Cognitive radar systems adapt processing, receiver and transmitted waveform parameters by continuously learning and interacting with the operative environment. IRST systems are passive; as such no RF emission is involved. Nevertheless, the cognitive paradigm can be applied to passive sensors in order to optimize operational modes choice, platform and processing parameters on the fly. A cognitive based IRST, while enhancing the overall performance of the system, would also reduce the crew workload during the mission. In this paper, steps and challenge toward cognitive IRST are described, along with a proof-of-concept example of improved tracking capabilities using reinforcement learning methods.
Passive ranging is the process of estimating the distance between an observer (own-ship) and one or more objects (targets) by using passive sensors and angle measurements only, without electromagnetic or acoustic emissions. It is the baseline technique to complete the three dimensional tracking capability of IRST systems, able to automatically search, detect and track targets with generally higher angular resolution than Radars in completely silent mode. As well-known from literature, range is univocally linked to angle only data, when specific relative dynamics occur. In other cases, when such univocal relation does not hold, range estimation is still considered an open research topic. In this paper we select a set of informative cases, derived from our experience in analyzing real sorties data and compare four popular algorithms on the basis of a set of new metrics that, in our opinion, captures the system performance in terms of usability and reliability. Ranging algorithms performance is usually evaluated by means of distance-based metrics (as RMSE) which focus on accuracy of the estimation. Usability and reliability are taken into account here by introducing what we call the Average Range Declaration Length (ARDL) and the Truth-Representative Score (TRS).
Infrared Search and Track systems are an essential element of the modern and future combat aircrafts. Passive automatic
search, detection and tracking functions, are key points for silent operations or jammed tactical scenarios.
SKYWARD represents the latest evolution of IRST technology in which high quality electro-optical components,
advanced algorithms, efficient hardware and software solutions are harmonically integrated to provide high-end
affordable performances. Additionally, the reduction of critical opto-mechanical elements optimises weight and volume
and increases the overall reliability.
Multiple operative modes dedicated to different situations are available; many options can be selected among multiple or
single target tracking, for surveillance or engagement, and imaging, for landing or navigation aid, assuring the maximum
system flexibility.
The high quality 2D-IR sensor is exploited by multiple parallel processing chains, based on linear and non-linear
techniques, to extract the possible targets from background, in different conditions, with false alarm rate control.
A widely tested track processor manages a large amount of candidate targets simultaneously and allows discriminating
real targets from noise whilst operating with low target to background contrasts.
The capability of providing reliable passive range estimation is an additional qualifying element of the system.
Particular care has been dedicated to the detector non-uniformities, a possible limiting factor for distant targets detection,
as well as to the design of the electro-optics for a harsh airborne environment.
The system can be configured for LWIR or MWIR waveband according to the customer operational requirements. An
embedded data recorder saves all the necessary images and data for mission debriefing, particularly useful during inflight
system integration and tuning.
Template-matching techniques for automatic detection of multiple, extended, and low contrast targets in infrared maritime scenarios are described and analyzed. In particular, we focus our attention on the specific area of the sea around the horizon, where common techniques of clutter removal, based on target contrast only, fail. Targets of interest are ships along the horizon line in adverse atmosphere conditions, with dim contrast with respect to the background. A database of ship images is used for the analysis. We conclude that the normalized cross-correlation (NCC) technique is a reasonable choice for this application due to its capability to provide an estimate of the similarity between images, even if they present different energy levels and are corrupted by noise. It also is more tolerant to the geometric distortions. After a description of the test setup, simulation results are presented to show the performances of the proposed technique; examples using both synthetic and real images are considered.
KEYWORDS: Personal digital assistants, Target detection, Sensors, Motion models, Infrared search and track, Detection and tracking algorithms, Infrared radiation, Data fusion, Infrared imaging, Long wavelength infrared
This paper describes an application of the IMM (Interacting Multiple Model) technique in a multiple target tracking system for an IRST (Infrared Search and Track) system operating in the mid and in the long wave infrared bands. The use of the two IR bands allows better performances in terms of detection probability, lower false tracks and short time for track initiation. To properly merge data from the two sensors, an enhancement of the PDA (Probabilistic Data Association) technique is introduced in the process. The approach has shown to properly operate with a very high number of possible targets in the two IR bands. Good results have been obtained also in the case of clustered detections, as well as in uniformly space distributed detections.
Test results of Automatic Target Recognition of IR images are described. They are mainly based on Template Matching Techniques and Synthetic Discriminant Functions (SDF) filters are adopted to increase the robustness of the method and to reduce computational load. Extensive tests are performed with a number of different scenarios and image noise levels. Dedicated refinements and operative adjustements to traditional approaches are implemented and described. The work has been originated with digitally generated target databases and proceeds with real IR images.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.