You are here

Advanced UAV and Mortar Target Detection and Tracking Algorithms for Low Signal-to-Noise Ratio and Cluttered Environments

Description:

TECHNOLOGY AREA(S): Electronics 

OBJECTIVE: To develop advanced image processing algorithms for the detection and tracking of small Unmanned Aerial Vehicles (UAVs) and Mortars in low Signal-to-Noise Ratio (SNR) and cluttered environments. 

DESCRIPTION: Many military weapon systems rely on passive thermal infrared sensors (MWIR/LWIR) for target detection and tracking. In many cases, the maximum detection range of these sensors are limited by the ability of the image processing algorithms to detect and extract a target of interest. Dim targets such as small Unmanned Aerial Vehicles (UAVs) and mortars are extremely difficult to detect and track due to the low contrast in the thermal imagery, or low signal-to-noise ratio (SNR). High clutter environments such as cloud or tree backgrounds also increase the difficulty in target detection and tracking. The challenge is to develop advanced image processing algorithms that can increase the maximum detection and tracking range against UAVs and mortars. The specific challenges to be addressed include: Target Detection/Tracking at SNRs less than 3dB Target Detection/Tracking in Cloud and Tree Backgrounds Unresolved Target Detection/Tracking (target size less than 1 pixel) Targets to be used in the analysis include the DJI Phantom and a 60mm mortar. The proposed algorithms must be able to process imagery in near real-time to be applied to military applications (Threshold: 300Hz bandwidth, Objective: 1kHz bandwidth). The algorithms must be written so that multiple targets (Threshold: 1 target, Objective: 10 targets) can be detected and tracked at a time. If successful, advanced algorithms for target detection and tracking will benefit many military applications. The specific platform of interest for this topic is a ground-based High Energy Laser (HEL) weapon system. Typical HEL acquisition sensors employ a passive MWIR camera with a wide-field of view (3 degrees). The objective camera and lens for this topic is not specified. The offeror must include a demonstration system (camera, lens, etc.) for algorithm performance demonstration during Phase II. The proposed algorithm must address at least one or more of the three challenges of interest. 

PHASE I: The phase I effort will result in analysis and design of the proposed algorithm. The phase I effort shall include a final report with modeling and simulation results supporting performance claims. The method for determining SNR will be documented. 

PHASE II: The Phase I designs will be utilized to fabricate, test and evaluate a breadboard system. The designs will then be modified as necessary to produce a final prototype. The final prototype will be demonstrated to highlight the increased detection and tracking capabilities in challenging environments. A complete demonstration system (camera, lens, etc.) must also be provided by the offeror. Phase II will include field testing against a target of interest (ex: small UAV) to validate performance claims. 

PHASE III: Civil, commercial and military applications include short-range counter-RAM and UAV target tracking, remote sensing, and small-satellite tracking. 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 detection/tracking processor that could be integrated into the Armys High Energy Laser Mobile Tactical Truck (HEL-MTT) 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. 

REFERENCES: 

1: C. Gao, D. Meng, Y. Yang, Y. Wang Infrared Patch-Image Model for Small Target Detection in a Single Image, IEEE Trans. On Image Processing, Vol. 22, Issue 12, Sep 2013, Pages 4996-5009

2: K. Wang, Y. Liu, X. Sun Small Moving Infrared Target Detection Algorithm under Low SNR Background, Information Assurance and Security, 2009, IAS 09, Vol 2, Aug 2009

3: S. Kim Min-local-LoG filter for detecting small targets in cluttered background, Electronics Letters, Vol 47, Issue 2, Pages 105-106 (2011)

4: X. Luo, X. Wu A Novel Fusion Detection Algorithm for Infrared Small Targets, Intelligent Information Technology Application, 2009. IITA 2009, Vol 3 (2009)

 

KEYWORDS: Infrared Search And Track, IRST, Unmanned Aerial Vehicle, Mortar, Detection, Signal-to-noise Ratio, Signal-to-clutter Ratio, Cloud Background, Unresolved Target, Image Processing, Algorithm 

US Flag An Official Website of the United States Government