Content uploaded by Panchamy Krishnakumari
Author content
All content in this area was uploaded by Panchamy Krishnakumari on Jan 09, 2018
Content may be subject to copyright.
94
Transportation Research Record: Journal of the Transportation Research Board,
No. 2645, 2017, pp. 94–103.
http://dx.doi.org/10.3141/2645-11
Identifying and classifying traffic and congestion patterns are essen-
tial parts of modern traffic management underpinned by the emerging
intelligent transport systems. This paper explores the potential of using
a combination of image processing methods to identify and classify
regions of congestion within spatiotemporal traffic (speed, flow) contour
maps. The underlying idea is to use these regions as (archetype) shapes
that in many combinations can make up a wide variety of larger-scale
traffic patterns. In this paper, use of a so-called statistical shape model
is proposed as a low-dimensional representation of the archetype shape,
and an active shape model algorithm coupled with linear classification
is developed to classify the patterns of interest. Application of the pro-
posed method is demonstrated with a preliminary set of speed contour
maps reconstructed from loop detector data in the Netherlands. The
results show that the extended active shape model can be used as a
multiclass classifier. In particular, 70% of the traffic patterns in the test
data were correctly classified with use of only two archetype shapes and
simple logistic classifiers. The results point to the importance of use of
expert knowledge by means of (a priori) manual classification of the
training examples. This work opens many research directions, including
semiautomated searches through traffic databases, automatic detection,
and classification of new traffic patterns.
In research, in education, and in practice, spatiotemporal contour maps
of speed, density, and flow provide an intuitive means to identify,
study, explain, and illustrate (longitudinal) traffic flow phenomena
on the basis of either real traffic data or data from traffic simulation
models. These phenomena include homogeneous congestion (HC)
patterns at bottlenecks, reduced flows related to blockages, wide
moving jams (WMJs) that propagate over large distances against
the direction of traffic flow, and high-density platoons of heavy
vehicles that form moving bottlenecks. With contour maps these
phenomena become visible, which helps scientists to formulate
hypotheses and derive theories and models to describe the under-
lying dynamics. Figure 1, for example, shows speed contour plots on
the A20 freeway in the Netherlands between Rotterdam and Gouda
(Figure 1a), the A13 between Rotterdam and The Hague (Figure 1b),
and the A16 east of Rotterdam (Figure 1c), which were used in a
study of traffic dynamics related to severe accidents.
Constructing smooth contour maps from (sensor) data is relatively
straightforward with the adaptive smoothing method introduced by
Treiber and Helbing (1) and further refined by others (2, 3). Techni-
cally, contour maps represent matrices of traffic variables (densities,
speeds, flows) on consecutive cells Δx along a route for consecutive
time periods Δt, where neither Δx nor Δt must be of constant size
or duration, respectively. When mapped onto an underlying grid
{xi, tj} with i = 1, . . . , N and j = 1, . . . , M, traffic contour plots
can be understood as images with a color mapping from the traffic
variable of interest to whatever color coding provides the required
visual representation. This image representation opens a wide array
of possibilities for traffic scientists and engineers, such as deriving
distributions of wave speeds from raw traffic data, without making
any prior assumptions (4). These wave speeds and patterns can then
be used for calibration and validation of traffic flow models (5).
This paper explores a different application perspective of image
processing techniques within the traffic domain, that is, the clas-
sification and identification of different traffic patterns. Classifying
congestion patterns has a twofold application—for off-line analysis
and for real-time predictions. For off-line analysis, it can be used to
find days and routes in the historical database with similar congestion
patterns. These data can be used by traffic managers to compare two
incidents to gain insight for better traffic control. The classification
of partial patterns along with metadata such as incident location and
severity can also be used for short-term predictions.
