An automatic target recognizer (ATR) is a real-time or near-real-time image/
signal-understanding system. An ATR is presented with a stream of data. It
outputs a list of the targets that it has detected and recognized in the data
provided to it. A complete ATR system can also perform other functions such
as image stabilization, preprocessing, mosaicking, target tracking, activity
recognition, multi-sensor fusion, sensor/platform control, and data packaging
for transmission or display.
In the early days of ATR, there were fierce debates between proponents of
signal processing and those in the emerging field of computer vision. Signal
processing fans were focused on more advanced correlation filters, stochastic
analysis, estimation and optimization, transform theory, and time-frequency
analysis of nonstationary signals. Advocates of computer vision said that
signal processing provides some nice tools for our toolbox, but what we really
want is an ATR that works as well as biological vision. ATR designers were
less interested in processing signals than understanding scenes. They proposed
attacking the ATR problem through artificial intelligence (AI), computational
neuroscience, evolutionary algorithms, case-based reasoning, expert systems,
and the like. Signal processing experts are interested in tracking point-like
targets. ATR engineers want to track a target with some substance to it,
identify what it is, and determine what activity it is engaged in. Signal
processing experts keep coming up with better ways to compress video. ATR
engineers want more intelligent compression. They want the ATR to tell the
compression algorithm which parts of the scene are more important and hence
deserving of more bits in the allocation. ATR, in and of itself, can be thought of as
a data reduction technique. The ATR takes in a lot of data and outputs
relatively little data. Data reduction is necessary due to bandwidth limitations of the data link and workload limits of the time-strapped human operator. People are very good at analyzing video until fatigue sets in or they get distracted. They don’t want to be like the triage doctor at the emergency ward, assessing everything that comes in the door, continually assigning priorities to items deserving further attention. Pilots and ground station operators want a
machine to relieve their burden as long as it rarely makes a mistake. Trying to
do this keeps ATR engineers employed. As often told to the author, pilots and image analysts are not looking for machines to replace them entirely. However, such decisions will be made higher up in the chain of command as ATR technology progresses.
The human vision system is not “designed” to analyze certain kinds of
data such as rapid step-stare imagery, complex-valued signals that arise in
radars, hyperspectral imagery, 3D LADAR data, or fusion of signal data with
various forms of precise metadata. ATR shines when the sustained data rate is
too high or too prolonged for the human brain, or the data is not well suited
for presentation to humans. Nevertheless, most current ATRs operate with
humans-in-the-loop. Humans, at present, are much better than ATRs at tasks
requiring consultation, comprehension, and judgement. Humans still make
the final decision and determine the action to be taken. This means that ATR
output, which is statistical and multi-faceted by nature, has to be presented to
the human decision makers in an easily understood form. This is a difficult
man–machine interface problem. Marching toward the future, more autonomous
robotic systems will necessarily rely more on ATRs to substitute for
human operators, possibly serving as the “brains” of entire robotic platforms.
We leave this provocative topic to the end of the book.
Systems engineers took notice once ATRs became deployable. Systems
engineers are grounded in harsh reality. They care little about the debate
between signal processing and computer vision. They don’t want to hear
about an ATR being brain-like. They are not interested in which classification
paradigm performs 1% better than the next. They care about the concept of
operations (ConOps) and how it directs performance and functionality. They
care about mission objectives and mission requirements. They want to identify
all possible stakeholders, form an integrated product team, determine key
performance parameters (KPPs), and develop test and evaluation (T&E)
procedures to determine if performance requirements are met. Self-test is the
norm for published papers and conference talks. Independent test and
evaluation, laboratory blind tests, field tests, and software regression tests are
the norm for determining if a system is deployable. The systems engineer’s
focus is broader than ATR performance. Systems engineers want the entire
system, or system of systems, to work well, including platform, sensors, ATR,
and data links. They want to know what data can be provided to the ATR and
what data the ATR can provide to the rest of the system. They want to know
how one part of the system affects all other parts of the system. Systems
designers care a lot about size, weight, power, latency, current and future
costs, logistics, timelines, mean time between failure, and product repair and
upgrade. They want to know the implications of system capture by the enemy.
