Magnus Snorrason

OPTIMAL SEARCH FOR A MOVING TARGET: A GEOMETRIC APPROACH

The problem of optimal (or near-optimal) exhaustive search for a moving target is of importance in many civilian and military applications. Search-andrescue in open sea or in sparsely-populated areas and search missions for previously-spotted enemy targets are just a few examples. Yet, few known algorithms exist for solving this problem and none of them combine the optimal allocation of search effort with the actual computation of trajectories that a searcher must (and physically can) follow. We propose a divide-andconquer geometric approach for constructing optimal search paths for arbitrarily-shaped regions of interest. The technique is both generalizable to multiple search agents and extensible in that additional real-life search requirements (maneuverability constraints, additional information about the sensor, etc.) can be incorporated into the existing framework. Another novelty of our approach is the ability to optimally deal with a search platform which, due to design constraints, can only perform detection while moving along straight-line sweeps.

Learn sesame a learning agent engine

Open Sesame! 1.0-released in 1993-was the worlds first commercial user interface learning agent. The development of this agent involved a number of decisions about basic design issues that had not been previously addressed, including the expected types of agents and the preferred form and frequency of interaction. In the 2 years after shipping Open Sesame! 1.0, we have compiled a rich database of customer feedback. Many of our design choices have been validated by the general approval of our customers, while some were not received as favorably. Thanks to the overwhelming amount of feedback, we were able to substantially improve the design for Open Sesame! 2.0 and develop a cross-platform learning engine-Learn Sesame-that can be used to add learning agent functionality to any third-party application. In this article, we present a summary of the lessons learned from customer feedback, an outline of resulting design changes, the details of the developed learning agent engine, and planned research.

SEARCH PATH OPTIMIZATION FOR UAVS USING STOCHASTIC SAMPLING WITH ABSTRACT PATTERN DESCRIPTORS

The problem of generating the optimal search path for an unmanned aerial vehicle to locate a potentially moving target is of importance in many civilian and military applications. Search-and-rescue in open sea or in sparsely-populated areas and search missions for previously-spotted enemy targets are just a few examples. Few algorithms exist for solving this problem, and our solution is novel in that it combines the optimal allocation of search effort with the actual computation of trajectories that a searcher must (and physically can) follow. Our approach exploits the target’s spatial mobility constraints to derive accurate regions of interest, and then utilizes the geometric properties of a region of interest to decompose the overall search problem into a set of simpler search problems. Our approach involves applying computational geometry methods to partition the complex search region into minimallyoverlapping compact sub-regions. This enables closed-form computation of a flight trajectory for each sub-region, such that path length is min imized while full coverage is guaranteed and constraints of the airframe and sensor are met. The novelty of our solution described in this paper lies in how we optimize the global sequencing of individual trajectories into a complete near-optimal search path that covers the whole complex search region. We use the concept of abstract pattern descriptors to simplify the representation of each search pattern. A stochastic Metropolis sampling approach with Markov random fields is then used in conjunction with a simulated annealing algorithm to derive the near optimal global search path for each isochronal contour.

An image metric-based ATR performance prediction testbed

Automatic target detection (ATD) systems process imagery to detect and locate targets in imagery in support of a variety of military missions. Accurate prediction of ATD performance would assist in system design and trade studies, collection management, and mission planning. A need exists for ATD performance prediction based exclusively on information available from the imagery and its associated metadata. We present a predictor based on image measures quantifying the intrinsic ATD difficulty on an image. The modeling effort consists of two phases: a learning phase, where image measures are computed for a set of test images, the ATD performance is measured, and a prediction model is developed; and a second phase to test and validate performance prediction. The learning phase produces a mapping, valid across various ATR algorithms, which is even applicable when no image truth is avail-able (e.g., when evaluating denied area imagery). The testbed has plug-in capability to allow rapid evaluation of new ATR algorithms. The image measures employed in the model include: statistics derived from a constant false alarm rate (CFAR) processor, the power spectrum signature, and others. We present a performance predictor using a trained classifier ATD that was constructed using GENIE, a tool developed at Los Alamos National Laboratory. The paper concludes with a discussion of future research.

