]. Typical examples of these methods are kernel-based
detectors, such as the kernel matched subspace detectors (KMSD) [
12
], kernel spectral matched
filter (KSMF) [
13
], and kernel OSP [
14
]. The kernel-based methods map the original feature space
into a potentially high-dimensional kernel space to solve the linearly inseparable problem in the
original space. Apparently, as mentioned in the article [
15
], kernel-based methods are also based on
statistical hypothesis test, and inherit the shortcomings of traditional target detection methods. It can
be concluded that kernel-based methods attempt to find a stable and credible feature space (distance
metric) for separating potential target pixels and background ones [16–18].
Otherwise, the spectral resolution of HSIs is so high that these spectral bands are often highly
correlated. For decreasing spectral redundancy and releasing computational complexity, it is necessary
to reduce dimension by discarding redundant features for HSI target detection [
19
,
20
]. There are such
few target pixels of interest that HSI target detection rarely takes into consideration dimensionality
reduction, which may hide the accuracy of detecting targets. That is to say, target detection is usually
in a dilemma whether to reduce spectral redundancy or preserve discriminative information [
21
,
22
].
Thus, how to develop a proper metric with a low dimensionality for measuring the separability
between target pixels and background ones becomes the key for HSI target detection [23].
In fact, metric learning methods have proved to be a more straightforward and effective way
to obtain such a distance metric [
24
–
26
]. To date, there are a few metric learning methods that have
been proposed for HSI target detection. For example, Zhang et al. [
15
] learned an objective function of
the supervised distance maximization by putting a similarity propagation constraint and imposing a
manifold smoothness regularization. Dong et al. [
27
] presented the maximum margin metric learning
(MMML) method, which utilizes the maximum margin framework as the objective function to learn
distance metric space and can maximally separate target samples from background ones without
certain assumptions. Dong et al. [
28
] presented random forest metric learning (RFML) method, which
adopts random forests as the underlying representation of the metric learning, to deal with limited
numbers of target samples by merging the standard relative position and the absolute pairwise position.
In general, by using metric learning, we can find the distance metric matrix, so as to transform the
original space into the metric feature space. Then, we can detect the desired targets, especially when
the samples are imbalanced and the number of target samples is very limited.
In addition, a number of metric learning methods have been proposed to learn the distance metric,
such as neighborhood component analysis (NCA) method [
29
], large margin nearest neighbor (LMNN)
method [
30
], and so on. For each instance, NCA method expresses the probability of selecting the same
class instances as the neighbors, which can maximize the stochastic variance of leave-one-out k-nearest
neighbor (KNN) score on the training samples. LMNN method aims to find a distance metric such that
the instances from different classes are effectively separated by a large margin within the neighborhood,
where the margin is defined as the difference between the between-class and within-class distances.
Furthermore, the information-theoretic metric learning (ITML) method, proposed by Davis et al. [
31
],
expresses the weakly supervised metric learning problem as a Bregman optimization problem and can
handle a variety of constraints and incorporate a priori information on the distance function.
However, the existing metric learning based methods still have some obstacles to be addressed.
The major problem is that most methods mentioned above are global metric learning with global
constraints, making decisions by comparing their Mahalanobis distance d and judging d is lower or
higher than the a fixed threshold b, which is insufficient and suboptimal. Therefore, in this paper, ITML
Remote Sens. 2018, 10, 1415 3 of 16
method, which works in a weakly supervised manner, is innovatively introduced for hyperspectral
target detection with adaptively local constraints (ITML-ALC, for short). The proposed ITML-ALC
method explores adaptively local constraints to relax the fixed threshold, which can be used to compute
the Mahalanobis distance d and judge if given samples are targets by considering both b and the changes
between the distances before and after metric learning. By considering local constraints and avoiding
adopting those conflicting constraints, the separability between target samples and background ones
can be enhanced. Besides, non-square matrix
W
can be found for handling high-dimensional data
problems by transforming the original space into a metric learning space with a low dimensionality.
Compared with existing algorithms, ITML-ALC has several obvious advantages:
1.
The proposed ITML-ALC algorithm can use limited numbers of target samples to detect targets
without certain assumptions, compared with traditional target detection methods.
2.
ITML-ALC needs only one parameter to be adjusted, and the detection results are relatively
stable for different values of parameter.
3.
ITML-ALC can remain the locality information and improve the detection performance via
considering both the threshold and the changes between the distances before and after metric
learning, while existing metric learning based methods uses fixed threshold to make decision.
The rest of this paper is organized as follows. In Section 2, a briefly introduce of the original
ITML method is provided, and the proposed ITML-ALC method is then presented. The experimental
results of the proposed method using several challenging HSIs are detailed in Section 3, followed by
the discussion and conclusions in Sections 4 and 5.
2. Methods
2.1. Related Work
The ITML methodology minimizes the LogDet divergence subject to linear constraints. There are
two key techniques of ITML. One is the ability to handle a wide variety of constraints and to optionally
incorporate a priori information on the distance function. The other key technique is that it is fast
and scalable.
