# Automated Target Recognition **Entity class:** Machine-perception capability **Aliases:** ATR ## Definition **Automated target recognition** uses algorithms to detect, classify, identify, or prioritize objects and signatures in sensor data. Operational systems may use imagery, radar, acoustic, infrared, radio-frequency, or fused sensor inputs, with performance depending on environment, training data, model calibration, and latency. ## Relationships - **input architecture:** [[wiki/Multi-Sensor Fusion|Multi-Sensor Fusion]]. - **operational loop:** [[wiki/Sensor-to-Shooter Loop|Sensor-to-Shooter Loop]]. - **experiment:** [[wiki/Experimental Demonstration Gateway Event|Experimental Demonstration Gateway Event]]. - **collection:** [[collections/Terrorism, Counterterrorism, and the Intelligence Environment|Terrorism, Counterterrorism, and the Intelligence Environment]]. ## Sources / Provenance - [U.S. Army — EDGE 24](https://www.army.mil/article/279754/army_examines_aviation_technologies_at_edge_24) ## Simple Reminders, Quotations, and Thoughts > "Hostile Fire Indicating System (HFIS): Develop a low power multi-spectral sensor suitable for detecting, classifying, and geo-locating various forms of incoming hostile fire to SOF aircraft." > **— USSOCOM**, *accessed September 23, 2026, USSOCOM Capability Areas of Interest* [[reminders/Surveillance/Hostile-Fire Sensors Should Detect Classify and Geolocate by USSOCOM|Hostile-Fire Sensors Should Detect Classify and Geolocate by USSOCOM]] > "3D Modeling: Fuse Full Motion Video (FMV) from multiple sources to improve 3D modeling resolution of fine structures including thin wall and vertical obstructions such as poles and antennas." > **— USSOCOM**, *accessed September 23, 2026, USSOCOM Capability Areas of Interest* [[reminders/Surveillance/Full-Motion Video Can Improve 3D Models of Fine Structures by USSOCOM|Full-Motion Video Can Improve 3D Models of Fine Structures by USSOCOM]] > "ISR - Tactical RF Signal Classification: Small devices capable of scanning RF spectrum and reporting classifications of signals found, along with signal related information." > **— USSOCOM**, *accessed September 23, 2026, USSOCOM Capability Areas of Interest* [[reminders/Surveillance/Small Devices Can Classify Tactical Radio-Frequency Signals by USSOCOM|Small Devices Can Classify Tactical Radio-Frequency Signals by USSOCOM]] > "We embrace the speed and scale AI brings to our tradecraft – and so do our warfighters and readership." > **— Frank Whitworth**, *May 19, 2025, 2025 GEOINT Symposium Keynote* [[reminders/Information/Intelligence Tradecraft Should Embrace AI Speed and Scale by Frank Whitworth|Intelligence Tradecraft Should Embrace AI Speed and Scale by Frank Whitworth]] > "NGA Maven has decreased targeting workflow timelines by a substantial amount, with one warfighting element’s targeting cell seeing intelligence-operations timelines drop from hours to minutes from sensing to target engagement during a recent exercise." > **— Frank Whitworth**, *May 19, 2025, 2025 GEOINT Symposium Keynote* [[reminders/Information/Maven Can Cut Targeting Timelines From Hours to Minutes by Frank Whitworth|Maven Can Cut Targeting Timelines From Hours to Minutes by Frank Whitworth]] > "And to add to that, the latency of our models – our time lags in running inference specifically – has improved 80-percent in the year since NGA Maven became a program of record." > **— Frank Whitworth**, *May 19, 2025, 2025 GEOINT Symposium Keynote* [[reminders/Information/Model Inference Latency Improved Eighty Percent by Frank Whitworth|Model Inference Latency Improved Eighty Percent by Frank Whitworth]] > "At NGA, we’re leveraging AI to help sift through the millions of detects we get a day and are also starting to train the best industry models on the corpus of NGA reporting." > **— Frank Whitworth**, *May 19, 2025, 2025 GEOINT Symposium Keynote* [[reminders/Information/AI Can Sift Millions of Detections a Day by Frank Whitworth|AI Can Sift Millions of Detections a Day by Frank Whitworth]] > "Then the A2SoN auto-processes text and imagery sources to accurately identify features and events – which has led to 90 percent shorter data prep times." > **— Frank Whitworth**, *May 19, 2025, 2025 GEOINT Symposium Keynote* [[reminders/Information/Automated Text and Imagery Processing Cut Data Preparation by Ninety Percent by Frank Whitworth|Automated Text and Imagery Processing Cut Data Preparation by Ninety Percent by Frank Whitworth]] > "To manage the significant growth in the volume of GEOINT data and data sources available, NGA is making significant investments in automation to speed workflows, as well as AI/ML to fuse data to enable sense-making. We are leveraging computer vision to rapidly exploit data; using advanced modeling techniques to understand, correlate, and predict activity; and integrating automated modeling capabilities to prompt dynamic collection." > **— Frank Whitworth**, *May 14, 2025, 2025 HASC Testimony on National Security Space Programs* [[reminders/Information/Automation AI and Machine Learning Can Fuse Data for Sense-Making by Frank Whitworth|Automation AI and Machine Learning Can Fuse Data for Sense-Making by Frank Whitworth]] > "Today, NGA is incorporating GEOINT AI into warfighting headquarters around the world, accelerating their operations and enabling lethality through programs like NGA Maven." > **— Frank Whitworth**, *May 14, 2025, 2025 HASC Testimony on National Security Space Programs* [[reminders/Information/GEOINT AI Is Accelerating Operations and Enabling Lethality by Frank Whitworth|GEOINT AI Is Accelerating Operations and Enabling Lethality by Frank Whitworth]]