The presented work is an extension of previous work carried out at A.U.G. Signals Ltd. The problem is approached herein for vessel identification/verification using Deep Learning Neural Networks in a persistent surveillance scenario. Using images with vessels in the scene, Deep Learning Neural Networks were set up to detect vessels from still imagery (visible wavelength). Different neural network designs were implemented for vessel detection and compared based on learning performance (speed and demanded training sets) and estimation accuracy. Unique features from these designs were taken to create an optimized solution. This paper presents a comparison of the deep learning approaches implemented and their relative capabilities in vessel verification.
The objective of this paper is to develop novel classification structures for military targets detection and recognition by
employing different fusion techniques. In real applications, the great diversity of materials in the background areas and
the similarity between the background and target signatures result in high false alarm rates and large miss classification
errors. In this paper, three new systems are proposed using different fusion techniques: pixel level fusion, decision
fusion, and classification fusion employing confidence vectors. These new developed systems are tested using an
experimental data to show its effectiveness.
The probability distribution function (pdf) used to model Synthetic Aperture Radar (SAR) clutter is an important design element in Constant False Alarm Rate (CFAR) detection; the mean of the local CFAR window is taken as the first moment of the pdf. This study presents research examining the relationship between clutter statistics and radar resolution cell size in the Convair-580 (CV-580) C-SAR and RADARSAT-2 systems. The experiment consisted of decreasing the resolution of a HV polarized, high-resolution, CV-580 sea SAR image and determining the best fit pdf for the corresponding clutter. The same methodology was used on standard- and fine-beam-mode RADARSAT-2 HV images. It was found that the GΓ pdf could be fitted very well to the experimental data for all CV-580 and RADARSAT-2 resolutions. Furthermore, the highest resolution SAR data was Weibull distributed, and decidedly non-Gaussian, in all cases. The medium resolution CV-580 image was very closely modelled by the Lognormal distribution while the Rayleigh distribution (Gaussian statistics) proved highly suitable for modelling the lowest resolution SAR data. The test results presented in this paper may be useful to SAR researchers.