Segmentation of independent motions from video sequences is a challenging problem that can be a prelude to many further applications in computer vision. In this paper, we present an accurate and efficient approachfor automatic segmentation of all the independently moving objects in the scene. The system begins with an
initialization module which provides initial partition of the scene, computes 2D motions, and includes some necessary preparing work. Then, we propose a novel object classification method by analyzing and clustering motions. To achieve the best robustness, and minimize the total computation load, we choose to work on multi key frames simultaneously to obtain global optimal classification. Our approach achieves accurate object classification and avoids the uncertainty in detection of moving objects. We demonstrate high stability, accuracy
and performance of our algorithm with a set of experiments on real video sequences.
Based on the difference of photonic band structures between TE and TM polarization modes in periodic multiplayer and the combining effect of one-dimensional (1D) hybrid dual-periodical photonic crystals (PCs), a novel method to design polarization band-pass filters used in wavelength division multiplexing system is presented. Such the polarization band-pass filters can be fabricated by dual-periodical TiO2/SiO2 thin film PC structures and theoretical calculation shows that they can have excellent optical properties with TM polarization transmission and TE polarization reflectance. And we try to physically discuss and explain the relation between the parameters of PC heterostructures and the optical characteristics of the filters, such as the number of TM polarization passbands, peak transmittance, half-band width and rejection and so on.