Classifying congestion patterns is not a new idea. The ASDA/
FOTO method of Kerner et al. is a well-known, patented, theory-
laden approach (6), and many machine learning alternatives are avail-
able (7–10). Whereas the latter studies focused on class labels that
indicate level of service (e.g., light, medium, and heavy congestion),
this study’s aim, like that of Kerner et al., is to classify entire spatio-
temporal congestion patterns. In contrast to that of Kerner et al., this
study does not use an elaborate set of expert rules but instead uses
flexible and data-driven methods. A supervised learning method was
used in an earlier study to classify such patterns with a multiclass
support vector machine (11). That study derived an equal-size fea-
ture vector for all small and larger traffic patterns identified in traffic
contour maps. In this paper, (geometrical) shapes instead of feature
vectors are used. The method used comprises several image pro-
cessing techniques to break down larger-scale traffic patterns into
smaller regions. The underlying idea is that these regions constitute
base (archetype) shapes that in many combinations can make up a
wide variety of larger-scale traffic patterns. With robust identifica-
tion methods for such archetype shapes, it is possible to dissect,
identify, and classify complex traffic patterns automatically. Despite
Traffic Congestion Pattern Classification
Using Multiclass Active Shape Models
Panchamy Krishnakumari, Tin Nguyen, Léonie Heydenrijk-Ottens,
Hai L. Vu, and Hans van Lint
P. Krishnakumari and H. van Lint, Delft University of Technology, Stevinweg 1,
2600 GA Delft, Netherlands. T. Nguyen, Swinburne University of Technology,
Melbourne, Victoria, Australia. Current affiliation for T. Nguyen: Delft University
of Technology, Stevinweg 1, 2600 GA Delft, Netherlands. L. Heydenrijk-Ottens,
CGI Nederland B.V., George Hintzenweg 89, 3068 AX Rotterdam, Netherlands.
H. L. Vu, Monash University, 23 College Walk, 3800 Clayton, Victoria, Australia.
Corresponding author: P. Krishnakumari, p.k.krishnakumari@tudelft.nl.
Krishnakumari, Nguyen, Heydenrijk-Ottens, Vu, and van Lint 95
the approach’s simplicity, the classification results are encouraging,
with 70% accuracy attained with just two archetype shapes and
simple logistic classifiers and without resorting to the use of addi-
tional information (e.g., flow), as in the method of Kerner et al. The
applications for this technique are numerous and range from traf-
fic database searching and indexing to traffic state estimation and
prediction.
The rest of the paper is organized as follows. The next section gives
an overview of the approaches in the multiclass classifier using active
shape models (ASMs). Then the experimental setup is described,
along with the validation method. The results of the method are pre-
sented, and a synthesis of the findings is then given. The paper closes
with preliminary conclusions and an outlook on further improvement
of the method.
METHOD
In this work, an approach that is fundamentally different from
the state of the art in traffic pattern classification is introduced and
developed. Instead of the use of local features to identify charac-
teristics of traffic patterns, (archetype) shapes are used to classify
patterns to capture the global structure of these patterns. This method
works at a higher abstraction level than feature-based methods. The
Space (km)
Space (km)
(b)
(c)
Time
Time
Speed (km/h)Speed (km/h)
Space (km)
(a)
Time
Speed (km/h)
FIGURE 1 Three severe incidents with similar characteristics regarding incident, spatiotemporal
extent of queue, and vehicle loss hours: (a) A20, June 9, 2015; (b) A13, March 24, 2015;
and (c) A16, January 9, 2011.
96 Transportation Research Record 2645
shape-based methods are usually used for shape recognition and
fitting, mainly in image recognition. This is the first paper, to the
authors’ knowledge, that introduces shape-based classification in
the traffic domain for multiclass classification. The overall method
is outlined in Figure 2a.
The idea is to extract contours from speed contour maps and use
these as the basis for building the shape model, the base shape clas-
sifier (SC) model, and the pattern classifier model. All these compo-
nents are explained below; a full mathematical explanation is beyond
the scope of this paper. The final part of the method explains how
the fitting result from ASM has been used for a multiclass prediction
process.
Contour Extraction
The basic ingredients of the method are contour maps of detector
data generated with the adaptive smoothing method. This method is
extensively described elsewhere (1–3). Raw data for 1 day are con-
sidered in one contour map, which therefore can contain multiple
congestion patterns for a given day. The individual traffic congestion
patterns from each space–time plot are extracted with a naïve contour
extraction.
The naïve contour extraction finds the outline of a pattern in an
image, as there are multiple patterns in one image (Figure 3a). The first
step is to filter out irrelevant information by assuming a speed thresh-
old, v_thres, that differentiates between congested and freely flowing
traffic. In this paper, v_thres = 65. This crude assumption can be
relaxed, as discussed later in the paper. This step results in a Boolean
mask, as shown in Figure 3b. After thresholding, dilation is used to fill
the holes created to provide a smooth mask. This smoothed mask is
then used to detect the contours in the image by joining the continu-
ous points along the boundary with similar pixel intensity (12). The
detected contours are used to define the boundary to extract each
pattern in an image (Figure 3c). Resulting from the naïve contour
extraction is a data set of various traffic congestion pattern images.
An additional contour refinement is then performed on the
obtained patterns to extract the congestion shape from each pattern.
