This book is an international collection of contributions from academia, industry and the armed forces. It addresses current and emerging Spatial Vision Models and their application to the understanding, prediction and evaluation of the tasks of target detection and recognition. The discussion in many of the chapters is framed in terms of military targets and military vision aids. However, the techniques analyses and problems are by no means limited to this area of application. The detection and recognition of an armored vehicle from a reconnaissance image are performed by the same visual system used to detect and recognize a tumor in an X-ray. The analysis of the interaction of the human visual system with night vision devices is not different from the analysis needed in the case of an operator examining structures using a remote (endoscopic) camera, etc. The book is organized into three general sections. The first covers basic modeling of central (foveal) vision and its theoretical background. The second is centered on the evaluation of model performance in applications, while the third is dedicated to aspects of peripheral vision modeling and the expansion of peripheral modeling to include visual search.

Target object detection and identification are among the primary uses for a remote sensing system. This is crucial in several fields, including environmental and urban monitoring, hazard and disaster management, and defense and military. In recent years, these analyses have used the tremendous amount of data acquired by sensors mounted on satellite, airborne, and unmanned aerial vehicle (UAV) platforms. This book promotes papers exploiting different remote sensing data for target object detection and identification, such as synthetic aperture radar (SAR) imaging and multispectral and hyperspectral imaging. Several cutting-edge contributions, which provide examples of how to select of a technology or another depending on the specific application, will be detailed.

The visual recognition problem is central to computer vision research. From robotics to information retrieval, many desired applications demand the ability to identify and localize categories, places, and objects. This tutorial overviews computer vision algorithms for visual object recognition and image classification. We introduce primary representations and learning approaches, with an emphasis on recent advances in the field. The target audience consists of researchers or students working in AI, robotics, or vision who would like to understand what methods and representations are available for these problems. This lecture summarizes what is and isn't possible to do reliably today, and overviews key concepts that could be employed in systems requiring visual categorization. Table of Contents: Introduction / Overview: Recognition of Specific Objects / Local Features: Detection and Description / Matching Local Features / Geometric Verification of Matched Features / Example Systems: Specific-Object Recognition / Overview: Recognition of Generic Object Categories / Representations for Object Categories / Generic Object Detection: Finding and Scoring Candidates / Learning Generic Object Category Models / Example Systems: Generic Object Recognition / Other Considerations and Current Challenges / Conclusions

The eventual goal of this research is to develop a method that emulates human vision and hence is consistently able to predict human performance in target detection/recognition/identification tasks. The model used for simulating human visual performance is the OptiMetrics' developed Visual Performance Model (VPM). With the inclusion of proper calibration parameters, any visual or thermal spectrum sensor can be modeled with VPM. This modeling capability will yield a design tool, which economically allows comparison of various types of sensors and displays, and eliminates the need for many operator tests of prototype devices. This will result in better system designs and may shorten the acquisition cycle for target acquisition systems. A previous research effort compared detectability (d') values resulting from laboratory target detection experiments with those predicted by VPM for first generation (1st Gen) FLIR imagery. Good correlation between VPM predictions and human operator experiments was obtained. This report documents VPM'sd' predictions for third generation (3rd Gen) FLIR imagery. Laboratory d' results for the 3rd Gen imagery were not available at the time main text was written, however, those experimental values are documented in an appendix. The d' values calculated by VPM agree well with the 3rd Gen experimental values. Based on that comparison, it appears that VPM is a valuable tool for prediction sensor and display performance.