Real-world operating conditions (OCs) influence sensor data collection, situational context assessment, human interpretation, and image fusion results. For example, the performance of a target-detection, recognition, classification, and identification system is based on a scenario involving collected information such as multimodal, multiperspective, or multiresolution images. OCs that affect image data depend on the sensor wavelength (e.g., EO, IR, and radar sensors), associated scenario phenomenology (e.g., target materials, weather, and lighting), and knowledge representation of the situation (e.g., target movements, roads). This chapter discusses OC modeling for sensors and how they affect automatic target classification (ATC) image fusion systems. The OCs are divided into four categories: target, environment, sensor, and ATC training. The purpose of this chapter is to develop a scenario-based OC-distribution model for the "real world" that can be used to realistically interpret image fusion analysis. An accurate OC theoretical model will greatly enhance the performance assessment of image fusion systems by affording Bayesian conditioning and aiding in the sensitivity assessment of image fusion performance over different OCs. Image sensor data are collected from different layered sensors.