At one time, ATR was the sole charge of the large defense electronics
companies, working closely with the government labs. Only the defense
companies and government have fleets of data collection aircraft, high-end
sensors, and access to foreign military targets. Although air-to-ground has been the focus of much ATR work, ATR actually covers a wide range of
sensors, operating within or between the layers of space, air, ocean/land
surface, and undersea/underground. Although the name ATR implies
recognition of targets, ATR engineers have broader interests. ATR groups
tackle any type of military problem involving the smart processing of imagery
or signals. The government (or government-funded prime contractor) is
virtually the only customer. So, some of the ATR engineer’s time is spent
reporting to the government, participating in joint data collections, taking
part in government-sponsored tests, and proposing new programs to the
government.
Since the 1960s, the field of ATR has advanced in parallel with similar
work in the commercial sector and academia, involving industrial automation,
medical imaging, surveillance and security, video analytics, and space-based
imaging. Technologies of interest to both the commercial and defense
sector include low-power processors, novel sensors, increased system
autonomy, people detection, robotics, rapid search of vast amounts of data
(big data), undersea inspection, and remote medical diagnosis. The bulk of
funding in some of these areas has recently shifted from the defense to the
commercial sector. More money is spent on computer animation for
Hollywood movies than for the synthesis of forward-looking infrared (FLIR)
and synthetic aperture radar (SAR) imagery. The search engine companies are
investing much more in neural networks compared to the defense companies.
Well-funded brain research programs are investigating the very basis of
human vision and cognitive processing. The days of specialized military
processors (e.g., VHSIC) are largely over. Reliance is now on chips in high-volume
production: multi-core processors (e.g., Intel and ARM), FPGAs
(e.g., Xilinx and Intel/Altera), and GPUs (e.g., Nvidia and AMD). Highly
packaged sensors (visible, FLIR, LADAR, and radar) combined with
massively parallel processors are advancing rapidly for the automotive
industry to meet new safety standards (e.g., Intel/MobilEye). Millions of
systems will soon be produced per year. Current advanced driver assistance
systems (ADAS) can detect pedestrians, animals, bicyclists, road signs, traffic
lights, cars, trucks, and road markers. These are a lot like ATR tasks. The
rapid advancement of ADAS will lead to driverless cars.
Some important differences between ATRs and commercial systems are
worth noting. ATRs generally have to detect and recognize objects at much
longer ranges than commercial systems. Enemy detection and recognition are
non-cooperative processes. Although a future car might have a LADAR,
radar, or FLIR sensor, it won’t have one that can produce high-quality data
from a 20,000-ft range. An ADAS will detect a pedestrian but won’t report if
he is carrying a rifle. Search engine companies need to search large volumes of
data with an image-based search, but they don’t have the metadata to help the
search, such as is available on military platforms. That being said, the cost and innovation rate of commercial electronics can’t be matched by military
systems. The distinction between commercial and military systems is starting
to blur in some instances. Cell phones now include cameras, inertial
measurement units, GPS, computers, algorithms, and transmitters/receivers.
Slightly rugged versions of commercial cell phones and tablet computers are
starting to be used by the military, even with ATR apps. “Toy” drones are
approaching the sophistication of the smallest military unmanned air vehicles.
They are now produced in volumes of a million per year. ATR engineers are
in tune with advances in the commercial sector and their applicability to
ATR. Even their hobbies tend to focus on technology, e.g., hobbies such as
quadcopters, novel cameras, 3D printers, computers, phone apps, robots, etc.
