Traffic Congestion Pattern Classification Using Multiclass Active Shape Models

2017 ◽  
Vol 2645 (1) ◽  
pp. 94-103 ◽  
Author(s):  
Panchamy Krishnakumari ◽  
Tin Nguyen ◽  
Léonie Heydenrijk-Ottens ◽  
Hai L. Vu ◽  
Hans van Lint
Keyword(s):  
Expert Knowledge ◽  
Statistical Shape Model ◽  
Transport Systems ◽  
Active Shape Model ◽  
Traffic Patterns ◽  
Shape Model ◽  
Active Shape Models ◽  
Contour Maps ◽  
Active Shape

Identifying and classifying traffic and congestion patterns are essential 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 proposed 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.

scholarly journals Creating a 2D Active Shape Model Using itk::ImagePCAShapeModelEstimator

2011 ◽  
Author(s):  
John Durkin ◽  
David Miller ◽  
Kenneth Urish
Keyword(s):  
Active Contour ◽  
Active Shape Model ◽  
Knee Cartilage ◽  
Shape Model ◽  
Active Shape Models ◽  
Contour Segmentation ◽  
Shape Models ◽  
Segmentation Algorithms ◽  
Active Shape ◽  
Weak Boundaries

Although many variations of active contour segmentation algorithms exist, most are based on solely edge criteria and breakdown or leak at weak boundaries. One solution to this problem is constraining the segmented area to only statistically possible shapes with the guidance of a shape model. The purpose of this document is to fill the void in the ITK user guide on building active shape models. We describe how to create a 2d active shape model of articular femoral knee cartilage using ITK’s ImagePCAShapeModelEstimator. Sample code and example images are provided for displaying the initial principle components of variation. Shape models built with our code can be used for segmentation with itk::GeodesicActiveContourShapePriorLevelSetImageFilter.

scholarly journals The interleaved partial active shape model search (IPASM) algorithm – Preliminary results of a novel approach towards 3D ultrasound-based bone surface reconstruction

10.29007/ckw2 ◽  
2018 ◽  
Author(s):  
Christoph Hänisch ◽  
Benjamin Hohlmann ◽  
Klaus Radermacher
Keyword(s):  
Search Algorithm ◽  
Imaging Modality ◽  
Statistical Shape Model ◽  
Training Data ◽  
Active Shape Model ◽  
Imaging Data ◽  
Shape Model ◽  
Underlying Distribution ◽  
Model Search ◽  
Active Shape

In applications such as biomechanical simulations or implant planning, bone surfaces of the knee are most often reconstructed from computed tomography or magnetic resonance imaging data. Here, ultrasound (US) might serve as an alternative imaging modality. However, established methods cannot directly be transferred to US due to differences in imaging quality and underlying physics.In this paper, we present a generalisation of the well-known active shape model search algorithm (ASM) that allows for segmenting various structures in US volume images that are too large to be captured with a single recording. The multi-view segmentation approach uses a-priori knowledge in the form of a statistical shape model (SSM) as is the case with the classical ASM. This allows to extrapolate missing information and to generate shapes that comply with the underlying distribution of some training data. The main differences are, however, that the SSM is not only adapted to a single image but to multiple images and that the adaption process is interleaved. As a result, within each iteration the surface information of all sub-volumes is propagated and used in all subsequent steps.In-silico tests were conducted to investigate how this algorithm would perform in real tracked US data. US volume images were split in slightly overlapping sub-volumes, noise was added, and the alignment was distorted. We could show that the algorithm is capable of reconstructing shapes in the lower millimetre range and for some cases even with submillimetric accuracy. The algorithm is hardly affected by orientation errors below 5 degrees and displacement errors below 5 mm; above these limits, the average absolute SDE as well as its associated variance increases.

scholarly journals Intensity Profiles in Active Shape Model

2020 ◽  
Vol 34 (5) ◽  
pp. 531-539
Author(s):  
Moulkheir Naoui ◽  
Ghalem Belalem
Keyword(s):  
Image Segmentation ◽  
Active Shape Model ◽  
Complex Structures ◽  
Shape Model ◽  
Object Shape ◽  
Active Shape Models ◽  
Matching Process ◽  
Shape Models ◽  
Active Shape ◽  
The Right

Active shape model is a deformable model which has proven very successful results in the field of image segmentation. The success of ASM model lies in its ability to find the right positions of all landmark points which define the object shape. Intensity profiles are an important part of the Active Shape Models (ASM) which help steer and optimize matching process. However, their simplicity in the standard version of the ASM turns into weakness. The difficulties are met when they are applied to complex structures. The main purpose of this paper is to give a review and discussion about the alternatives proposed in the literature that provide more elaborated intensity models and their impact on the performance of ASM.

Human face shape classification method based on active shape model

2009 ◽  
Vol 29 (10) ◽  
pp. 2710-2712 ◽  
Author(s):  
Li-qiang DU ◽  
Peng JIA ◽  
Zong-tan ZHOU ◽  
De-wen HU
Keyword(s):  
Classification Method ◽  
Active Shape Model ◽  
Shape Classification ◽  
Human Face ◽  
Shape Model ◽  
Face Shape ◽  
Active Shape

Echocardiogram segmentation using active shape model and mean squared eigenvalue error

2021 ◽  
Vol 69 ◽  
pp. 102807
Author(s):  
Yasser Ali ◽  
Soosan Beheshti ◽  
Farrokh Janabi-Sharifi
Keyword(s):  
Active Shape Model ◽  
Shape Model ◽  
Active Shape

Three-dimensional active shape model matching for left ventricle segmentation in cardiac CT

2003 ◽  
Author(s):  
Hans C. van Assen ◽  
Rob J. van der Geest ◽  
Mikhail G. Danilouchkine ◽  
Hildo J. Lamb ◽  
Johan H. C. Reiber ◽  
...  
Keyword(s):  
Left Ventricle ◽  
Cardiac Ct ◽  
Three Dimensional ◽  
Active Shape Model ◽  
Model Matching ◽  
Shape Model ◽  
Active Shape ◽  
Ventricle Segmentation
Sign in / Sign up

Export Citation Format

Share Document