Real-time awareness and rapid target detection are critical for the success of military missions. New technologies
capable of detecting targets concealed in forest areas are needed in order to track and identify possible threats. Currently,
LAser Detection And Ranging (LADAR) systems are capable of detecting obscured targets; however, tracking
capabilities are severely limited. Now, a new LADAR-derived technology is under development to generate 4-D datasets
(3-D video in a point cloud format). As such, there is a new need for algorithms that are able to process data in real time.
We propose an algorithm capable of removing vegetation and other objects that may obfuscate concealed targets in a
real 3-D environment. The algorithm is based on wavelets and can be used as a pre-processing step in a target
recognition algorithm. Applications of the algorithm in a real-time 3-D system could help make pilots aware of high risk
hidden targets such as tanks and weapons, among others. We will be using a 4-D simulated point cloud data to
demonstrate the capabilities of our algorithm.
The field steerable mirror (FSM) Infrared camera system used in Persistent Surveillance Systems provides wide
area coverage using smaller number of cameras. The mirror locations float in a-priori known manner through the
field of view and is supposed to be stitched together using image features. This is because the platform motion
between mirror positions makes it difficult to exploit a-prior knowledge of the mirror positions. The mosaic
generation mechanism developed at ITT Exelis utilizes a calibration step which uses elementary shapes that are
joined continuously to create complex topologies that capture platform movement. This shape topology process
can be extended to other platforms and systems. This paper presents the process by which the meta-data is used
in the calibration step that will ultimately allow for real-time Infrared image mosaic generation. By using the
geographic coordinates, found in the image meta-data, we are able to estimate the amount of overlap between
any two images to be stitched, preventing the need for unnecessary and expensive image feature extraction and
matching. This is achieved by using a polygon clipping approach to determine the vertex coordinates of the
captured images in order to estimate overlap and disconnection in the field of view.
In this paper, an algorithm that extracts regional texture information by computing spectral difference histograms over
window extents in hyperspectral images is presented. The spectral angle distance is used as the spectral metric and
different window sizes are explored for computing the histogram. The histograms are used in a semi-supervised learning
framework that uses both labeled and unlabeled samples for training the support vector machine classifier, which is then
tested with unlabeled samples. Results are presented with real and synthetic hyperspectral images. The method
performs well with high spatial resolution images. The algorithm performs well under different noise levels.