Suppose that we have a set of L-dimensional training samples
{
x
1
, x
2
, · · · , x
n
}
∈ R
L×n
, in which
n represents the number of training samples and L is the number of feature dimensions.
z
ij
∈ (+
1,
−
1
)
denotes the relationship between the training samples
x
i
and
x
j
. Considering relationships of the
similarity or dissimilarity between pairs of samples, distances between samples in the same class can
be constrained as similar, and ones in different classes can be constrained as dissimilar. Then, we have
a set of similar constraints S and a set of dissimilar constraints D as Equation (1):
S : ∀(x
i
, x
j
) ∈ S x
i
, x
j
∈ same class, z
ij
= 1,
D : ∀(x
i
, x
j
) ∈ D x
i
, x
j
∈ different class, z
ij
= −1.
(1)
Metric learning aims to learn metric matrix
M
, which specifies the Mahalanobis distance
d
M
(x
i
,
x
j
)
between any pairs of samples x
i
and x
j
as:
d
M
(x
i
, x
j
) =
q
(x
i
− x
j
)
T
M(x
i
− x
j
). (2)
In order to ensure that
d
M
(x
i
,
x
j
)
is a meaningful distance, the learned metric matrix
M
must be
symmetric and positive semidefinite (PSD) variance matrix, guaranteeing that
d
M
(x
i
,
x
j
)
is symmetrical,
non-negativite, and has triangle inequality [
32
,
33
]. Considering the high dimensional of HSIs and
M
is
PSD matrix, a nonsquare matrix W ∈ R
L×D
(D L), defining a mapping from the high-dimensional
space into a low-dimensional embedding, can be established, and M = WW
T
[34–36].
In the Equation (2), our objective is to find the PSD matrix
M
(or
W
) and the corresponding
distance threshold b such that for any pairs
(x
i
,
x
j
) ∈ S
the distance between them is smaller than b,
Remote Sens. 2018, 10, 1415 4 of 16
and for any pairs
(x
i
,
x
j
) ∈ D
the distance between them is greater than b, which can be described as
Equation (3):
d
M
(x
i
, x
j
) ≤ b (x
i
, x
j
) ∈ S,
d
M
(x
i
, x
j
) ≥ b (x
i
, x
j
) ∈ D.
(3)
The ITML method can minimize the differential relative entropy between two multivariate
Gaussians and handle a variety of constraints on the distance function via a natural information-
theoretic approach. Thus, given a Mahalanobis distance parameterized by
M
, its corresponding
multivariate Gaussian can be expressed as:
p(x; M) =
1
Z
exp(−
1
2
d
M
(x, µ)), (4)
where
µ
is the mean of Gaussians,
Z
is a normalizing constant in the Equation (4). By using the
bijection, the distance between two Mahalanobis distance functions parameterized by
M
0
and
M
can
be measured by the differential relative entropy of corresponding multivariate Gaussians:
KL(p(x; M
0
)||p(x; M)) =
Z
p(x; M
0
) log
p(x; M
0
)
p(x; M)
dx, (5)
In the Equation (5),
M
0
is a given Mahalanobis distance function, such as identity matrix.
In conjunction with given pairs of similar points
S
and pairs of dissimilar points
D
, the distance
metric learning can be summarized as the following optimization problems:
min
M
KL(p(x; M
0
)||p(x; M))
subject to d
M
(x
i
, x
j
) ≤ b
1
(x
i
, x
j
) ∈ S,
d
M
(x
i
, x
j
) ≥ b
2
(x
i
, x
j
) ∈ D,
(6)
where b
1
, b
2
are given upper and lower bounds, respectively.
Some research has shown that the differential relative entropy of corresponding multivariate
Gaussians is equivalent to the LogDet divergence between the covariance matrices [37]:
KL(p(x; M
0
)||p(x; M)) =
1
2
d
log det
(M
−1
0
, M
−1
) =
1
2
d
log det
(M, M
0
), (7)
where M
−1
0
, M
−1
are the covariance of the distributions.
Taking into account that a feasible solution of Equation (6) may not exist, we incorporate slack
variable
ξ
into Equation (6) to guarantee the existence of the metric matrix
M
. Thus, the Equation (6)
can be represented as the following optimization problem with Equation (7):
min
M≥0,ξ
d
log det
(M, M
0
) + γ·d
log det
(diag(ξ), diag(ξ
0
))
s.t. tr(M(x
i
− x
j
)(x
i
− x
j
)
T
) ≤ ξ
c(i,j)
(x
i
, x
j
) ∈ S,
tr(M(x
i
− x
j
)(x
i
− x
j
)
T
) ≥ ξ
c(i,j)
(x
i
, x
j
) ∈ D,
(8)
where
ξ
0
denotes initialized slack variables, and
c(i
,
j)
is the index of the
(i
,
j) − th
constraint.
γ
is the
tradeoff parameter, which controls the tradeoff between satisfying the constraints and minimizing
d
log det
.
2.2. Combining ITML and Adaptively Local Constraints
The ITML method uses fixed threshold to make decision, which makes it less effective to handle
data with complex distributions even if the associated metric is correct. To address this issue, this paper
proposes an adaptively local decision rule to design pairwise constraints to relax the fixed threshold
for target detection. We design a local decision function
f (d
ij
)
to achieve this goal, where
d
ij
is the
剩余15页未读,继续阅读
weixin_38693419
- 粉丝: 6
- 资源: 931
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
评论0