Synopsis
From an engineer who has been 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 is 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. Inexperienced practitioners might 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 confuser objects. This fourth edition, with a new chapter on autonomous lethal weapons and ATR, provides a blueprint for smarter, more autonomous, more sophisticated ATR designs.
"synopsis" may belong to another edition of this title.
