As part of a broader research effort in multispectral image analysis, an improved segmentation algorithm based on the classical Watershed concept was developed. A requirement for this research was to develop a segmentation algorithm that could effectively extract objects of interest in both visual and thermal image pairs. The classical Watershed algorithm can be enhanced with "markers" identifying clusters of pixels belonging to the same object or to the background. There are several ways to create the markers and the proposed Watershed with Thermal Markers allows the user to extract objects of interest from both visual and/or thermal dataset using an initial seed extracted from the thermal image.
Computer and machine vision applications are used in numerous fields to analyze static and dynamic imagery in order to assist or automate decision-making processes. Advancements in sensor technologies now make it possible to capture and visualize imagery at various wavelengths (or bands) of the electromagnetic spectrum. Multispectral imaging has countless applications in various fields including (but not limited to) security, defense, space, medical, manufacturing and archeology. The development of advanced algorithms to process and extract salient information from the imagery is a critical component of the overall system performance.
The fundamental objective of this research project was to investigate the benefits of combining imagery from the visual and thermal bands of the electromagnetic spectrum to improve the recognition rates and accuracy of commonly found objects in an office setting. A multispectral dataset (visual and thermal) was captured and features from the visual and thermal images were extracted and used to train support vector machine (SVM) classifiers. The SVM’s class prediction ability was evaluated separately on the visual, thermal and multispectral testing datasets.
The use of the intensity change and line-of-sight (LOS) change concepts have previously been documented in the open-literature
as techniques used by non-imaging infrared (IR) seekers to reject expendable IR countermeasures (IRCM).
The purpose of this project was to implement IR counter-countermeasure (IRCCM) algorithms based on target intensity
and kinematic behavior for a generic imaging IR (IIR) seeker model with the underlying goal of obtaining a better
understanding of how expendable IRCM can be used to defeat the latest generation of seekers.
The report describes the Intensity Ratio Change (IRC) and LOS Rate Change (LRC) discrimination techniques. The
algorithms and the seeker model are implemented in a physics-based simulation product called Tactical Engagement
Simulation Software (TESS™). TESS is developed in the MATLAB®/Simulink® environment and is a suite of RF/IR
missile software simulators used to evaluate and analyze the effectiveness of countermeasures against various classes of
guided threats.
The investigation evaluates the algorithm and tests their robustness by presenting the results of batch simulation runs of
surface-to-air (SAM) and air-to-air (AAM) IIR missiles engaging a non-maneuvering target platform equipped with
expendable IRCM as self-protection. The report discusses how varying critical parameters such track memory time,
ratio thresholds and hold time can influence the outcome of an engagement.
The paper describes a methodology for characterizing the signatures of targets for Imaging Infrared (IIR) missiles and
generating dynamic missile engagement scenarios using MathWorks tools (primarily MATLAB and Simulink). The
over-all objective of this work was to develop high fidelity physics-based simulations of the attack of IIR missiles on
targets that are using various types of countermeasures for survivability. While the methodology has been implemented
in products used for analyses of both ship and main battle tank protection this paper focuses on the ship application.
The methodology involves a multi-step process. First the infrared signatures of the objects are characterized using a
graphical tool that enables the user to select individual or groups of surfaces on the objects (targets and countermeasures)
and specify their surface temperatures and spectral emissivities. Second, a dynamic IR scene generator creates the scene
as viewed by the missile's seeker. Then an imaging IR seeker, using the option of several tracking algorithms,
discriminates the target. Finally, the inclusion of dynamic models for missile guidance, aerodynamics and propulsion
together with signal propagation enable the closing of the loop in the missile's fly-out. The simulation dynamically
computes the distance between each surface and the missile seeker and uses the specified atmospheric attenuation profile
to produce a simulated IR image at the seeker. This is processed using several optional tracking algorithms to generate
steering signals. This process is repeated every time-step of the simulation and determines the trajectory of the missile
and the hit or miss of the missile at engagement completion.
The paper includes the following topics: characterizing IR signatures, generating dynamic IR scenes, simulating
representative close-loop missile fly-out engagements, evaluating performance and running simulation batches.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.