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.

This technical report describes the application of a human-visual system simulation model, a computational vision model, as a method for prediction of operator target detection or recognition performance with infrared imaging sensors. The present report correlates the simulation model's predictions with laboratory data from human observers. The eventual goal of this work is to develop a methodology that will allow reliable predictions of imaging sensor system performance without the need for repeated laboratory testing with human observers. In this report, the visual performance model (VPM) has been applied to a set of airborne, 1st generation FLIR imagery of mobile ground targets (including Scud-B mobile transporter-erector-launchers TELs). The detectability/recognizability metrics (d' values) obtained from VPM have been compared with similar laboratory data obtained using human operators. Good correlations between the VPM detectability/recognizability predictions and the human operator results were obtained during the present study (i.e., r values greater than .70). Future efforts are planned to examine VPM's utility for camouflaged targets and for 3rd generation FLIR imagery.

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

Advanced Methods and Deep Learning in Computer Vision presents advanced computer vision methods, emphasizing machine and deep learning techniques that have emerged during the past 5–10 years. The book provides clear explanations of principles and algorithms supported with applications. Topics covered include machine learning, deep learning networks, generative adversarial networks, deep reinforcement learning, self-supervised learning, extraction of robust features, object detection, semantic segmentation, linguistic descriptions of images, visual search, visual tracking, 3D shape retrieval, image inpainting, novelty and anomaly detection. This book provides easy learning for researchers and practitioners of advanced computer vision methods, but it is also suitable as a textbook for a second course on computer vision and deep learning for advanced undergraduates and graduate students. Provides an important reference on deep learning and advanced computer methods that was created by leaders in the field Illustrates principles with modern, real-world applications Suitable for self-learning or as a text for graduate courses