Automatic Target Recognition

This book examines the roles of sensors, physics–based attributes, classification methods, and performance evaluation in automatic target recognition. It details target classification from small mine–like objects to large tactical vehicles. Also explored in the book are invariants of sensor and transmission transformations, which are crucial in the development of low latency and computationally manageable automatic target recognition systems.

Radar Automatic Target Recognition (ATR) and NonCooperative Target Recognition (NCTR) captures material presented by leading international experts at a NATO lecture series and explores both the fundamentals of classification techniques applied to data from a variety of radar modes and selected advanced techniques at the forefront of research. The ability to detect and locate targets by day or night, over wide areas, regardless of weather conditions has long made radar a key sensor in many military and civil applications. However, the ability to automatically and reliably distinguish different targets represents a difficult challenge, although steady progress has been made over the past couple of decades. This book explores both the fundamentals of classification techniques applied to data from a variety of radar modes and selected advanced techniques at the forefront of research. Topics include: the problem as applied to the ground, air and maritime domains; impact of image quality on the overall target recognition performance; performance of different approaches to the classifier algorithm; improvement in performance to be gained when a target can be viewed from more than one perspective; ways in which natural systems perform target recognition; impact of compressive sensing; advances in change detection, including coherent change detection; and challenges and directions for future research.

This authoritative resource presents a comprehensive illustration of modern Artificial Intelligence / Machine Learning (AI/ML) technology for radio frequency (RF) data exploitation. It identifies technical challenges, benefits, and directions of deep learning (DL) based object classification using radar data, including synthetic aperture radar (SAR) and high range resolution (HRR) radar. The performance of AI/ML algorithms is provided from an overview of machine learning (ML) theory that includes history, background primer, and examples. Radar data issues of collection, application, and examples for SAR/HRR data and communication signals analysis are discussed. In addition, this book presents practical considerations of deploying such techniques, including performance evaluation, energy-efficient computing, and the future unresolved issues.

"This third edition of Automatic Target Recognition provides a roadmap for breakthrough ATR designs with increased intelligence, performance, and autonomy. Clear distinctions are made between military problems and comparable commercial Deep Learning problems. These considerations need to be understood by ATR engineers working in the defense industry as well as by their government customers. A reference design is provided for a next-generation ATR that can continuously learn from and adapt to its environment. The convergence of diverse forms of data on a single platform supports new capabilities and improved performance. This third edition broadens the notion of ATR to multisensor fusion. Radical continuous-learning ATR architectures, better integration of data sources, well-packaged sensors, and low-power teraflop chips will enable transformative military designs"--

"From an engineer designing Automatic Target Recognition (ATR) systems for 40 years, comes this step-by-step guide to producing state-of-the-art ATR systems. The full spectrum of ATR designs are covered, from systems that just suggest targets to the warfighter to ATRs that could serve as the "brains" of lethal autonomous robots. Unfortunately, when it comes to ATR, some practitioners claim that their off-the-shelf canned algorithms magically leap from academic research to deployment with scant domain knowledge or system engineering. Deep learning is marketed more than deep understanding, deep explainability or deep fusion of on-platform resources. Naïve practitioners twist a few algorithmic knobs, and test on data of uncertain virtue, until performance seems superb. Unfortunately, with the enemy and ever changing environment conspiring to defeat detection and recognition, naively designed ATRs can fail in unexpected and spectacular ways. Trustworthy ATRs need to fuse multiple data and metadata sources, continuously learn from and adapt to their environment, interact with humans in natural language, and deal with in-library and out-of-library targets and confusor objects. This book provides a blueprint for smarter, more autonomous, more sophisticated ATR designs"--

This three-volume set LNCS 10666, 10667, and 10668 constitutes the refereed conference proceedings of the 9th International Conference on Image and Graphics, ICIG 2017, held in Shanghai, China, in September 2017. The 172 full papers were selected from 370 submissions and focus on advances of theory, techniques and algorithms as well as innovative technologies of image, video and graphics processing and fostering innovation, entrepreneurship, and networking.

The two-volume set of LNCS 11941 and 11942 constitutes the refereed proceedings of the 8th International Conference on Pattern Recognition and Machine Intelligence, PReMI 2019, held in Tezpur, India, in December 2019. The 131 revised full papers presented were carefully reviewed and selected from 341 submissions. They are organized in topical sections named: Pattern Recognition; Machine Learning; Deep Learning; Soft and Evolutionary Computing; Image Processing; Medical Image Processing; Bioinformatics and Biomedical Signal Processing; Information Retrieval; Remote Sensing; Signal and Video Processing; and Smart and Intelligent Sensors.