Automatic Target Recognition (ATR) Technology

Abstract

Automatic Target Recognition (ATR) systems provide the capability to detect, identify, and track high value targets from collected sensor data. ATRs have typically been designed for specific sensors and provide only limited, static mission support due to pre-programmed target lists and operating modes. Extending ATR technology to accommodate sensor upgrades or include new emerging targets has been costly and time-consuming. The objective of the ATR Technology program was to develop technologies that reduce operational limitations while also providing significant performance improvements, dramatically reduced development times, and reduced life-cycle maintenance costs. Breakthroughs in deep learning algorithms and embedded computing systems promised dramatic improvements in ATR utility. The program focused on three core areas: (1) development of on-line adaptive algorithms that enabled performance-driven sensing and ATR utility; (2) algorithm training technology that enabled rapid incorporation of new targets; and (3) technologies that dramatically reduced required data rates, processing times, and the overall hardware and software demands of ATR systems. ATR technology developed under the program transitioned to multiple agencies within the Department of Defense.

Document Details

Document Type
Accomplishment
Publication Date
Oct 01, 2021
Source ID
ad69d5868ffc011e64eb8d6cdb88e469

Tags

Fields of Study

  • Engineering

Readers

  • Distributed Systems and Data Platform Development
  • Military Science and Technology Research and Modernization.
  • Sensor Fusion and Tracking Systems.

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy

Related Documents