The irrelevant information is filtered out from the naïve extracted
pattern image with the same assumption used before; low speed
implies congestion, as shown in Figure 3e. A morphological clos-
ing strategy that consists of two successive binary transformations,
dilation followed by erosion (13), is used to eliminate small and iso-
lated gaps from the relevant regions without destroying the original
shape, as shown in Figure 3f. For both transformations, a 3 × 3 cross-
structuring element is used. This binary smoothed mask is then used
to detect the contours in the image (12), as shown in Figure 3g.
Manual Classification
The refined contour extraction results in a data set of various traffic
congestion pattern images. This data set is manually classified into
five classes according to the size of images (space and time extent
of traffic jam) and the type of congestion. Table 1 shows the five
classes with some examples. This classification is arbitrary—other
analysts may come up with more or fewer classes and different
criteria. Unsupervised learning also can be used for creating these
classes. However, this would require building feature vectors based
on the application or using complete black-box methods like deep
learning to find all the relevant features in the patterns.
Base Shape Identification
and Base Shape Predictor
The manually classified data show that all the patterns in the class
are approximately a combination of two base shapes, isolated WMJs
(IWMJs) and HC. For example, Table 1 shows that low-frequency
WMJ patterns comprise n WMJ shapes, mixed class patterns com-
prise both HC and IWMJ patterns, and so on. The key distinction in
the context of this paper between the two base shapes is that WMJs
are stripe-like shapes, whereas HC patterns form triangular shapes.
This distinction is backed by theoretical research that investigated a
wide range of congestion patterns (1, 14). These works distinguish
two main types of congestion based on first-order traffic flow theory,
synchronized and WMJs, which includes characteristics similar to
those in the base archetypes. Hence, it was decided to start with
these two distinct and well-defined base shapes. As more archetypes
emerge from data, the proposed method can be scaled to include these
base shapes.
Speed contour maps
Contour extraction
Multiclass predictor
Class 1 Class 2 Class NIdentify base shapes
Base shape predictor
(a)
Contours of base
shape
ASM training
ASM fitting
Shape classifier
training
Shape predictor
Isolated and Homogeneous
(b)
Pattern classifier
training
For each pattern
For each shape
ASM fitting
Shape predictor
Class predictor
Class 1–5
(c)
FIGURE 2 Approach: (a) overview, (b) base shape predictor,
and (c) multiclass predictor.
Krishnakumari, Nguyen, Heydenrijk-Ottens, Vu, and van Lint 97
The ASM, given a new observed shape, tries to fit this shape to
one of the base shapes. To do this, the originally single-class ASM
algorithm was extended to a multiclass ASM through inclusion of a
linear classifier that predicts whether a given shape is HC or IWMJ.
Figure 2b outlines how to do this step by step. Each step is explained
in the following (a full mathematical explanation of the ASM com-
ponents, including the multiclass extension, is beyond the scope
of this paper). The two main phases in ASM are discussed below:
constructing a statistical shape model (SSM) for each base shape
(model training) and fitting a new shape to this SSM (model fitting).
ASM Training
The ASM is a model-based segmentation method introduced by
Cootes et al. (15). The method is based on the principle that a shape
can be represented by a mean shape and its variations. The mean
shape and the variances constitute the SSM, which contains all the
parameters that are needed to define that shape. The SSM is used
to find potential instances of the shape model in a new image or con-
tour. Initially, a set of landmarks in the new contour is defined, after
which the shape defined by these landmarks is deformed accord-
ing to the SSM to provide the best fit possible within the SSM. The
deformation is based on finding correspondences between the new
shape and the shape defined by various SSM components and itera-
tive minimization of a cost function for the fit. The allowed degree
of deformation is constrained by the variations defined in the SSM.
If the SSM includes large variances, large deformations are possible,
and vice versa.
An overview of the method is given below. A more detailed
explanation is available elsewhere (15). The steps for building
the SSM model (i.e., the training phase) for a base shape are as
follows:
Step 1. Align the shapes to the first shape in the data set, and
generate a mean shape from the aligned shapes. First, all the shapes
must have the same number of landmarks, which is rarely the case.
Therefore, a so-called iterative closest point (ICP) method is used
(a)
(b)
(c)
(d) (e)
(f) (g)
Speed (km/h)
FIGURE 3 Contour extraction, naïve and refined: (a) raw data, multiple patterns;
(b) threshold mask; (c) naïve extracted contour with boundary; (d) naïve extracted
pattern; (e) binary image; (f) performed closing; and (g) refined contours.
98 Transportation Research Record 2645
to register the contours from all classes to a given model contour.
In ICP, a point set is transformed to best match the chosen model,
where the transformations are revised iteratively until the distance
between the point set and the model is minimized (16). The align-
ment itself is achieved with Procrustes analysis because the standard
ASM also uses this method for alignment (17).
Step 2. Realign the shapes to the mean shape and generate a new
mean shape from the newly aligned shapes.
Step 3. Repeat Step 2 (update the mean shape) until convergence.
Step 4. Finally, apply principal component analysis (PCA) to
compute the eigenvectors and eigenvalues of the aligned shapes.
The SSM components are the eigenvectors of the centered shapes in
the training data, and the variances are the eigenvalues of these shapes.
When PCA is applied to the data, any shape (within the training set) x
(an n-dimensional vector of points) can be approximated with
xxPb (1)≈+
where
–
x = SSM mean shape having point correspondences with x and
the same dimension,
P = SSM principal components, and
b = parameters corresponding to the SSM components that deform
the shape.
This is the basis for fitting a new set of landmarks to the SSM.
The first four components of the IWMJ base class are shown in
Figure 4a. This figure explains the shape variations of the class
according to the mean shape.
ASM Fitting
Given a new shape Y′ for testing, the shape is registered with the
mean shape by using ICP to compute Y. With Y and the SSM model
TABLE 1 Class Description for Manually Classified Patterns
Name Remarks Examples
Isolated WMJs Short (1–2 km) high-density traffic jams. Both head
and tail of this queue propagate backward with
virtually constant speeds (typically −18 km/h).
WMJs typically result from large disturbances
(e.g., abrupt braking) farther downstream.
Heterogeneous Congestion 1,
low-frequency WMJs
Large-scale light congestion patterns with a few
WMJs emitting from the congested area.
Heterogeneous Congestion 2,
high-frequency WMJs
Large-scale light congestion patterns with many
WMJs emitting from the congested area.
Homogeneous congestion High-density (low-speed) severe congestion regions,
typically caused by incidents or other lane block-
ages. In terms of shape, the downstream front is
stationary, whereas the upstream front moves with
various shock wave speeds.
Mixed large-scale pattern Combination patterns not falling in either of the
other categories.
Krishnakumari, Nguyen, Heydenrijk-Ottens, Vu, and van Lint 99
of the shape, ASM fitting finds the model points x that best fit Y. The
steps for ASM fitting are as follows:
Step 1. Initialize the shape parameter b as 0, implying model
points = mean shape, that is, x = –
x.
Step 2. Generate the model points positions with x = –
x + Pb,
where P is the SSM principal component.
Step 3. Find the pose parameters transform that best aligns the
model points x to the new set of landmarks Y by using Procrustes
analysis (17).
Step 4. Project Y into the model coordinate frame Y′ by using the
inverse transform from Equation 1.
Step 5. Update the shape parameters b to match Y′ by finding the
least squares solution of Ax′ = B, where A is P, x′ is b, and B = Y′ − –
x.
Step 6. Repeat Steps 2 through 5 until convergence.
An example of an ASM fitting result is shown in Figure 4b.
The fitting error metric for the ASM that is used as the convergence
criteria is the Euclidean distance between the mean shape and the
ASM fitted shape. The ASM stops the iteration when there is no
significant difference in the error metric result from the previous
iteration and the current iteration. Here, an error difference thresh-
old of 0.0001 was used, which is statistically insignificant with respect
to the error rate and the shape surface area.
Designing and Training a Base Shape Classifier
Now, with a working ASM model for both base shapes (IWMJ and
HC), a shape classifier is needed that can predict which of these base
shapes provides the best representation for a newly found shape in a
speed contour plot. First, the new shape is fitted with both base shapes,
resulting in fitting error values ei (error on the IWMJ base shape)
and eh (error on the HC base shape), respectively. These errors are
defined as the Euclidean distance between the SSM mean and the
fitted shape. Additionally, to increase prediction accuracy, a third
metric is computed that is based on additional nonshape properties
of IWMJ and HC shapes, respectively. As an example, in this case a
metric is based on the spatiotemporal area covered by the shape a
(in meter × seconds) and the gradient g (the variation in speed in the
given area a). The compound metric is the ratio g/a, which can be
understood as the amount of heterogeneity (variation in speed) per
unit space × time, resulting in a three-dimensional feature vector
(ei, eh, g/a). To build the classifier, a well-known method in linear clas-
sification, logistic regression, is applied (18). It originally was a con-
ditional probability model that measures the likelihood relationship
between a specific output and an input by using a logistic function:
pt et
1
1(2)
()
=+−
140
120
100
80
60
40
20
Landmarks (target)
Resulting fit
SSM mean
60 70 80 90 100 110 120 130 140
Result (iteration 11/11, sum of residuals = 28.11)
(b)
(a)
–60
40
30
20
10
0
–10
–20
–30
–40
mean
–40 –20 0
Component 1 ± 3 SD
(explaining 61.54% of original variance)
Component 2 ± 3 SD
(explaining 10.41% of original variance)
Component 3 ± 3 SD
(explaining 5.63% of original variance)
Component 4 ± 3 SD
(explaining 3.78% of original variance)
20 40 60 –40
30
20
10
0
–10
–20
–30
–40 mean
–30 –20 –10 02010 30 40 –40
40
30
20
10
0
–10
–20
–30
–40 mean
–30 –20 –10 02010 30
40
40
30
20
10
0
–10
–20
–30
–40 mean
–40 –20 02040
FIGURE 4 IWMJ: (a) first four PCA components of IWMJ shape model and (b) ASM fitting for IWMJ shape after Nth iterations (N = 11).
100 Transportation Research Record 2645
where t is a linear combination of input feature vector x and a is
the vector of coefficients, which is considered a model character-
istic. In preparing training data, isolated and homogeneous shapes
are labeled as 0 and 1, respectively. These numbers are supposed
to be outputs of logistic function. Coefficient vector aSC is trained
to minimize the cost of matching logistic function to training data,
which is measured by Euclidean distance.
pxy
ii
xi
SC
cost
(3)
2
training set
ai
∑
()
()
=−
∈
xe
eg
a
iih
,, (4)=
yi
0for isolated shapes
1for homogeneous shapes (5)=
The resulting (trained) model is the (base) shape predictor, which
classifies a shape as either IWMJ or HC. The shape classifier is used
to build feature vectors for training pattern classifiers for multiclass
classification.
Using the Base Shape Classifier
Given a new shape, the shape is fitted to the IWMJ and HC SSM as
described in the section on ASM fitting to create a description vector
xSC = (ei, eh, g/a). This vector is used by the shape classifier model to
make the decision based on the following equation:
a
x
i
shape
0
SC SC
=
>
homogeneous shape
isolated shapeotherwise
(6)
This equation together with the logistic function gives a straight-
forward explanation for the classifier to make the decision. The new
shape is classified as a homogeneous shape if the probability given by
the logistic function is greater than 0.5. An overview of the method
is shown in Figure 5a.
Multiclass Pattern Classifier and Predictor
The aim of this work is to classify a given traffic (congestion) pattern
into one of five predefined classes (Table 1). The final step now is
to design, train, and test a classifier that can do this. A schematic
overview of the proposed method is shown in Figure 2c.
Since each of these five patterns can be broken down into com-
binations of two (archetype) base shapes (IWMJ and HC), the first
step in classifying a congestion pattern is to break down the pattern
into these base shapes, as shown in Figure 5a. For each of the five
classes a training set can be built. The output data are the class labels
(1 to 5), and the input data are equal to a simple two-dimensional
feature vector (ni, nh), where ni is the number of occurrences of the
IWMJ shape in the given pattern and nh is the number of occurrences
of the HC shape in the given pattern.
ASM Fitting
Gradient
Area
Shape
Predictor
ei
eh
g/a
Isolated and
Homogeneous
Class
Predictor
Isolated and
Homogeneous
Isolated and
Homogeneous
(ni, nh)Class
(a)
(b)
FIGURE 5 Multiclass predictor: (a) base shape prediction given shape and (b) class prediction
given new pattern.
Krishnakumari, Nguyen, Heydenrijk-Ottens, Vu, and van Lint 101
The general idea of the multiclass pattern predictor is given in
Figure 5b. Multiclass logistic regression is used to implement it.
A simple yet efficient method, the so-called one-versus-all (OVA)
scheme, was used for training; it constructs one binary logistic
regression model for each class and assigns a probability p to the
training sample belonging to this class versus the probability that it
belongs to any of the other classes.
After the classifier is trained, there are five coefficients, ai=FC1,...,FC5,
corresponding to five binary logistic regression models of five classes.
For a given (new) pattern with feature vector xFC = (ni, nh), the class
label is assigned to it, giving rise to the largest probability, that is,
px
i
i
clas
sargmaxFC FC (7)a
i
()
=
EXPERIMENTAL SETUP
The data used in this study come from the National Data Warehouse
for Traffic Information (19), a Dutch organization that archives and
provides real-time access to traffic data from the Dutch agency of the
Ministry of Infrastructure and the Environment (Rijkswaterstaat),
the 12 Dutch provinces, two metropolitan regions, and four of the
largest cities in the Netherlands (Amsterdam, Rotterdam, Utrecht,
and The Hague). The data used for the experiments were collected
from two heavily congested roads in the Netherlands:
• Southbound A13 from Den Haag-Zuid to Rotterdam center and
• Eastbound A15 from Havens 5500–5700 to Rotterdam
Ijsselmonde.