ATR is not limited to a device; it is also a field of research and
development. ATR technology can be incorporated into systems in the form
of self-contained hardware, FPGA code, or higher-level language code. ATR
groups can help add autonomy to many types of systems. ATR can be viewed
very narrowly or very broadly, borrowing concepts from a wide variety of
fields. Papers on ATR are often of the form: “Automatic Target Recognition
using XXX,” where the XXX can be any technology such as super-resolution,
principal component analysis, sparse coding, singular value decomposition,
Eigen templates, correlation filters, kinematic priors, adaptive boosting,
hyperdimensional manifolds, Hough transforms, foveation, etc. In the more
ambitious papers, the XXX is a mélange of technologies, such as fuzzy-rule-based
expert systems, wavelet neural genetic networks, fuzzy morphological
associative memory, optical holography, deformable wavelet templates,
hierarchical support vector machines, Bayesian recognition by parts, etc. Get
the picture? Nearly any type of technology, everything but the kitchen sink,
can be thrown at the ATR problem, with scant large-scale independent
competitive test results to indicate which approach really works best,
supposing that “best” can be defined and measured. This book is not a
comprehensive survey of every technology that has ever been applied to ATR.
This book covers some of the basics of ATR. While some of the topics in this
book can be found in textbooks on pattern recognition and computer vision,
this book focuses on their application to military problems as well as the
unique requirements of military systems.
The topics covered in the book are organized in the way one would design
an ATR. The first step is to understand the military problem and make a list
of potential solutions to the problem. A key issue is the availability of
sufficiently comprehensive sets of data to train and test the potential solutions.
This involves developing a sound test plan, specifying procedures and
equations, and determining who is going to do the testing. Testing isn’t open
ended. Exit criteria are needed to determine when a given test activity has
been successfully completed. The next steps in ATR design are choosing the
detector and classifier. The detector focuses attention on the regions-of-interest in the imagery requiring additional scrutiny. The classifier further processes
these regions-of-interest and is the decision engine for class assignment. It can
operate at any or all levels of a decision tree, from clutter rejection to
identifying a specific vehicle or activity. Detected targets are often tracked.
Target tracking has historically been treated as a separate subject from ATR,
mainly because point-like targets contain too little information to apply an
ATR. However, as sensor resolution improves, the engineering
disciplines of target tracking and ATR are starting to merge. The ATR and
tracker can be united for efficiency and performance. The fifth chapter covers the basics of multisensor fusion. Then it broadens the topic to a variety of other forms of fusion. A strawman design is provided for a more advanced ATR, but with no claim that this is the only
way to construct a next-generation ATR. The strawman design should be
thought of as a brainstormed simple draft proposal intended to generate
discussion of its advantages and disadvantages, and to trigger the generation
of new and better proposals. Future ATRs will have to combine data from
multiple sources. The seventh chapter points out how primitive current ATRs really are, as compared to biological systems. It suggests ways for measuring the intelligence of an ATR.
This goes far beyond the basic performance measurement techniques covered
in Chapter 1. The final chapter examines the role of ATR in its ultimate embodiment—that being lethal autonomous robots. These are air, land, or sea weapons that detect, track, recognize, and attack targets on their own. There is no human-in-the-loop to control the attack; instead, the weapon itself decides when and what to strike, based on guidelines provided to it. Such weapons can come in the form of unmanned ground vehicles, unmanned undersea vehicles, or swarms of mini-drones. The chapter covers legal, moral, ethical, and technical issues, as well as what can go wrong. The first appendix lists the many resources available to the ATR
engineer. Many of the listed agencies supply training and testing data,
perform blind tests, and sponsor research into compelling new sensor and
ATR designs. The second appendix advances the notion that a problem that is
well described is half solved. The third appendix explains the acronyms used
in the book.
CHAPTER 1: ATR technology has benefited from a significant investment
over the last 50 years. However, the once-accepted definitions and evaluation
criteria have been displaced by the march of technology. The first chapter
updates the language for describing ATR systems and provides well-defined
criteria for evaluating such systems. This will move forward collaboration
between ATR developers, evaluators, and end-users.
