Learning to Track Aircraft in Infrared Imagery

Airborne target tracking in infrared imagery remains a challenging task. The airborne target usually has a low signal-to-noise ratio and shows different visual patterns. The features adopted in the visual tracking algorithm are usually deep features pre-trained on ImageNet, which are not tightly coupled with the current video domain and therefore might not be optimal for infrared target tracking. To this end, we propose a new approach to learn the domain-specific features, which can be adapted to the current video online without pre-training on a large datasets. Considering that only a few samples of the initial frame can be used for online training, general feature representations are encoded to the network for a better initialization. The feature learning module is flexible and can be integrated into tracking frameworks based on correlation filters to improve the baseline method. Experiments on airborne infrared imagery are conducted to demonstrate the effectiveness of our tracking algorithm.

The Use of the Reassignment Technique in the Time-Frequency Analysis Applied in VHF-Based Passive Forward Scattering Radar

This paper presents the application of the time-frequency (TF) reassignment technique in passive forward scattering radar (FSR) using Digital Video Broadcasting – Terrestrial (DVB-T) transmitters of opportunity operating in the Very High Frequency (VHF) band. The validation of the proposed technique was done using real-life signals collected by the passive radar demonstrator during a measurement campaign. The scenario was chosen to test detection ranges and the capability of estimating the kinematic parameters of a cooperative airborne target in passive FSR geometry. Additionally, in the experiment the possibility of utilizing FSR geometry in foliage penetration conditions taking advantage of the VHF band of a DVB-T illuminator of opportunity was tested. The results presented in this paper show that the concentrated (reassigned) energy distribution of the signal in the TF domain allows a more precise target Doppler rate to be estimated using the Hough transform.

An Application of a Special Method for Designating the Control Forces for the Homing of an Anti-Aircraft Missile on an Aerial Target by Use of a Method of Proportional Navigation

An analysis of application feasibility of a special method for surface-to-air missile (SAM) control during homing on an airborne target was carried out in this paper. A prior implementation of the method was motion control for a gyroscope axis with three degrees of freedom [1, 2] at the stages of spatial seeking and tracking of a detected target. The positive results obtained during that research led to a conclusion that the proposed control method would be appropriate for the determination of the control forces for missile guidance. This method consists of the application of the phase trajectories of control errors. Switching over of the control forces at suitable phase plane points reduced the control errors to zero and facilitated a proper flight path of the SAM. This paper presents a switching algorithm, equations of the kinematics and dynamics of SAM flight, and a number of examples of numerical simulations of the problem contemplated herein. The simulation results were represented in a graphic format.