Igor V. Ternovskiy

Mapping-singularities-based motion estimation

Existing methods of image-based motion measurement (except point source cases) idealize borders (edges) of objects. Small changes in movement, direction, or projection can introduce errors into movement measurement. We propose a method that applies differential mapping singularities theory (catastrophe theory) in the context of 3-D object projection into a 2-D image plane, and takes advantage of the fact that the edges of an object can be interpreted in mapping singularities (catastrophes). Several theorems show that mapping of an arbitrary smooth surface can create only 14 singularities. Small changes in object position do not change the type of singularity, but simply shift its critical point. A trajectory of moving critical points, extracted from edge and edge vicinity pixels, can be divide into areas that correspond to different singularity types (a so-called phase diagram). Based on a phase diagram, it is possible to select a corresponding singularity relationship graph (SRG). Knowledge of a SRG allows correct prediction of changes during object movement. This approach provides a significant reduction in calculations for motion prediction and permits correction of predicted motion in all sets of predicted frames. In addition, SRG knowledge allows object tracking, even with sudden changes of direction and use of camouflage.

Self-structuring data learning approach

In this paper, we propose a hierarchical self-structuring learning algorithm based around the general principles of the Stanovich/Evans framework and “Quest” group definition of unexpected query. One of the main goals of our algorithm is for it to be capable of patterns learning and extrapolating more complex patterns from less complex ones. This pattern learning, influenced by goals, either learned or predetermined, should be able to detect and reconcile anomalous behaviors. One example of a proposed application of this algorithm would be traffic analysis. We choose this example, because it is conceptually easy to follow. Despite the fact that we are unlikely to develop superior traffic tracking techniques using our algorithm, a traffic based scenario remains a good starting point if only do to the easy availability of data and the number of other known techniques. In any case, in this scenario, the algorithm would observe and track all vehicular traffic in a particular area. After some initial time passes, it would begin detecting and learning the traffic’s patters. Eventually the patterns would stabilize. At that point, “new” patterns could be considered anomalies, flagged, and handled accordingly. This is only one, particular application of our proposed algorithm. Ideally, we want to make it as general as possible, such that it can be applies to numerous different problems with varying types of sensory input and data types, such as IR, RF, visual, census data, meta data, etc.

Improved near-earth object detection using dynamic logic

Current efforts aimed at detecting and identifying Near Earth Objects (NEOs) that pose potential risks to Earth use moderately sized telescopes combined with image processing algorithms to detect the motion of these objects. The search strategies of such systems involve multiple revisits at given intervals between observations to the same area of the sky so that objects that appear to move between the observations can be identified against the static star field. Dynamic Logic algorithm, derived from Modeling Field Theory, has made significant improvements in detection, tracking, and fusion of ground radar images. As an extension to this, the research in this paper will examine Dynamic Logics ability to detect NEOs with minimal human-in-the-loop intervention. Although the research in this paper uses asteroids for the automation detection, the ultimate extension to this study is for detecting orbital debris. Many asteroid orbits are well defined, so they will serve as excellent test cases for our new algorithm application.

Front Matter: Volume 8408

This PDF file contains the front matter associated with SPIE Proceedings Volume 8408, including the Title Page, Copyright information, Table of Contents, and the Conference Committee listing.© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.This PDF file contains the front matter associated with SPIE Proceedings Volume 8408, including the Title Page, Copyright information, Table of Contents, and the Conference Committee listing.

Real-time ATR for unattended visual sensor wireless networks

A new approach to Automatic Target Recognition and unmanned navigation based on sensor fusion, theory of catastrophes, and real-time processing is described.

Soft computing and soft communications for synchronized data

In this paper a new algorithmic and hardware approach to real-time processing, computing, compression and transmission of multi-media (video, imagery, audio, sensor, telemetry, computer data) information, in the form of synchronized data, was proposed. The proposed approach, called Soft Computing and Soft Communication, leads to multi-media throughput minimization and data homogenization.

