In real world monitoring applications, moving object detection remains to be a challenging task due to factors such as background clutter and motion, illumination variations, weather conditions, noise, and occlusions. As a fundamental first step in many computer vision applications such as object tracking, behavior understanding, object or event recognition, and automated video surveillance, various motion detection algorithms have been developed ranging from simple approaches to more sophisticated ones. In this thesis, we present two moving object detection frameworks. The first framework is designed for robust detection of moving and static objects in videos acquired from stationary cameras. This method exploits the benefits of fusing a motion computation method based on spatio-temporal tensor formulation, a novel foreground and background modeling scheme, and a multi-cue appearance comparison. This hybrid system can handle challenges such as shadows, illumination changes, dynamic background, stopped and removed objects. Extensive testing performed on the CVPR 2014 Change Detection benchmark dataset shows that FTSG outperforms most state-of-the-art methods. The second framework adapts moving object detection to full motion videos acquired from moving airborne platforms. This framework has two main modules. The first module stabilizes the video with respect to a set of base-frames in the sequence. The stabilization is done by estimating four-point homographies using prominent feature (PF) block matching, motion filtering and RANSAC for robust matching. Once the frame to base frame homographies are available the flux tensor motion detection module using local second derivative information is applied to detect moving salient features. Spurious responses from the frame boundaries and other post- processing operations are applied to reduce the false alarms and produce accurate moving blob regions that will be useful for tracking.