This paper reports the successful application of automatic target recognition and identification (ATR/I) algorithms to
simulated 3D imagery of 'difficult' military targets. QinetiQ and Selex S&AS are engaged in a joint programme to build
a new 3D laser imaging sensor for UK MOD. The sensor is a 3D flash system giving an image containing range and
intensity information suitable for targeting operations from fast jet platforms, and is currently being integrated with an
ATR/I suite for demonstration and testing.
The sensor has been extensively modelled and a set of high fidelity simulated imagery has been generated using the
CAMEO-SIM scene generation software tool. These include a variety of different scenarios (varying range, platform
altitude, target orientation and environments), and some 'difficult' targets such as concealed military vehicles. The
ATR/I algorithms have been tested on this image set and their performance compared to 2D passive imagery from the
airborne trials using a Wescam MX-15 infrared sensor and real-time ATR/I suite.
This paper outlines the principles behind the sensor model and the methodology of 3D scene simulation. An overview of
the 3D ATR/I programme and algorithms is presented, and the relative performance of the ATR/I against the simulated
image set is reported. Comparisons are made to the performance of typical 2D sensors, confirming the benefits of 3D
imaging for targeting applications.
Airborne surveillance and targeting sensors are capable of generating large quantities of imagery, making it difficult for the user to find the targets of interest. Automatic target identification (ATI) can assist this process by searching for target-like objects and classifying them, thus reducing workload. ATI algorithms, developed in the laboratory by QinetiQ, have been implemented in real-time on ruggedised processing capable of flight. A series of airborne tests has been carried out to assess the performance of the ATI under real world conditions, using a Wescam EO/IR turret as the source of imagery. The tests included examples of military vehicles in urban and rural scenarios, with varying degrees of hide and concealment. Tests were conducted in different weather conditions to assess the robustness of the sensor and ATI combination. This paper discusses the tests carried out and the performance of the ATI achieved as a function of the test parameters. Conclusions are drawn as to the current state of ATI and its applicability to military requirements.
Future targeting systems, for manned or unmanned combat aircraft, aim to provide increased mission success and platform survivability by successfully detecting and identifying even difficult targets at very long ranges. One of the key enabling technologies for such systems is robust automatic target identification (ATI), operating on high resolution electro-optic sensor imagery. QinetiQ have developed a real time ATI processor which will be demonstrated with infrared imagery from the Wescam MX15 in airborne trials in summer 2005. This paper describes some of the novel ATI algorithms, the challenges overcome to port the ATI from the laboratory onto a real time system and offers an assessment of likely airborne performance based on analysis of synthetic image sequences.
The problem of the automatic detection and identification of military vehicles in hyperspectral imagery has many possible solutions. The availability and utility of library spectra and the ability to atmospherically correct image data has great influence on the choice of approach. This paper concentrates on providing a robust solution in the event that library spectra are unavailable or unreliable due to differing atmospheric conditions between the data and reference. The development of a number of techniques for the detection and identification of unknown objects in a scene has continued apace over the past few years. A number of these techniques have been integrated into a "Full System Model" (FSM) to provide an automatic and robust system drawing upon the advantages of each. The FSM makes use of novel anomaly detectors and spatial processing to extract objects of interest in the scene which are then identified by a pre-trained classifier, typically a multi-class support vector machine. From this point onwards adaptive feedback is used to control the processing of the system. Stages of the processing chain may be augmented by spectral matching and linear unmixing algorithms in an effort to achieve optimum results depending upon the type of data. The Full System Model is described and the boost in performance over each individual stage is demonstrated and discussed.