基于交织序列的偏振方向映射方法

Direction of polarization, as one of the basic information in polarization imaging technology, can reflect the direction information of object surface in the scene. Therefore, the distribution of polarization direction in the scene plays an important role in the interpretation of the scene information. The conventional representation method of polarization direction has two main problems: one is high dimension of mapping results for 2-D or 3-D information mapping methods, another one is low noise-robustness of mapping methods caused by the low distance correlation of mapping relationship. A 1-D numerical value mapping method of polarization direction information based on the interleaved sequence with distance-preserving property was proposed. Firstly, the direction information was extracted from the stokes vector component as the 2-D mapping method of polarization direction. Based on the interleaved sequence method, the 2-D numerical value was mapped into the 1-D numerical value. Then, the relationship between the distance-preserving property and mapping method to noise-robustness was studied, and the distance-preserving property of the proposed mapping method of polarization direction and the conventional mapping method of polarization angle was analyzed. Finally, the simulation experiment and real-scene experiment were conducted. In the simulation experiment, the peak signal to noise ratio (PSNR) mean of the mapping results of proposed method was increased by 6% compared to the mapping method of polarization. In the real-scene experiment, the mapping results of proposed method reduced the information dimension compared to the mapping method of stokes vector and the no-reference PSNR (NRPSNR) mean of the non-negative matrix factorization (NMF) features was increased by 14% compared to the mapping method of polarization angle, which proved that the proposed mapping method has low information dimension and good noise-robustness.