Joint tracking and classification of extended targets with complex shapes

2021 ◽  
Vol 22 (6) ◽  
pp. 839-861
Author(s):  
Liping Wang ◽  
Ronghui Zhan ◽  
Yuan Huang ◽  
Jun Zhang ◽  
Zhaowen Zhuang
Keyword(s):  
Complex Shapes ◽  
Joint Tracking

scholarly journals Joint Tracking and Classification of Extended Targets Using Random Matrix and Bernoulli Filter for Time-Varying Scenarios

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 129584-129603 ◽  
Author(s):  
Liping Wang ◽  
Yuan Huang ◽  
Ronghui Zhan ◽  
Jun Zhang
Keyword(s):  
Random Matrix ◽  
Time Varying ◽  
Bernoulli Filter ◽  
Joint Tracking

scholarly journals Joint Tracking and Classification of Multiple Targets with Scattering Center Model and CBMeMBer Filter

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1679 ◽  
Author(s):  
Ronghui Zhan ◽  
Liping Wang ◽  
Jun Zhang
Keyword(s):  
Sequential Monte Carlo ◽  
Multiple Targets ◽  
Range Resolution ◽  
Aspect Angle ◽  
Scattering Center ◽  
Simulation Results ◽  
Wideband Radar ◽  
Joint Tracking ◽  
High Range

This paper deals with joint tracking and classification (JTC) of multiple targets based on scattering center model (SCM) and wideband radar observations. We first introduce an SCM-based JTC method, where the SCM is used to generate the predicted high range resolution profile (HRRP) with the information of the target aspect angle, and target classification is implemented through the data correlation of observed HRRP with predicted HRRPs. To solve the problem of multi-target JTC in the presence of clutter and detection uncertainty, we then integrate the SCM-based JTC method into the CBMeMBer filter framework, and derive a novel SCM-JTC-CBMeMBer filter with Bayesian theory. To further tackle the complex integrals’ calculation involved in targets state and class estimation, we finally provide the sequential Monte Carlo (SMC) implementation of the proposed SCM-JTC-CBMeMBer filter. The effectiveness of the presented multi-target JTC method is validated by simulation results under the application scenario of maritime ship surveillance.

A Language for Financial Chart Patterns

2018 ◽  
Vol 17 (05) ◽  
pp. 1537-1560
Author(s):  
Jiajun Zhu ◽  
Yuqing Wan ◽  
Yain-Whar Si
Keyword(s):  
Financial Time Series ◽  
Composite Index ◽  
Pattern Language ◽  
Future Price ◽  
Domain Specific ◽  
Complex Shapes ◽  
Dow Jones Industrial Average ◽  
Price Trends ◽  
Chart Patterns

In stock markets around the world, financial analysts continuously monitor and screen chart patterns (technical patterns) to predict future price trends. Although a plethora of methods have been proposed for classification of these patterns, there is no uniform standard in defining their shapes. To facilitate the classification and discovery of chart patterns in financial time series, we propose a novel domain-specific language called “Financial Chart Pattern Language” (FCPL). The proposed language is formally described in Extended Backus–Naur Form (EBNF). FCPL allows incremental composition of complex shapes from simple basic units called primitive shapes. Hence, patterns defined in FCPL can be reused for composing new chart patterns. FCPL separates the specification of a chart pattern from the mechanism of its implementation. Due to its simplicity, FCPL can be used by stock market experts and end users to describe the patterns without programming expertise. To highlight its capabilities, several representative financial chart patterns are defined in FCPL for illustration. In the experiments, we classify several representative chart patterns from the datasets of HANG SENG INDEX (HSI), NYSE AMEX COMPOSITE INDEX (NYSE), and Dow Jones Industrial Average (DJI).

Geometric Tools Dedicated to the Adaption and Idealization of 3D Models for F.E. Analysis

1997 ◽  
Author(s):  
Philippe Véron ◽  
Jean-Claude Léon
Keyword(s):  
Geometric Model ◽  
A Priori ◽  
3D Models ◽  
Geometric Configuration ◽  
A Posteriori ◽  
Complex Shapes ◽  
Mesh Adaption ◽  
Node Removal ◽  
Candidate Node

Abstract Geometric adaptions and idealizations of 3D models for F.E. analysis purposes are often necessary. Geometric tools are proposed to partly automatize shape adaptions and idealizations of polyhedral models. The simplification process is monitored using error zones attached to each polyhedron vertex. Their dimension may be either set by the designer, by an a posteriori or by an a priori mechanical mesh adaption process. Such an approach allows to process various polyhedral models characterized by general and complex shapes. A classification of nodes and edges is carried out to apply a specific node removal operator in accordance with the local geometric configuration around a node. Moreover, specific criteria are used to select the best candidate node for removal. Also, additional operators have been developed to process particular configurations and produce the final idealized model. During this geometric idealization process, the shape restitution of the part is maintained through an inheritance process of the error zones. Topological changes as well as the coherence of the non-manifold geometric model are managed using specific criteria to produce acceptable approximations of idealized geometries.

scholarly journals Shape-to-graph Mapping Method for Efficient Characterization and Classification of Complex Geometries in Biological Images

2020 ◽  
Author(s):  
William Pilcher ◽  
Xingyu Yang ◽  
Anastasia Zhurikhina ◽  
Olga Chernaya ◽  
Yinghan Xu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Quantitative Information ◽  
Mapping Method ◽  
Terminal Point ◽  
Small Data ◽  
Imaging Data ◽  
Biophysical Parameters ◽  
Biological Images ◽  
Complex Shapes

AbstractWith the ever-increasing quality and quantity of imaging data in biomedical research comes the demand for computational methodologies that enable efficient and reliable automated extraction of the quantitative information contained within these images. One of the challenges in providing such methodology is the need for tailoring algorithms to the specifics of the data, limiting their areas of application. Here we present a broadly applicable approach to quantification and classification of complex shapes and patterns in biological or other multi-component formations. This approach integrates the mapping of all shape boundaries within an image onto a global information-rich graph and machine learning on the multidimensional measures of the graph. We demonstrated the power of this method by (1) extracting subtle structural differences from visually indistinguishable images in our phenotype rescue experiments using the endothelial tube formations assay, (2) training the algorithm to identify biophysical parameters underlying the formation of different multicellular networks in our simulation model of collective cell behavior, and (3) analyzing the response of U2OS cell cultures to a broad array of small molecule perturbations.Author SummaryIn this paper, we present a methodology that is based on mapping an arbitrary set of outlines onto a complete, strictly defined structure, in which every point representing the shape becomes a terminal point of a global graph. Because this mapping preserves the whole complexity of the shape, it allows for extracting the full scope of geometric features of any scale. Importantly, an extensive set of graph-based metrics in each image makes integration with machine learning routines highly efficient even for a small data sets and provide an opportunity to backtrack the subtle morphological features responsible for the automated distinction into image classes. The resulting tool provides efficient, versatile, and robust quantification of complex shapes and patterns in experimental images.

Sign in / Sign up

Export Citation Format

Share Document