Surveillance of areas of interest through image acquisition is becoming increasingly essential for intelligence services. Several types of platforms equipped with sensors are used to collect good quality images of the areas to be monitored. The evolution of this field has different levels: some studies are only based on improving the quality of the images acquired through sensors, others on the efficiency of platforms such as satellites, aircraft and vessels which will navigate the areas of interest and yet others are based on the optimization of the trajectory of these platforms. Apart from these, intelligence organizations demonstrate an interest in carrying out such missions by sharing their resources. This thesis presents a framework whose main objective is to allow intelligence organizations to carry out their observation missions by pooling their platforms with other organizations having similar or geographically close targets. This framework will use Multi-Objective Optimization algorithms based on genetic algorithms to optimize such mission planning. Research on sensor fusion will be a key point to this thesis, researchers have proven that an image resulting from the fusion of two images from different sensors can provide more information compared to the original images. Given that the main goal for observation missions is to collect quality imagery, this work will also use High-Level Information Fusion to optimize mission planning based on image quality and fusion. The results of the experiments not only demonstrate the added value of this framework but also highlight its strengths (through performance metrics) as compared to other similar frameworks.