实现超快实时目标识别，抗平移缩放旋转变化。
Ultra-fast Real-time Target Recognition Using a Shift, Scale, and Rotation Invariant Hybrid Opto-electronic Joint Transform Correlator
- 采用光电子联合变换相关器，结合极坐标梅林变换预处理。
- 达到720帧每秒的处理速度，实现实时抗变性目标识别。
- 适用于太空态势感知等需要高速精准识别的场景。
光电子相关器（HOC）克服了全光学相关器（AOC）的诸多限制，同时保持高速运行。然而，传统配置下的HOC或AOC无法检测相对于参考图像发生旋转或缩放的目标。这一问题可通过极坐标梅林变换（PMT）预处理步骤解决，该步骤将输入图像转换为包含大部分相关信息的签名，且具有平移、缩放和旋转不变性（SSRI）。PMT需光学完成傅里叶变换，电子完成对数极坐标重映射。我们此前已展示一种流水线架构，可在720帧每秒（fps）下完成PMT运算，从而构建高效的光电子PMT预处理器。本文首次实验验证了完整HOC系统，采用改进型联合变换相关结构，实现面向太空态势感知的实时、超快SSRI目标识别。
原文摘要 · Abstract (English)
Hybrid Opto-electronic correlators (HOC) overcome many limitations of all-optical correlators (AOC) while maintaining high-speed operation. However, neither the OEC nor the AOC in their conventional configurations can detect targets that have been rotated or scaled relative to a reference. This can be addressed by using a polar Mellin transform (PMT) pre-processing step to convert input images into signatures that contain most of the relevant information, albeit represented in a shift, scale, and rotation invariant (SSRI) manner. The PMT requires the use of optics to perform the Fourier transform and electronics for a log-polar remapping step. Recently, we demonstrated a pipelined architecture that can perform the PMT at a speed of 720 frames per second (fps), enabling the construction of an efficient opto-electronic PMT pre-processor. Here, we present an experimental demonstration of a complete HOC that implements this technique to achieve real-time and ultra-fast SSRI target recognition for space situational awareness. For this demonstration, we make use of a modified version of the HOC that makes use of Joint Transform Correlation , thus rendering the system simpler and more compact.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。