ATR is used as an umbrella term for a broad range of military technology
beyond just the recognition of targets. In a more general sense, ATR means
sensor data exploitation. Two types of definitions are included in the first
chapter. One type defines fundamental concepts. The other type defines basic
performance measures. In some cases, definitions consist of a list of
alternatives. This approach enables choices to be made to meet the needs of
particular programs. The important point to keep in mind is that within the
context of a particular experimental design, a set of protocols should be
adopted to best fit the situation, applied, and then kept constant throughout
the evaluation. This is especially important for competitive testing.
The definitions given in Chapter 1 are intended for evaluation of end-to-end
ATR systems as well as the prescreening and classifier stages of the systems. Sensor performance and platform characteristics are excluded from the
evaluation. It is recognized that sensor characteristics and other operational
factors affect the imagery and associated metadata. A thorough understanding
of data quality, integrity, synchrony, availability, and timeline are important for
ATR development, test, and evaluation. Data quality should be quantified and
assessed. However, methods for doing so are not covered in this book. The
results and validity of ATR evaluation depend on the representativeness and
comprehensiveness of the development and test data. The adequacy of
development and test data is primarily a budgetary issue. The ATR engineer
should understand and be able to convey the implications of limited, surrogate,
or synthetic data. The ATR engineer should be able to damp down naïve
proposals centered around the use of an off-the-shelf deep-learning neural
network as a miraculous cure to the alleged ATR affliction.
Chapter 1 formalizes definitions and performance measures associated
with ATR evaluation. All performance measures must be accepted as ballpark
predictions of actual performance in combat. More carefully formulated
experiments will provide more meaningful conclusions. The final measure of
effectiveness takes place in the battlefield.
CHAPTER 2: Hundreds of simple target detection algorithms were tested on
mid- and longwave FLIR images, as well as X-band and Ku-band SAR
images. Each algorithm is briefly described. Indications are given as to which
performed well. Some of these simple algorithms are loosely derived from
standard tests of the difference of two populations. For target detection, these
are typically populations of pixel grayscale values or features derived from
them. The statistical tests are often implemented in the form of sliding triplewindow
filters. Several more-elaborate algorithms are also described with
their relative performances noted. These algorithms utilize neural networks,
deformable templates, and adaptive filtering. Algorithm design issues are
broadened to cover system design issues and concepts of operation.
Since target detection is such a fundamental problem, it is often used as a
test case for developing technology. New technology leads to innovative
approaches for attacking the problem. Eight inventive paradigms, each with
deep philosophical underpinnings, are described in relation to their effect on
target detector design.
CHAPTER 3: Target classification algorithms have generally kept pace with
developments in the academic and commercial sectors since the 1970s.
However, most recently, investment into object classification by Internet
companies and various large-scale projects for understanding the human brain
has far outpaced that of the defense sector. The implications are noteworthy.
There are some unique characteristics of the military classification
problem. Target classification is not solely an algorithm design problem,
but is part of a larger system design task. The design flows down from a ConOps and KPPs. Required classification level is specified by contract.
Inputs are image and/or signal data and time-synchronized metadata. The
operation is often real-time. The implementation minimizes size, weight, and
power (SWaP). The output must be conveyed to a time-strapped operator
who understands the rules of engagement. It is assumed that the adversary is
actively trying to defeat recognition. The target list is often mission dependent,
not necessarily a closed set, and can change on a daily basis. It is highly
desirable to obtain sufficiently comprehensive training and testing data sets,
but costs of doing so are very high, and data on certain target types are scarce
or nonexistent. The training data might not be representative of battlefield
conditions, suggesting the avoidance of designs tuned to a narrow set of
circumstances. A number of traditional and emerging feature extraction and
target classification strategies are reviewed in the context of the military target
classification problem.
CHAPTER 4: The subject being addressed is how an automatic target tracker
(ATT) and an ATR can be fused so tightly and so well that their
distinctiveness becomes lost in the merger. This has historically not been the
case outside of biology and a few academic papers. The biological model of
ATT∪ATR arises from dynamic patterns of activity distributed across many
neural circuits and structures (including those in the retinae). The information
that the brain receives from the eyes is "old news" at the time that it receives
it. The eyes and brain forecast a tracked object’s future position, rather
than relying on the perceived retinal position. Anticipation of the next
moment—building up a consistent perception—is accomplished under
difficult conditions: motion (eyes, head, body, scene background, target)
and processing limitations (neural noise, delays, eye jitter, distractions). Not
only does the human vision system surmount these problems, but it has innate
mechanisms to exploit motion in support of target detection and
classification. Biological vision doesn’t normally operate on snapshots.
Feature extraction, detection, and recognition are spatiotemporal. When
scene understanding is viewed as a spatiotemporal process, target detection,
target recognition, target tracking, event detection, and activity recognition
(AR) do not seem as distinct as they are in current ATT and ATR designs.
They appear as similar mechanisms taking place at varying time scales. A
framework is provided for unifying ATT, ATR, and AR.
CHAPTER 5: Predatory animals detect, stalk, recognize, track, chase, home in
on, and if lucky, catch their prey. Stereo vision is generally their most important
sensor asset. Most predators also have a good sense of hearing. Some predators
can smell their prey from a mile away. Most creatures combine data from
multiple sensors to eat or avoid being eaten. Different creatures use different
combinations of sensors, including sensors that detect vibration, infrared
radiation, various spectral bands, polarization, Doppler, and magnetism. Biomimicry suggests that a combination of diverse sensors works better than
use of a single sensor type. Sensor fusion intelligently combines sensor data
from disparate sources such that the resulting information is in some ways
superior to the data from a single source. Chapter 5 provides techniques for
low-level, mid-level, and high-level information fusion. Other forms of fusion
are also of interest to the ATR engineer. Multifunction fusion combines
functions normally implemented by separate systems into a single system. Zero-shot
learning (ZSL) is a way of recognizing a target without having trained on
examples of the target. ZSL provides a vivid description of a detected target as a
fusion of its semantic attributes. The commercial world is embracing
multisensor fusion for driverless cars. New sensor and processor designs are
emerging with applicability to autonomous military vehicles.
CHAPTER 6: Traditional feedforward neural networks, including multilayer
perceptrons (MLPs) and the newly popular convolutional neural networks
(CNNs), are trained to compute a function that maps an input vector to an
output vector. The N-element output vector can convey estimates of the
probabilities of N target classes. Nearly all current ATRs perform target
classification using feedforward neural networks. These can be shallow or
deep. The ATR detects a candidate target, transforms it to a feature vector,
and then processes the vector unidirectionally, step by step; the number of
steps is proportional to the number of layers in the neural network. Signals
travel one way from input to output. A recurrent neural network (RNN) is an
appealing alternative. Its neurons send feedback signals to each other. These
feedback loops allow RNNs to exhibit dynamic temporal behavior. The
feedback loops also establish a type of internal memory. While feedforward
neural networks are generally trained in a supervised fashion by
backpropagation of output error, RNNs are trained by backpropagation
through time.
Although feedforward neural networks are said to be inspired by the
architecture of the brain, they do not model many abilities of the brain, such as
natural language processing and visual processing of spatiotemporal data.
Feedback is omnipresent in the brain, endowing both short-term and longterm
memory. The human brain is thus an RNN—a network of neurons with
feedback connections. It is a dynamical system. The brain is plastic, adapting
to the current situation. The human vision system not only learns patterns in
sequential data, but even processes still frame (snapshot) data quite well with
its RNN, jerking the eyes in saccades to shift focus over key points on a
snapshot, turning the snapshot into a movie.
