Situation-aware framework for moving object detection in moving cameras

In this paper, we propose a situation-aware background learning scheme to detect moving objects in the dynamic background environments using moving cameras. To tackle the challenges arising from the dynamic background, we deal with four problems: false positives from inaccurate camera motion estimation, sudden scene changes such as illumination, slow moving object relative to camera movement, and motion model limitation in a dashcam video. In the experiments, the effectiveness of the proposed framework is validated on the various data sets containing the target situations.