This paper describes two practical fusion techniques (hybrid fusion and cued fusion) for automatic target cueing that combine features derived from each sensor data at the object-level. In the hybrid fusion method each of the input sensor data is prescreened (i.e. Automatic Target Cueing (ATC) is performed) before the fusion stage. The cued fusion method assumes that one of the sensors is designated as a primary sensor, and thus ATC is only applied to its input data. If one of the sensors exhibits a higher Pd and/or a lower false alarm rate, it can be selected as the primary sensor. However, if the ground coverage can be segmented to regions in which one of the sensors is known to exhibit better performance, then the cued fusion can be applied locally/adaptively by switching the choice of a primary sensor. Otherwise, the cued fusion is applied both ways (each sensor as primary) and the outputs of each cued mode are combined. Both fusion approaches use a back-end discrimination stage that is applied to a combined feature vector to reduce false alarms. The two fusion processes were applied to spectral and radar sensor data and were shown to provide substantial false alarm reduction. The approaches are easily extendable to more than two sensors. INTRODUCTIONRecent crisis and conflict operations have reinforced the need for broad area imagery coverage to support all stages of operations. The first utility of imagery usually takes the form of target detection/recognition and change detection. The ability to reliably and rapidly detect, discriminate and classify military targets can provide a significant tactical advantage in the battlefield. Automatic target detection and recognition (ATD/ATR) has been a focus of research for the last two decades. The performance of automatic target recognition has not yet reached the required level of recognition accuracy and speed. The complexity of the recognition process has forced the development of automatic target prescreening technologies in order to cue the complex/time-consuming recognition stage to limited/reduced data. Currently ATR processes are primarily used as a second layer for reduction of false cues (i.e., target / no target decision) and leaving the actual recognition to human operator.The limitations (high probability of detection/recognition at an unacceptable level of false alarms) of current systems utilizing a single sensing domain in addressing the various deployed CC&D techniques have led to the incorporation of multiple sensors. It is expected that the result of fusing data from multiple independent sensors will offer the potential for better performance than can be achieved by either sensor, and will reduce vulnerability to sensorspecific countermeasures and deployment factors. The first and most significant increment in performance improvement will come from multi-source fusion at the prescreening (target detection) stage. This will enable either the use of current recognition processing or will allow the application of more complex processes to ...

We present an image quality metric and prediction model for SAR imagery that addresses automated information extraction and exploitation by imagery analysts. This effort drarws on our team's direct experience with the development of the Radar National Imagery Interpretability Ratings Scale (Radar NIIRS), the General Image Quality Equations (GIQE) for other modalities, and extensive expertise in ATR characterization and performance modeling. In this study, we produced two separate GIQEs: one to predict Radar NIIRS and one to predict Automated Target Detection (ATD) performance. The Radar NIIRS GIQE is most significantly influenced by resolution, depression angle, and depression angle squared. The inclusion of several image metrics was shown to improve performance. Our development of an ATD GIQE showed that resolution and clutter characteristics (e.g., clear, forested, urban) are the dominant explanatory variables. As was the case with NIIRS GIQE, inclusion of image metrics again increased performance, but the improvement was significantly more pronounced. Analysis also showed that a strong relationship exists between ATD and Radar NIIRS, as indicated by a correlation coefficient of 0.69; however, this correlation is not strong enough that we would recommend a single GIQE be used for both ATD and NIIRS prediction.

No abstract

The application of remote sensing to the social sciences is an emerging research area. People's behavior and values shape the environment in which they live. Similarly, values and behaviors are influenced by the environment. This study explores the relationship between features observable in overhead imagery and direct measurements of attitudes obtained through surveys. We focus on three topic areas:• Income and Economic Development • Centrality and Decision Authority • Social CapitalUsing commercial satellite imagery data from rural Afghanistan, we present an exploration of the direct and indirect indicators derived from the imagery. We demonstrate a methodology for extracting relevant measures from the imagery, using a combination of human-guided and automated methods. These imagery observables indicate characteristics of the villages which will be compared to survey data in future modeling work. Preliminary survey modeling, based on data from sub-Saharan Africa, suggests that modeling of the Afghan data will also demonstrate a relationship between remote sensing data and survey-based measures of economic and social phenomena. We conclude with a discussion of the next steps, which include extensions to new regions of the world.

No abstract