3.4 Automatic Target Recognition (ATR)

3.4.1 Warfighting Needs

ATR addresses the Joint Warfighter Operational Needs S&T areas as follows: (1) Dominant Battlefield Awareness - ATR gives real-time identification of adversary from high bandwidth sensors providing both sufficient knowledge to neutralize and, also, enormous data compression for transmission on battlefield data links; (2) Precision Force - ATR's real-time ID of forces over wide area compresses C4I timeline for responsive "sensor to shooter" operations and enables timely reacquisition of target for strike platform; (3) Combat Identification - ATR gives beyond visual range ID to launch missiles at long range enabling lethal enemy engagement, reduced fratricide and ownship survival; (4) Joint Theater Missile Defense - ATR enables finding ground-based missile launchers in a timely manner consistent with clusive adversary operations, discriminating RV's from decoys during reentry, and to discriminate cruise missiles from slow moving, low flying confusers; (5) Military Operations in Urban Terrain - ATR enables finding targets in cluttered urban environment to precisely ID targets allowing precision weapon employment resulting in minimal collateral damage; (6) Joint Readiness - ATR synthetic scene generation and modeling provides capabilities for enhanced simulation and training; (7) Joint Countermine - ATR technology enables rapid detection of mines; (8) Counterproliferation - ATR aids in timely bomb damage assessment. ATR is needed for both ISR and Weapon Delivery systems. Transitions planned for Joint STARS, P3, S3, U2R, Tier 2. Tier 2+, Tier3-, F14, F15, F16, F18, F22, Apache, Comanche, AWACS, Abrams, Bradley, MSX, THAAD Destroyer, CG-47, DDG-51, DDG-993, and DD-963.

3.4.2 ATR Overview

3.4.2.1 Goals and Timeframes. The ATR program goals are grouped into two categories-those organized by target class (land, sea, air), driven by the need to improve ATR performance and those that are general ATR goals driven by the need to reduce both acquisition and life cycle costs.

Technological advances in this subarea are critical to attainment of identification goals in Radar technology (3.1) and Electro-Optic Technology (3.2).

3.4.2.2 Major Technical Challenges. The major technical challenge is the development of robust algorithms (single and multi-sensor) to contend with the target signature variations due to target configuration (e.g., stores, articulation, manufacturing, wear/tear), target/sensor acquisition parameters (e.g., aspect, depression, squint angles), target phenomenology (e.g., cavity responses, glints, IR thermal behavior), and target/clutter interaction (e.g., foliage masking, camouflage). These algorithms must also maintain low false alarm rates and operate in real time. Other significant challenges include rapid target insertion/on-the-fly training to support flexible and sustained employment of ATR and the development of open architecture ATR’s to provide expandable hardware and software insertion for affordable capability growth.

3.4.2.3 Related Federal and Private Sector Efforts. Image processing technologies are developed in medical imaging, law enforcement, automated manufacturing, transportation sensing, remote sensing, environmental sensing, robotics, and multi-media. Commercial computer technologies are leveraged as well.

3.4.3 S&T Investment Strategy

In addition to DTAP planning process and TARA reviews, the ATR community (government, industry, & university) meets 3 times a year at the ATR Working Group (ATRWG) meetings to promote industry involvement in planning and MOU coordination process.

3.4.3.1 Technology Demonstrations. Technology Demonstrations in this subarea contribute to several EO and Radar application DTOs which are demonstrating combined advances in sensor and ATR technology.

3.4.3.1.1 ATR Dominant Target ID. DTO SE.17.02.ANFEC. Demonstrations include both passive and active detection, tracking cueing and identification of targets in the battlespace. The following programs perform intelligent data compression and/or recognition of stationary ground vehicular targets from recce type platforms such as U2R or Tier 3-: SAIP, Clipping Service, STARLOS, and RADIUS. Efforts recognizing ground or air moving targets include Moving Target Recognition for Recce, Surveillance, and Attack; Air Target Algorithm Development; Non-cooperative Air Target Recognition; and Multi-sensor Fusion for Airborne Surveillance, and Moving Target Exploitation. Important transition targets include JointSTARS, P3, and S3 for ground and surface targets; and F14, F15, F16, F18, F22, and AWACS for airborne targets. Key developments performing multi-sensor recognition include Unmanned Ground Vehicle/Reconnaissance, Surveillance, and Target Acquisition Demonstrations, Hunter Sensor Suite (in RFPI ACTD), and Target Acquisition ATD (reported in EO subarea). Other activities include reentry vehicle discrimination from decoy's using EO and Radar sensors and Automatic Radar Periscope Detections and Discrimination using high range resolution radar.

3.4.3.2 Technology Development. Technology being developed in this subarea includes:

Development of both template and model based algorithms using single and multiple radar and EO sensors, attacking both ground and air targets.

Leveraging of commercially developed multi-chip modules to design and demonstrate a family of affordable, miniaturized, high density, high performance image and digital signal processors for advance weapons applications. ATR evaluation and databases are the backbone of ATR development as it is largely an experimental science, joint development of standard metrics, evaluation procedures, and databases and sharing under ATRWG pursued. Signature modeling and scene synthesis, critical to rapid target insertion capability and cost effective complement to training and evaluation field data is conducted.

Algorithm tools are developed, focused on a common environment to reduce ATR development and evaluation cost and improve algorithm performance via shared and distributed algorithm design, software reuse, and de-coupling of software development from real time HPC architectures.

3.4.3.3 Basic Research. As outlined in the Basic Research TAP, ATR is a key focus for the 6.1 community. Important research themes include multi-resolution processing, fusion, advanced and non-linear signal processing, computational electromagnetics, algebraic invariance, artificial intelligence and knowledge based systems, advanced imaging techniques and inverse problems, and distributed/parallel computing. Recent key initiatives include the Reduced Signature Target Recognition effort which is focused on advanced algorithm and computational electromagnetic research and the Signal Processing and AI Program.