Space–time plots of carriageway speed for these two roads were
constructed with all available loop data for the entire month of
March 2015. Each space–time plot represents a period of 24 h from
00:01 to 23:59 at a resolution of 30 s and 100 m. Each of the plots
contains multiple congestion patterns. After each pattern was iden-
tified and extracted separately with naïve contour extraction, there
were 140 traffic congestion patterns detected on the first road and
160 patterns on the second road. Because only large-scale patterns
with similar space–time ratios are of interest here, 120 patterns were
selected to create the classes. The patterns were manually classified
into five classes based on spatiotemporal extent and characteristics
of traffic congestion, as shown in Table 1. The number of patterns
per class is small; the first trial was intended to demonstrate the ideas
and learn lessons for larger-scale application. After the classes were
identified by experts, the naïve contours were refined to construct
better distinctive contours from the patterns. From these refined con-
tours, two base shapes were identified; 35 contours were manually
chosen to build the SSM models of both homogeneous and isolated
base shapes. These same contours are used to train the shape classifier.
A simple OVA approach was used for the multiclass predictor that
reduced the problem of classifying contours among five classes into
five feature vectors, where each model discriminated a given class
from the other four classes (20). For this OVA approach, there were
N = 5 binary classifiers, the kth classifier trained with positive exam-
ples belonging to class k and negative examples belonging to the
other four classes. The classifier that produced the maximum output
was considered to be the best fit. Rifkin and Klautau stated that,
provided the binary classifiers are tuned well, this OVA approach
is extremely powerful and produces results that often are at least as
accurate as other, more complex approaches (20). The accuracy of the
ASM OVA classifier was measured to judge the overall efficiency of
the algorithm with the following formula:
accuracy numberofcorrectly classified images
total numberofimages(8)=
A confusion matrix, or contingency table (21), is constructed to
investigate which class is behaving poorly, and that class is studied
further for a better understanding of the data and to make future
recommendations to improve accuracy.
RESULTS AND DISCUSSION
This section presents the results of the proposed method. The OVA
ensemble of ASM models achieved an average prediction accuracy
of 70%, which is relatively low compared with the state of the art.
However, this method represents five classes by using only two
archetype shapes, whereas other methods need more degrees of
freedom for defining each class. Thus, the presented method can
constrain the classification complexity while providing satisfactory
accuracy for a preliminary study with such a small data set. A more
elaborate confusion matrix is given in the Table 2. The table shows
the percentage of correctly and erroneously classified patterns in
each class given the ground truth. For example, for the IWMJs class,
the ground truth patterns in that class were correctly classified with
81% accuracy, but there were some patterns in other classes that
were wrongly classified as IWMJ. The high-frequency WMJs class
contains the most patterns that were wrongly classified with 50%
accuracy.
Table 2 shows that two classes have low accuracy compared with
the other classes, namely, high-frequency WMJ and mixed. It is
TABLE 2 Confusion Matrix for OVA Evaluation
Predicted
Known Isolated
Low
Frequency
High
Frequency Homogeneous Mixed
Isolated 0.81 0.03 0.03 0.13 0.00
Low frequency 0.03 0.76 0.09 0.09 0.03
High frequency 0.00 0.28 0.50 0.16 0.06
Homogeneous 0.21 0.00 0.00 0.74 0.05
Mixed 0.05 0.00 0.22 0.17 0.56
102 Transportation Research Record 2645
hypothesized that this result reflects the small training data set or
the limited representativeness of the samples in that class. The data
were further investigated to qualitatively test this hypothesis.
Two of the wrongly classified patterns are shown in Figure 6a;
in this case, both were wrongly classified as mixed patterns instead
of low-frequency WMJ and HC, respectively. These patterns are
actually mixed congestion patterns. The classifier confused these
because they have a feature vector similar to that of the mixed class.
Successful classification depends on the subjective manual classifi-
cation process and the degree to which labeling patterns that can be
distinguished through OVA ASM are successful. This definition of
success was confirmed by an initial analysis of the wrongly classified
patterns in which the authors agreed with the classifier’s decision
on 15% of all wrongly classified patterns rather than with the initial
manual classification. To reduce the subjectivity of the manual clas-
sification, unsupervised clustering and reinforcement learning can be
used as an alternative for building the classes.