Sequential correction of perspective warp in camera-based documents

Documents captured with hand-held devices, such as digital cameras often exhibit perspective warp artifacts. These artifacts pose problems for OCR systems which at best can only handle in-plane rotation. We propose a method for recovering the planar appearance of an input document image by examining the vertical rate of change in scale of features in the document. Our method makes fewer assumptions about the document structure than do previously published algorithms.

Vision-based obstacle detection and path planning for planetary rovers

NASAs next-generation Mars rovers are capable of capturing panoramic stereo imagery of their surroundings. Three- dimensional terrain maps can be derived from such imagery through stereo image correlation. While 3-D data is inherently valuable for planning a path through local terrain, obstacle detection is not fully reliable due to anomalies and noise in the range data. We present an obstacle-detection approach that first identifies potential obstacles based on color-contrast in the monocular imagery and then uses the 3-D data to project all detected obstacles into a 2-D overhead-view obstacle map where noise originating from the 3-D data is easily removed. We also developed a specialized version of the A* search algorithm that produces optimally efficient paths through the obstacle map. These paths are of similar quality as those generated by the traditional A* , at a fraction of the computational cost. Performance gains by an order of magnitude are accomplished by a two-stage approach that leverages the specificity of obstacle shape on Mars. The first stage uses depth-first A* to quickly generate a somewhat sub-optimal path through the obstacle map. The following refinement stage efficiently eliminates all extraneous way-points. Our implementation of these algorithms is being integrated into NASAs award-winning Web-Interface for Telescience.

A Systems View of Scale Space

Over the last 30 years, scale space representations have emerged as a fundamental tool for allowing systems to become increasingly robust against changes in camera viewpoint. Unfortunately, the implementation details that are required to properly construct a scale space representation are not published in the literature. Incorrectly implementing these details will lead to extremely poor system performance. In this paper, we address the practical considerations associated with scale space representations. Our focus is to make explicit how a scale space is constructed, thereby increasing the accessibility of this powerful representation to developers of computer vision systems.

Single Camera Stereo for Mobile Robot Surveillance

Mobile robot designers frequently look to computer vision to solve navigation, obstacle avoidance, and object detection problems such as those encountered in parking lot surveillance. Stereo reconstruction is a useful technique in this domain. The advantage of a single-camera stereo method versus a stereo rig is the flexibility to change the baseline distance to best match each scenario. This directly increases the robustness of the stereo algorithm and increases the effective range of the system. The challenge comes from accurately rectifying the images into an ideal stereo pair. Structure from motion (SFM) can be used to compute the camera motion between the two images, but its accuracy is limited and small errors can cause rectified images to be misaligned. We present a single-camera stereo system that incorporates a Levenberg-Marquardt minimization of rectification parameters to bring the rectified images into alignment.

Mining vibrometry signatures to determine target separability

Laser vibrometry sensors measure minute surface motion colinear with the sensors line-of-sight. If the vibrometry sensor has a high enough sampling rate, an accurate estimate of the surface vibration is measured. For vehicles with running engines, an automatic target recognition algorithm can use these measurements to produce identification estimates. The level of identification possible is a function of the distinctness of the vibration signature. This signature is dependent upon many factors, such as engine type and vehicle weight. In this paper, we present results of using data mining techniques to assess the identification potential of vibrometry data. Our technique starts with unlabeled vibrometry measurements taken from a variety of vehicles. Then an unsupervised clustering algorithm is run on features extracted from this data. The final step is to analyze the produced cluters and determine if physical vehicle characteristics can be mapped onto the clusters.

Identifying vehicles using vibrometry signatures

Laser vibrometry is an exciting new sensor technology that promises to improve automatic target recognition (ATR) performance. Sensors, such as micro-laser interferometer Doppler, measure minute vibrations on the surface of an object from a large stand-off distance. In this paper, we demonstrate a baseline ATR algorithm designed for vibrometry data that can reliably recognise military vehicles when trained and tested on similar operating conditions.