基于功率谱压缩-平移的多通道联合变换相关识别方法研究

Recognition method for Optical Multiple Channeled Joint Transform Correlation Based on Compression and Translation of Power Spectrum

为了充分利用光学相关识别系统的空间-频谱带宽,提高光学相关识别技术的并行处理效率和识别准确度,提出了基于功率谱压缩-平移算法的多通道联合变换相关识别方法,该方法将峰值位置变化的标准差作为相关识别的判据。在输入空间光调制器的不同区域加载场景图像和N幅参考图像,然后在图像上分别叠加经迭代算法优化的相位模板,使得场景图像的傅里叶谱和每一幅参考图像的傅里叶谱在频谱面的不同空间区域相干叠加。调节相位优化算法的约束参量,使得每个通道的联合变换功率谱互不干扰,可实现N个通道的并行处理。分析了不同优化相位的傅里叶谱的局域峰值杂波均值和相关输出的峰值位置变化标准差之间的关系,并将其作为相位优选的依据。研究结果表明,在所提实验和数值模拟参数条件下,多通道联合变换相关识别系统可以在不增加经典相关识别系统复杂度的前提下,实现16通道的并行处理,这对光学相关器的实用化具有重要意义。

In order to make full use of the spatial-spectral bandwidth of optical correlation recognition system and to enhance the parallel processing efficiency and recognition accuracy of optical correlation recognition technology,a recognition method for multiple channeled joint transform correlation is proposed based on the compression and translation of power spectra,in which the standard deviation of the variation of position of correlation peak is derived to act as a new criterion for correlation recognition.The scene image and N reference images are first uploaded on the different zones of the input spatial light modulator.Then,the optimized phase maps using the iterative algorithm are superimposed onto the images.In the Fourier plane,interference will occur between the Fourier spectrum of the scene image and that of every single reference image within different zones of the Fourier plane.No interference of Fourier spectra among the reference images will appear when the restriction parameter is suitably adjusted in the phase optimization algorithm.As a result,the N channeled parallel processing without crosstalk is achieved.The relationship between the localized peak clutter mean of the Fourier spectrum with the optimized phase and the standard deviation of the variation of position of correlation peak is analyzed and utilized as a criterion for the selective preference on the optimized phase mask.The results indicate that the proposed multiple channeled joint transform correlator can achieve 16-channel correlation recognition without the increase of system complexity compared with the classical optical correlator under specific experimental conditions,which is quite important for the practicality of an optical correlator.