生物视觉启发的颗粒全息图动静分割神经网络  

Bio-Vision-Inspired Neural Network for Dynamic-Static Segmentation of Particle Holograms

作　　者：汤铭杰 徐捷 陈振熙 熊锐 钟丽云[3] 吕晓旭[3] 田劲东 Tang Mingjie;Xu Jie;Chen Zhenxi;Xiong Rui;Zhong Liyun;LüXiaoxu;Tian Jindong(Guangdong Laboratory of Artificial Intelligence and Digital Economy(Shenzhen),Shenzhen 518100,Guangdong,China;College of Physics and Optoelectronic Engineering,Shenzhen University,Shenzhen 518060,Guangdong,China;Guangdong Provincial Key Laboratory of Nanophotonic Functional Materials and Devices,South China Normal University,Guangzhou 510006,Guangdong,China)

机构地区：[1]人工智能与数字经济广东省实验室(深圳),广东深圳518100 [2]深圳大学物理与光电工程学院,广东深圳518060 [3]华南师范大学纳米光子功能材料与器件广东省重点实验室,广东广州510006

出　　处：《光学学报》2025年第1期58-67,共10页Acta Optica Sinica

基　　金：国家自然科学基金(62075140,62005175,61727814);广东省自然科学基金(2024A1515011366)。

摘　　要：全息成像广泛应用于水体微藻、空气花粉、生物细胞等溶胶颗粒检测。通过重建算法能够获得动态目标的多种图像,如振幅、相位、形貌等,但常常受到静态颗粒背景条纹的干扰。为了解决动、静颗粒全息图的分割问题,受生物视觉对光强及光强变化具有双重敏感性的启发,设计了一种同时处理灰度图像和事件数据的神经网络算法。通过融合双模态数据并结合自监督学习,成功实现了动、静目标相互叠加全息图的完整分割及独立输出。消融实验验证了仿生模块的必要性及优越性,自监督学习的策略确保了算法的泛化性。该仿生型神经网络算法保留了溶胶颗粒全息图中的高频条纹,为后续的相位成像、三维成像等任务提供保障。Objective Holographic imaging,widely used for detecting sol particles such as microalgae,pollen,and biological cells,allows us to reconstruct various images,such as amplitude,phase,and morphology,from recorded holograms.However,these reconstructions often suffer from interference caused by background fringes of static particles.In practical applications,static particles can adhere to the optical surfaces within the imaging pathway,leading to noisy images and reduced accuracy in detecting dynamic particles.Therefore,the accurate segmentation of dynamic and static particles is crucial to enable effective downstream tasks such as two-dimensional(2D) shape and phase imaging,or three-dimensional(3D) reconstructions of the particles.To address this challenge,we propose Hformer,a biologically inspired neural network based on the Transformer architecture,designed specifically for the dynamic-static particle segmentation problem in holographic imaging.The key innovation of Hformer is its ability to process both grayscale images and event data—mimicking the dual sensitivity of biological vision to light intensity and changes in light intensity over time.By integrating these two modalities and employing self-supervised learning,Hformer achieves high-quality segmentation of holograms containing overlapping dynamic and static targets,ensuring the preservation of high-frequency fringes necessary for subsequent reconstructions.Methods Hformer incorporates several key components,including grayscale and event inputs,spiking neural network(SNN),transformer-based architecture,dual decoders,and a self-supervised learning strategy.The input to the Hformer network consists of three consecutive grayscale images,which are combined into a three-channel image.Simultaneously,these grayscale images are processed by an event generator to produce event data,capturing the dynamic changes within the scene.Hformer uses an SNN to process the event data,mimicking the biological processing of visual information through discrete spikes.The SNN eff

关 键 词：全息 图像处理 动静分割 仿生算法 神经网络 

分 类 号：O436[机械工程—光学工程]