移动平台下运动目标检测的MOF算法

建立了基于摄像机焦点运动所引起的场景全局运动的视差补偿技术（MOF）。摄像机自由移动时，由于场景的景深所带来的视差问题，需要对摄像机运动引起的场景全局运动进行补偿。重点研究了摄像机视角下摄像机与图像序列间光流场之间的运动关系，并实现了表征场景全局运动的MOF模型的建立。从摄像机视角的角度，利用射影几何的关系推导出光流场的约束条件，由场景的整体运动推测摄像机的运动，从而剔除视差虚警。最后，利用实际采集的图像数据进行实验，并与相关算法进行了分析对比，最终给出了MOF算法在摄像机平移、旋转等情况下的运动目标检测效果。

MOF algorithm for moving target detection on mobile platform

Based on the global motion of the scene caused by the movement of the camera focus, a method named MOF(Motion Of Focus) was established. As the camera moved freely, the compensation of the overall movement was needed for the strong parallax caused by the depth of field. From the perspective of the camera, analysis of the compensation was performed which emphasized on the movement relation between the moving camera and optical field, and a MOF Model was given to show the characterization of the overall movement of the scene. With the camera movement speculated by the overall movement, optical flow constraints were deduced to exclude the parallax false alarm by projective geometry from the perspective of the moving camera. At the end, experiments were performed based on actual image data. And the results compared with other algorithms show that this model is practical under the translation and rotation of camera.