A second reason for the low accuracy is the constraints of the
assumptions that have been made for extracting the contours, such
as thresholding at 65 km/h. These are evident in Figure 6b, where
the highlighted shapes consist of combinations of two or more
isolated shapes and combinations of isolated and homogeneous
shapes, respectively. Finally, speed was used exclusively to distin-
guish patterns. Identifying and classifying distinct traffic patterns
also requires information on the flows, particularly when one is dis-
tinguishing between congested patterns. Using just the speed and
the naïve single speed thresholding can uniquely identify only a few
patterns. To extend the repertoire of the classifiers, more archetypes
are needed to approximate all the unique shapes that are present
within the patterns, both speed and flow patterns must be combined,
and meta-information (speed limits, geometry, etc.) may be needed
to construct a more dynamic thresholding method to extract the
shapes from the patterns.
Still, given all these limitations, the simplicity and transparency
of the method (a few base shapes + logistic regression) offers great
potential for further research and application development.
CONCLUSION AND FUTURE WORK
This paper proposed a method, consisting of contour detection, shape
models, and a multiclass OVA classifier, to automatically classify
spatiotemporal traffic patterns with network sensor data. The various
components were adequate for labeling complex traffic patterns with
acceptable accuracy, although the data set used was too small to
warrant definite conclusions. With only two archetype shapes and
simple logistic classifiers, 70% accuracy of the classification on the
test data was achieved. Furthermore, for the 30% of cases in which
the classifier could not decide on any of the five designated patterns,
the contour shapes were affected by the assumptions and subjective
manual labeling was used to construct the training data.
There are many future directions of research that can further
improve the accuracy. First, the ensemble scores can be used to
directly put a confidence score to each classification. Further sophis-
tication can be reached by ensemble bootstrapping or more modern
Bayesian techniques. Second, an iterative manual–automated classi-
(a)
Low Frequency Ú Mixed
Speed (km/h)
Speed (km/h)
0
20
40
60
80
100
120
Homogeneous Ú Mixed
0
20
40
60
80
100
120
(b)
FIGURE 6 Synthesis of wrongly classified patterns: (a) manually classified and (b) potential base shapes.
Krishnakumari, Nguyen, Heydenrijk-Ottens, Vu, and van Lint 103
fication procedure is envisaged in which the manual classification is
reevaluated after each training round with the classification scores
of the OVA ASM. This procedure could yield splitting or combin-
ing classes, hierarchically subdividing classes, or otherwise. Third,
metadata (type of date and time, circumstances, topological charac-
teristics, etc.) can be combined to better classify the patterns. Another
extension will combine speed plots with flow contour plots for better
definition of classes of congestion and for improved accuracy. Finally,
the database will be further enriched with more congestion patterns,
with a goal of identifying more complex patterns.
ACKNOWLEDGMENTS
The authors acknowledge the Dutch National Data Warehouse for
Traffic Information for sponsoring this project. This work received
support from the SETA Project, funded by the European Union’s
Horizon 2020 Research and Innovation Program, and an Australian
Research Council fellowship grant. The authors thank the anonymous
reviewers for their constructive remarks.
REFERENCES
1. Treiber, M., and D. Helbing. Reconstructing the Spatio-Temporal Traffic
Dynamics from Stationary Detector Data. Cooperative Transportation
Dynamics, Vol. 1, No. 3, 2002, pp. 3.1–3.24.
2. Schreiter, T., H. van Lint, M. Treiber, and S. Hoogendoorn. Two Fast
Implementations of the Adaptive Smoothing Method Used in Highway
Traffic State Estimation. In Proceedings of the 13th International Con-
ference on Intelligent Transportation Systems, 2010, IEEE, New York,
2010, pp. 1202–1208. https://doi.org/10.1109/ITSC.2010.5625139.
3. van Lint, J., and S. P. Hoogendoorn. A Robust and Efficient Method for
Fusing Heterogeneous Data from Traffic Sensors on Freeways. Com-
puter-Aided Civil and Infrastructure Engineering, Vol. 25, No. 8, 2010,
pp. 596–612. https://doi.org/10.1111/j.1467-8667.2009.00617.x.
4. Schreiter, T., H. van Lint, Y. Yuan, and S. Hoogendoorn. Propagation
Wave Speed Estimation of Freeway Traffic with Image Processing
Tools. Presented at 89th Annual Meeting of the Transportation Research
Board, Washington, D.C., 2010.
5. Treiber, M., and A. Kesting. Validation of Traffic Flow Models with
Respect to the Spatiotemporal Evolution of Congested Traffic Patterns.