An improved type of RNN, called long short-term memory (LSTM), was
developed in the 1990s by Jürgen Schmidhuber and his former Ph.D. student
Sepp Hochreiter. LSTM and its many variants are now the predominant
RNN. LSTM is said to be in use in billions of commercial devices.
Brains don’t come in a box like a desktop computer or supercomputer. All
natural intelligence is embodied and situated. Many military systems, such as
unmanned air vehicles and robot ground vehicles, are embodied and situated.
The body (platform) maneuvers the sensor systems to view the battlespace
from different situations. An ATR based on an RNN, that is embodied and
situated [ES], adaptive and plastic [Pl], and of limited precision (e.g., 16-bit
floating point), will be denoted by the model M=ES-Pl-RNN(ℚ16). A
recurrent ATR is more powerful in many ways than a standard ATR. Both
computationally more powerful and biologically more plausible than other
types of ATRs, an RNN-based ATR understands the notion of events that
unfold over time. Its design can benefit from ongoing advances in
neuroscience.
Professor Schmidhuber has made an additional improvement to his
model. He tightly couples a controller C to a model M. Both can be RNNs
or composite designs incorporating RNNs. Following Schmidhuber’s lead,
we propose a strawman ATR that couples a controller C to our model
M=ES-Pl-RNN(ℚ16) to form a complete system (C ∪ M) that is more
powerful in many ways than a standard ATR. C ∪ M can learn a never-ending
sequence of tasks, operate in unknown environments, realize abstract
planning and reasoning, perform experiments, and retrain itself on-the-fly.
This next-generation ATR is suitable for implementation on two chips: a
single custom low-power chip (<1 W) for effecting M, hosted by a standard
processor serving as the controller C. A heterogeneous chip design,
incorporating high-speed I/O, multicore ARM processors, logic gates,
GPU, codec, and neural section is also appropriate. This next-generation
ATR is applicable to various military systems, including those with extreme
size, weight, and power constraints.
CHAPTER 7: ATRs have been under development since the 1960s. Advances
in computer processing, computer memory, and sensor resolution are easy to
evaluate. However, the time horizon of the truly smart ATR seems to be
receding at a rate of one year per year. One issue is that there has never been a
way to measure the intelligence of an ATR. This is fundamentally different
from measuring detection and classification performance. The description of
what constitutes an ATR, and in particular a smart ATR, keeps changing.
Early ATRs did little more than detect fuzzy bright spots in first-generation
FLIR video or ten-foot-resolution SAR data. Sensors are getting better,
computers are getting faster, and the ATR is expected to take over more of the
workload. With unmanned systems there is no human onboard to digest
information. The ATR is compelled to transmit only the most important
information over a limited-bandwidth data link. The ATR or robotic system
can be viewed as a substitute for a human. What constitutes intelligence in
artificial humans has long been debated, starting with stories of golems, continuing to the Turing test, and including current dire predictions of super-intelligent
robots superseding humans. Chapter 7 provides a Turing-like test
for judging the intelligence of an ATR.
CHAPTER 8: Automation has advanced unceasingly for hundreds of years. The final chapter of this book reflects on the clash of automation and human values. At the forefront of this clash is the Lethal Autonomous Robot (LAR). LARs are defined as mobile, fully autonomous, offensive mechanized platforms that adapt their behavior to meet prescribed goals within a constantly changing environment. LARs are intelligent machines that detect, classify, track and kill their targets without human intervention. ATR is the essential component of the LAR. Unlike existing ATRs, which are generally just aided target recognizers, humans will be out of the immediate kill chain in LARs. The machine will determine what gets destroyed, and who gets killed, according the target list and rules of engagement provided to it. This places a heavy burden on the ATR to distinguish between combatants and noncombatants, military and civilian objects. However, even a smart ATR combined with smart decision-making software is deemed intolerable by many human rights organizations and some nation states. They are demanding that a human be in the loop with final control over an attack. They want to ban fully autonomous LARs altogether (or under the majority of circumstances), as has been done with chemical weapons, blinding lasers, cluster munitions, napalm, biological weapons and conventional anti-personnel mines.
