High-speed Opto-electronic Pre-processing of Polar Mellin Transform for Shift, Scale and Rotation Invariant Image Recognition at Record-Breaking Speeds
arxiv(2023)
摘要
Space situational awareness demands efficient monitoring of terrestrial sites
and celestial bodies, necessitating advanced target recognition systems.
Current target recognition systems exhibit limited operational speed due to
challenges in handling substantial image data. While machine learning has
improved this scenario, highresolution images remain a concern. Optical
correlators, relying on analog processes, provide a potential alternative but
are hindered by material limitations. Recent advancements in hybrid
opto-electronic correlators (HOC) have addressed such limitations, additionally
achieving shift, scale, and rotation invariant (SSRI) target recognition
through use of the polar Mellin transform (PMT). However, there are currently
no techniques for obtaining the PMT at speeds fast enough to take advantage of
the inherent speed of the HOC. To that end, we demonstrate an optoelectronic
PMT pre-processor that can operate at record-breaking millisecond frame rates
using commercially available components for use in an automated SSRI HOC image
recognition system for space situational awareness.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要