Transportation Research Part C: Emerging Technologies, Vol. 21, No. 1,
2012, pp. 31–41. https://doi.org/10.1016/j.trc.2011.09.002.
6. Kerner, B. S., H. Rehborn, M. Aleksic, and A. Haug. Recognition and
Tracking of Spatial–Temporal Congested Traffic Patterns on Freeways.
Transportation Research Part C: Emerging Technologies, Vol. 12, No. 5,
2004, pp. 369–400. https://doi.org/10.1016/j.trc.2004.07.015.
7. Andrews Sobral, L. O., L. Schnitman, and F. De Souza. Highway Traf-
fic Congestion Classification Using Holistic Properties. Presented at
10th IASTED International Conference on Signal Processing, Pattern
Recognition and Applications, 2013.
8. Jin, X., D. Srinivasan, and R. L. Cheu. Classification of Freeway Traffic
Patterns for Incident Detection Using Constructive Probabilistic Neural
Networks. IEEE Transactions on Neural Networks, Vol. 12, No. 5, 2001,
pp. 1173–1187. https://doi.org/10.1109/72.950145.
9. Riaz, A., and S. A. Khan. Traffic Congestion Classification Using
Motion Vector Statistical Features. In Proceedings of the 6th Inter-
national Conference on Machine Vision, International Society for Optics
and Photonics, 2013.
10. Thianniwet, T., S. Phosaard, and W. Pattara-Atikom. Classification
of Road Traffic Congestion Levels from Vehicle’s Moving Patterns:
A Comparison Between Artificial Neural Network and Decision Tree
Algorithm. In Electronic Engineering and Computing Technology
(S. L. Ao and L. Gelman, eds.), Springer, New York, 2010, pp. 261–271.
https://doi.org/10.1007/978-90-481-8776-8_23.
11. Nguyen, H. N., P. Krishnakumari, H. L. Vu, and H. van Lint. Traffic
Congestion Pattern Classification Using Multi-Class SVM. In Proceed-
ings of the 19th International Conference on Intelligent Transportation
Systems, IEEE, New York, 2016, pp. 1059–1064.
12. Suzuki, S., and K. Abe. Topological Structural Analysis of Digitized
Binary Images by Border Following. Computer Vision Graphics and
Image Processing, Vol. 30, No. 1, 1985, pp. 32–46. https://doi.org/10.1016
/0734-189X(85)90016-7.
13. Vincent, L. Morphological Grayscale Reconstruction in Image Analysis:
Applications and Efficient Algorithms. IEEE Transactions on Image
Processing, Vol. 2, No. 2, 1993, pp. 176–201. https://doi.org/10.1109
/83.217222.
14. Helbing, D., M. Treiber, A. Kesting, and M. Schönhof. Theoretical vs.
Empirical Classification and Prediction of Congested Traffic States.
European Physical Journal B, Vol. 69, No. 4, 2009, pp. 583–598.
https://doi.org/10.1140/epjb/e2009-00140-5.
15. Cootes, T. F., C. J. Taylor, D. H. Cooper, and J. Graham. Active Shape
Models—Their Training and Application. Computer Vision and Image
Understanding, Vol. 61, No. 1, 1995, pp. 38–59. https://doi.org/10.1006
/cviu.1995.1004.
16. Chetverikov, D., D. Svirko, D. Stepanov, and P. Krsek. The Trimmed
Iterative Closest Point Algorithm. In Proceedings of the 16th Inter-
national Conference on Pattern Recognition, IEEE, New York, 2002,
pp. 545–548. https://doi.org/10.1109/ICPR.2002.1047997.
17. Goodall, C. Procrustes Methods in the Statistical Analysis of Shape.
Journal of the Royal Statistical Society, Series B: Methodological,
Vol. 53, 1991, pp. 285–339.
18. Hosmer, D. W., S. Lemeshow, and R. X. Sturdivant. Introduction to the
Logistic Regression Model. In Applied Logistic Regression, John Wiley
& Sons, New York, 2000, pp. 1–30.
19. National Data Warehouse of Traffic Information. http://www.ndw.nu/en/.
20. Rifkin, R., and A. Klautau. In Defense of One-Vs-All Classification.
Journal of Machine Learning Research, Vol. 5, 2004, pp. 101–141.
21. Fawcett, T. An Introduction to ROC Analysis. Pattern Recognition
Letters, Vol. 27, No. 8, 2006, pp. 861–874. https://doi.org/10.1016
/j.patrec.2005.10.010.
The Standing Committee on Artificial Intelligence and Advanced Computing
Applications peer-reviewed this paper.
