Automatic target recognition
"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 &q...
Gespeichert in:
- 1. Verfasser:
- Format:
- Elektronisch E-Book
- Sprache:
- Englisch
- Veröffentlicht:
-
2020
- Ausgabe:
- Fourth edition
- Zusammenfassung:
-
"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. Naive 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"--
- Umfang:
- 1 online resource (396 pages)
- Anmerkungen:
-
"SPIE Digital Library."--Website. - Mode of access: World Wide Web. - System requirements: Adobe Acrobat Reader
Preface -- 1. Definitions and performance measures: 1.1. What is automatic target recognition (ATR)? 1.2. Basic definitions; 1.3. Detection criteria; 1.4. Performance measures for target detection; 1.5. Classification criteria; 1.6. Experimental design; 1.7. Characterizations of ATR hardware/software; References -- 2. Target detection strategies: 2.1. Introduction; 2.2. Simple detection algorithms; 2.3. More-complex detectors; 2.4. Grand paradigms; 2.5. Traditional SAR and hyperspectral target detectors; 2.6. Conclusions and future direction; References; Appendices -- 3. Target classifier strategies: 3.1. Introduction; 3.2. Main issues to consider in target classification; 3.3. Feature extraction; 3.4. Feature selection; 3.5. Examples of feature types; 3.6. Examples of classifiers; 3.7. Discussion; References -- 4. Unification of automatic target tracking and automatic target recognition: 4.1. Introduction; 4.2. Categories of tracking problems; 4.3. Tracking problems; 4.4. Extension
6. Next-generation ATR: 6.1. Introduction; 6.2. Hardware design; 6.3. Algorithm/software design; 6.4. Potential impact; References -- 7. How smart is your automatic target recognizer? 7.1. Introduction; 7.2. Test for determining the intelligence of an ATR; 7.3. Sentient versus sapient ATR; 7.4. Discussion: where is ATR headed? References -- 8. ATR and lethal autonomous robots: 8.1. Introduction; 8.2. Lethal autonomous robots; 8.3. ATR and LARs: moral, legal, and ethical perspectives; 8.4. LARs and the OODA loop; 8.5. Should LARs be characterized as AI, ATR, machine learning, neural networks, deep learning, or what? 8.6. LARs: evolutionary or revolutionary? 8.7. Can the LAR's ATR achieve human level performance? 8.8. LARs: what can go wrong? 8.9. Discussion; References -- Appendix 1: Resources -- Appendix 2: Questions to pose to the ATR customer -- Appendix 3: Acronyms and abbreviations -- Index - Schriftenreihe:
-
Tutorial texts in optical engineering
- ISBN:
-
9781510631205
9781510631229
9781510631212
9781510631199 - Schlagworte:
- Links: