You are here

Real Time Automated Multi-Sensor Target Classification Algorithm



OBJECTIVE: To develop an algorithm capable of reliable target classification for a wide range of targets, including, but not limited to, Rockets, Artillery and Mortars (RAM); Unmanned Aerial Vehicles (UAVs); and cruise missiles. 

DESCRIPTION: For defensive High Energy Laser (HEL) missions, the engagement timeline can be very short. Thus, it is highly desirable to have a robust target classification system that, at the very least, can provide additional information to the operator. It has been established that reliable classification cannot be accomplished using only state information such as target velocity and acceleration. However, modern HEL systems have multiple imaging sensors, and a laser range finder in addition to radar queueing information. This suite of sensors provides a wealth of information about the target that when combined together, can help with identification and classification of targets. 

PHASE I: The phase I effort will result in analysis and design of the proposed algorithm. The phase I effort should include the development of tools to test and evaluate the efficacy of the algorithm. The phase I effort shall include a final report. 

PHASE II: The phase II effort shall include development and testing of a breadboard system. The designs will then be modified as necessary to produce a final prototype. A complete demonstration system (camera, lens, etc.) will need to be provided by the offeror and larger items such as radars can be utilized for testing as GFE if they are required and available. The final prototype will be demonstrated in a field test against targets of interest to validate performance claims. 

PHASE III: High energy DoD laser weapons offer benefits of graduated lethality, rapid deployment to counter time-sensitive targets, and the ability to deliver significant force either at great distance or to nearby threats with high accuracy for minimal collateral damage. Future laser weapon applications will range from very high power devices used for air defense (to detect, track, and destroy incoming rockets, artillery, and mortars) to modest power devices used for counter-ISR. The Phase III effort would be to design and build a target identification/classification processor that could be integrated into the Army’s High Energy Laser Mobile Tactical Truck (HELMTT) vehicle. Military funding for this Phase III effort would be executed by the US Army Space and Missile Defense Technical Center as part of its Directed Energy research. 


1: B. Khaleghi, A. Khamis, F.O. Karray, and S.N. Razavi, "Multisensor data fusion: A review of the state-of-the-art," in Information Fusion, Vol. 14, Issue 4, pp. 28-44, 2013

2:  E. Blasch and B. Kahler, "Multiresolution EO/IR Target Tracking and Identification," in 7th International Conference on Information Fusion, pp. 275-282, 2005

3:  J.F. Khan, M.S. Alam, and S.M.A. Bhuiyan, "Automatic target detection in forward-looking infrared imagery via probabilistic neural networks," in Applied Optics, Vol. 48, Issue 3, pp. 464-476, 2009

4:  S.P. Yoon, T.L. Song, and T.H. Kim, "Automatic Target Recognition and Tracking in Forward-Looking Infrared Image Sequences with a Complex Background," in International Journal of Control, Automation, and Systems, Vol. 11, Issue 1, pp. 21-32, 2013

5:  H. Zhang, N.M. Nasrabadi, Y. Zhang, and T.S. Huang, "Multi-View Automatic Target Recognition using Joint Sparse Representation," in IEEE Transactions on Aerospace and Electronic Systems, Vol. 48, No. 3, pp. 2481-2497, 2012

6:  L.M. Novak, M.B. Sechtin, and M.J. Cardullo, "Studies of target detection algorithms that use polarimetric radar data," in IEEE Transactions on Aerospace and Electronic Systems, Vol. 25, Issue 2, pp. 150-165, 1989


Dr. Brett Hokr 

(256) 270-5668 

Amanda Black 

(256) 955-5543 

US Flag An Official Website of the United States Government