However, the borderline between LARs and weapons controlled by humans is indistinct. If the ATR in a LAR can detect and recognize targets better than the humans in the loop, the humans will inevitably defer to the targeting decisions of the ATR. Then the humans will just be in the loop for ethical cover. But, the humans will lengthen the kill chain, making systems under human control slower and less effective than true LARs. Robotic aircraft, ground and undersea vehicles, and swarms of small craft of all types will be so cheap and so effective, that giving them more autonomy—including to kill—may well prove irresistible to nation states and non-state actors. This will be particularly true when one’s powerful adversaries are relying on them. This is the real crux of the issue. As many countries are now racing to develop LARs, ethical issues will crash into realpolitik in the coming years.
Humans are better suited for leadership and command than robots. Robots are better suited for quick reaction and operation in dangerous situations like enemy fire, minefields, radioactive contamination and chemical attack. Human lives are precious. Robot “lives” not so much. Thus far, in the history of mankind, nothing has stopped automation. Nevertheless, robots will not replace humans in the larger loop of engineering and design, negotiating and treaty making, voting and political decisions, command and control. Robotic overlords subjugating humankind remain the stuff of science fiction and doomsayers.
LARs will be considered a success by some if their decisions to engage or not engage, kill or not kill, are speedier, and in some sense, superior to that of humans. Taking this several steps further, for LARs to be revolutionary war machines, the ATR at the heart of leading-edge LARs will need to be “brainier” than current ATRs in all the ways covered in Chapter 7. They will have to be able to operate alone or as part of human/robot teams. LARs will need to be easily understood and trusted by humans. They will have to analyze and explain their observations and how these observations led to their actions. LARs will need to draw rational conclusions (deduction), make plausible assumptions (abduction), and generalize from observations (induction). To reach this point, a LAR will require sufficient background knowledge, experience, adaptability, discernment and statistical thinking to turn incoming data into actions. All of this will be difficult to achieve. AI, neural networks, and ATR are often marketed as brain-like. However, no one knows enough about the brain to reverse engineer neural functioning. Beyond general human intelligence lies super-intelligence. LARs, let alone super-intelligent LARs, do not yet exist in any meaningful sense. Rudimentary LARs are under development for narrowly defined conditions and missions. But, LARs as smart and as capable, or smarter and more capable, than a well-trained soldier, sailor or pilot, are not imminent.
APPENDIX 1: The first appendix lists the many resources available to the
ATR engineer and includes a brief historical overview of the technologies
involved in ATR development.
APPENDIX 2: A successful project starts with a clear description of the
problem to be solved. However, a well-defined ATR problem is surprisingly
hard to come by. The second appendix provides some questions to pose to a
customer to help get a project going.
APPENDIX 3: The third appendix defines all of the acronyms and abbreviations used in this book.
Acknowledgments
Special thanks to the United States Army Night Vision and Electronic Sensors
Directorate (NVESD), Air Force, Navy, DARPA, and Northrop Grumman
for supporting this work over the years. This book benefited from critique and
suggestions made by the reviewers and SPIE staff.
Author’s Disclaimer
The views and opinions expressed in this book are solely those of the author in
his private capacity and do not represent those of any company, the United
States Federal Government, any entity of the U.S. Federal Government, or
any private organization. Links to organizations are provided solely as a
service to our readers. Links do not constitute an endorsement by any
organization or the Federal Government, and none should be inferred. While
extensive efforts have been made to verify statements and facts presented in
this book, any factual errors or errors of opinion are solely those of the
author. No position or endorsement by the U.S. Federal Government, any
entity of the Federal government, or any other organization regarding the
validity of any statement of fact presented in this book should be inferred.
Author’s Contact Information
Comments on this book are welcome. The author can be contacted at
Bruce.Jay.Schachter@gmail.com.
Bruce J. Schachter
March 2020