Similarity measures for target tracking with aerial images

A Self-structuring Data Learning Algorithm was introduced and has been implemented in our prior work. While the algorithm and the software package are advancing, it has been tested with both synthetic data and real-world data. After encouraging synthetic data test results, real-world data testing also shows promising outcomes while posing some challenges such as object occlusion, objects merging, and going into and emerging from under bridge. To resolve such problems, a multi-int solution is proposed. One of the key features in this solution is similarity measure. There are different types of similarity measures. In this paper, we primarily focus on aerial images similarity measure. The images we worked on presents unique challenge in similarity measure because of small object in distance and large area image, which consequently provides limited information. To deal with this difficulty, we have developed 14 different similarity metrics by employing Normalized Cross Correlation method, Sum of Squared Differences, and overlapping and colors of pixels. We used object tracking ability to evaluate the metrics. The simulation results show each metric has some advantages and disadvantages. In attempt to improve tracking capability, we imposed some metrics thresholds in addition to the image similarity metrics. Such metrics thresholds were learned from labeled data with valuation of tracking correctness. To further enhance tracking ability, speed similarity was incorporated on top of two features mentioned above. More improvement can be done by studying robustness of images similarity metrics and using tracks fusion.

Fusion of cyber sensors on a network for improved detection and classification

This paper investigates the fusion process of combining cyber sensors on a network to detect and classify cyber behaviors – good and bad. Some bad cyber activity can be confused as appropriate (good) activity and vice versa. To wrongly block good activity is an error. Also, to allow bad cyber activity to continue believing it to be good activity is also an error. We wish to minimize these errors. Some bad cyber activity can be classified according to its severity. Confusing an extremely severe cyber activity for a mildly bad cyber activity can be a costly mistake also. We assume there are several classification systems present on the network, that is, a sensor, processor and exploiter at a minimum for each system. Also, the sensors may be disparate. Assume each system has a ROC manifold that is known, or has a good approximation. The goal of this paper is to demonstrate that there a best combining rule.

Applying self-structured data learning algorithm to aerial infrared and visual images

Previously, we proposed and implemented a Self-structuring Data Learning Algorithm. This realized software package and the concept are still progressing. Earlier, it was tested with synthetic data and exhibited interesting results. The objectives of this paper are testing the algorithm with raw infrared and visual images and updating the algorithm as required. We first performed registration transformation and detection from the images with an existing software package. We then registered the detections with the registration transformations from both infrared and visual images. The registered detections were delivered to the algorithm for target detection and tracking without modification. Results revealed inability to handle very noisy infrared image features. To overcome this problem, we developed multiscale grid processing to improve detection classification in the algorithm. This updated algorithm shows much better target detection and tracking with the real-world data. More algorithm enhancements are in work such as incorporating pattern recognition, classification, and fusion.

Multi-spectral (optical/IR and RF) characterization of omnidirectional reflective dielectric thin film for sensor applications

Material characterization is important for the design and development of multi-spectral sensors. In this paper, we present the measurement and analysis of the optical properties of commercial multilayered dielectric films with high reflectivity in the visible (VIS) and near infrared (NIR) regimes. Using a UV/VIS/NIR spectrometer, we measured the reflectance and transmittance spectra of single, two-, and three-sheets of films at different incidence angles. Our results show that both reflectance and transmittance vary with incidence angles as well as the number of combined sheets of the films. For the NIR film, reflectance decreases from 90% to 70% as the angle changes from 70° to 50°, while for VIS film, the decrease is only from 90% to 85%. A low transmittance with less than 1% is found for VIS film, while that of NIR film is below 20%. We also find that the NIR film shows more spectrum variation with wavelength and combining more sheets can result in a 10% higher reflectance. For both NIR and VIS films, the measured permittivity is about 2.5 ∼ 2.7 between 2 GHz and 12 GHz.